The Sample Complexity of Revenue Maximization in the Hierarchy of Deterministic Combinatorial Auctions
|
|
- Arnold Williamson
- 5 years ago
- Views:
Transcription
1 The Sample Complexity of Revenue Maximization in the Hierarchy of Deterministic Combinatorial Auctions Ellen Vitercik Joint work with Nina Balcan and Tuomas Sandholm Theory Lunch 27 April 2016
2 Combinatorial (multi-item) auctions : $5 : $5 : $6 Combinatorial auctions allow bidders to express preferences for bundles of goods
3 Real-world examples US Government wireless spectrum auctions [FCC] Sourcing auctions [Sandholm 2013] Airport time slot allocation [Rassenti 1982] Building development, e.g. office space in GHC (no money) Property sales
4 Mechanism design Mechanism designer must determine: Allocation function: Who gets what? Payment function: What does the auctioneer charge? Goal: design strategy-proof mechanisms Easy for the bidders to compute the optimal strategy Easy for designer to analyze possible outcomes
5 Warm-up: single-item auctions : $5 Second-Price Auction NINA, -$3 Allocation (N:$5, T:$3) = give carrot to Nina : $3 ø, -$0 Payment (N:$5, T:$3) = charge Nina $3 TUOMAS Second-price auction: the classic strategy-proof, single-item auction.
6 Revenue-maximizing combinatorial auctions Standard assumptions: bidders valuations drawn from distribution D, mechanism designer knows D Allocation and payment rules often depend on D
7 Revenue-maximizing combinatorial auctions Design Challenges Support of D might be doublyexponential NP-hard to determine the revenue-maximizing deterministic auction with respect to D [Conitzer and Sandholm 2002] Feasible Solutions Draw samples from D instead Fix a rich class of auctions. Can we learn the revenuemaximizing combinatorial auction in that class with respect to D given samples drawn from D? Central problem in Automated Mechanism Design [Conitzer and Sandholm 2002, 2003, 2004, Likhodedov and Sandholm 2004, 2005, 2015, Sandholm 2003] No theory that relates the performance of the designed mechanism on the samples to that mechanism s expected performance on D, until now.
8 Outline Introduction Hierarchy of deterministic combinatorial auction classes Our contribution: how many samples are needed to learn over the hierarchy of auctions? Affine maximizer auctions and Rademacher complexity Mixed-bundling auctions and pseudo-dimension Summary and future directions
9 Combinatorial auctions NINA TUOMAS : $1 : 50 : $0 : $1 : 50 : possible outcomes o = (o 1, o 2 ) For example, o = (, )
10 A natural generalization of second price NINA TUOMAS : $1 : 50 : $0 : $1 : 50 : 50 Social Welfare o = SW o = i Bidders v i o o maximizes SW o SW -i o = j Bidders i v j o o i maximizes SW -i o Allocation: o Payment: Nina pays SW Nina o Nina SW Nina o The Vickrey-Clarke-Groves mechanism (VCG).
11 VCG in action NINA TUOMAS : $1 : 50 : $0 : $1 : 50 : 50 o =, o Nina = (,, ) Nina pays v Tuomas (, ) v Tuomas ( ) = 0 How do we get the bidders to pay more?
12 Outcome boosting NINA TUOMAS : $1 : 50 : $0 : $1 : 50 : 50 value,, = v Nina + v Tuomas (, ) = 50
13 Outcome boosting NINA TUOMAS : $1 : 50 : $0 : $1 : 50 : 50 value,, = v Nina + v Tuomas (, ) = o =, o Nina = (,, )
14 Outcome boosting NINA TUOMAS : $1 : 50 : $0 : $1 : 50 : 50 value,, = v Nina + v Tuomas (, ) = o =, o Nina = (,, ) Nina pays v Tuomas (, ) + 99 v Tuomas ( ) = 99
15 Affine maximizer auctions (AMAs) Boost outcomes: λ(o) Take bids v Compute outcome: n j Bidders λ o = argmax o SW o + λ o Compute Bidder i s payment: SW i o i + λ o i SW i o + λ o
16 Affine maximizer auctions (AMAs) Boost outcomes: λ(o) Take bids v Compute outcome: o = argmax o v j o + λ o Compute Bidder i s payment: n j Bidders v j o i + λ o i v j o + λ o j Bidders {i} j Bidders {i}
17 Affine maximizer auctions (AMAs) Boost outcomes: λ(o); Weight bidders: w i Take bids v Compute outcome: o = argmax o v j o + λ o Compute Bidder i s payment: n j Bidders v j o i + λ o i v j o + λ o j Bidders {i} j Bidders {i}
18 Affine maximizer auctions (AMAs) Boost outcomes: λ(o); Weight bidders: w i Take bids v Compute outcome: o = argmax o w j v j o + λ o Compute Bidder i s payment: n j Bidders v j o i + λ o i v j o + λ o j Bidders {i} j Bidders {i}
19 Affine maximizer auctions (AMAs) Boost outcomes: λ(o); Weight bidders: w i Take bids v Compute outcome: o = argmax o w j v j o + λ o n j Bidders Compute Bidder i s payment: 1 w i w j v j o i j Bidders {i} + λ o i w j v j o j Bidders {i} + λ o
20 Hierarchy of parameterized auction classes Affine maximizer auctions [R79] w i, λ o R Virtual valuation combinatorial auctions [SL03] λ o = λ i o i Bidders λ-auctions [J07] w i = 1 λ o R Mixed bundling auctions with reserve prices [TS12] Mixed bundling auctions [J07] w i = 1 λ o = 0 except any outcome where a bidder gets all items item reserve prices w i = 1 λ o = 0 except outcome where a bidder gets all items
21 Outline Introduction Hierarchy of deterministic combinatorial auction classes Our contribution: how many samples are needed to learn over the hierarchy of auctions? Affine maximizer auctions and Rademacher complexity Mixed-bundling auctions and pseudo-dimension Summary and future directions
22 Our contribution Optimize λ o and w given a sample S~D N (Automated Mechanism Design) We want: The auction with best revenue over the sample has almost optimal expected revenue Any approximately revenue-maximizing auction over the sample will have approximately optimal expected revenue For any auction we output, we want S large enough such that: empirical revenue expected revenue < ε In other words, how many samples S = N do we need to ensure that empirical revenue expected revenue = 1 N v S rev A v E v~d rev A v for all auctions A in the class? (We can only do this with high probability.) < ε
23 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Mixed bundling auctions [J07] N = O U/ε 2
24 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Mixed bundling auctions [J07] N = O U/ε 2 Nearly-matching exponential lower bounds.
25 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Mixed bundling auctions [J07] N = O U/ε 2 Learning theory tool: Rademacher complexity
26 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Mixed bundling auctions [J07] N = O U/ε 2 Learning theory tool: Pseudo-dimension
27 Outline Introduction Hierarchy of deterministic combinatorial auction classes Our contribution: how many samples are needed to learn over the hierarchy of auctions? Affine maximizer auctions and Rademacher complexity Mixed-bundling auctions and pseudo-dimension Summary and future directions
28 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Mixed bundling auctions [J07] N = O U/ε 2
29 Key challenge Our problem... Boost outcomes: λ(o); Weight bidders: w i Take bids v Compute outcome: o = argmax o w j v j o + λ o n j Bidders Compute Bidder i s payment: 1 w i w j v j o i j Bidders {i} + λ o i w j v j o j Bidders {i} + λ o Whereas typically in machine learning
30 Rademacher complexity More expressive function classes need more samples to learn How to measure expressivity? How well do functions from the class fit random noise? Empirical Rademacher complexity: x 1,, x N ~ 1, 1 N, S = v 1,, v N 1 R S A = E x sup A A N x i rev A v i, where Rademacher complexity: R N A = E S~D N R S A With probability at least 1 δ, for all A A, empirical revenue expected revenue 2R N A + U 2 ln 2/δ N *U is the maximum revenue achievable over the support of the bidders valuation distributions
31 Rademacher complexity More expressive function classes need more samples to learn How to measure expressivity? How well do functions from the class fit random noise? Empirical Rademacher complexity: x 1,, x N ~ 1, 1 N, S = v 1,, v N 1 R S A = E x sup A A N x i rev A v i, where Rademacher complexity: R N A = E S~D N R S A A = all binary valued functions R N A = 1 2 A = one binary valued function R N A = 0
32 Rademacher complexity of AMAs Theorem Let A be the class of n-bidder, m-item AMA revenue functions. If N = O Un m m U + n m/2 /ε 2, then with high probability over a sample S~D N, empirical revenue expected revenue < ε for all rev A A. Key idea: split revenue function into its simpler components Weighted social welfare without any one bidder s participation (n components) Amount of revenue subtracted out to maintain strategyproof property Then use compositional properties of Rademacher complexity and other tricks, for example: If F = f f = g + h, g G, h H, then R N F R N G + R N H
33 Outline Introduction Hierarchy of deterministic combinatorial auction classes Our contribution: how many samples are needed to learn over the hierarchy of auctions? Affine maximizer auctions and Rademacher complexity Mixed-bundling auctions and pseudo-dimension Summary and future directions
34 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions [J07] N = O U/ε 2
35 Mixed bundling auctions (MBAs) NINA : $1 : $0 : $1 TUOMAS : 50 : 50 : 50 Class of auctions parameterized by a scalar c Boost the allocations where one bidder gets all goods by c value,, = v Nina + v Tuomas (, ) = value,, = v Nina, + v Tuomas ( ) = How large must the sample S be in order to ensure that for all MBAs, empirical revenue expected revenue < ε?
36 revenue Structural properties of MBA revenue functions Lemma Fix v S. Then rev v c is piecewise linear with at most n + 1 discontinuities. c
37 VC-dimension Complexity measure for binary-valued functions only Example: F = {single interval on the real line} No set of size 3 can be labeled in all 2 3 ways by F Class of functions F shatters set S = x 1,, x N if for all b 0, 1 N, there exists f F such that f x i = b i VC-dimension of F is the cardinality of the largest set S that can be shattered by F How can we extend VC-dim to real-valued functions?
38 Pseudo-dimension x 1 f x 1 r (1) 0 x 2 f x 2 r (2) 0 x 3 f x 3 > r (3) 1 x 4 f x 4 r (4) 0 x 5 f x 5 > r (5) 1 x 6 f x 6 r (6) 0 x 7 f x 7 > r (7) 1 x 8 f x 8 > r (8) 1 x 9 f x 9 r (9) 0 Sample S = x 1,, x N Class of functions F into U, U r = r (1),, r (N) R N witnesses the shattering of S by F if for all T S, there exists f T F such that f T x i r (i) iff x i T Pseudo-dimension of F is the cardinality of the largest sample S that can be shattered by F P-dim(F) = VC-dim( (x, r) 1 f x r>0 f F )
39 How many samples do we need? Set of auction revenue functions A with range in 0, U, distribution D over valuations v. For every ε > 0, δ 0, 1, if N = O U ε 2 P dim(a) ln U ε + ln 1 δ, then with probability at least 1 δ over a sample S~D N, empirical revenue expected revenue < ε for every rev A A. Pseudo-dimension allows us to derive strong sample complexity bounds.
40 How many samples do we need? Affine maximizer auctions [R79] N = O Un m m U + n m/2 /ε 2 Virtual valuation combinatorial auctions [SL03] N = O Un m m U + n m/2 /ε 2 λ-auctions [J07] N = O Un m m U + n m/2 /ε 2 Mixed bundling auctions with reserve prices [TS12] N = O U/ε 2 m 3 Variables N: sample size n: # bidders m: # items U: maximum revenue achievable over the support of the bidders valuation distributions Mixed bundling auctions [J07] N = O U/ε 2
41 2-bidder MBA pseudo-dimension Theorem Let A = rev c c 0 be the class of n-bidder, m-item mixed bundling auction revenue functions. Then P-dim(A) = O log n.
42 2-bidder MBA pseudo-dimension Theorem Let A = rev c c 0 be the class of 2-bidder, m-item mixed bundling auction revenue functions. Then P-dim(A) = 2. Proof sketch. Fact: there exists a set of 2 samples that is shattered by A. We need to show that no set of 3 samples can be shattered by A. Suppose, for a contradiction, that S = v 1, v 2, v 3 is shatterable. Recall v 1 = v 1 1 1, v 2 This means: There exists r = r 1, r 2, r 3 R 3 and 2 S = 8 MBA parameters C = c 1,, c 8 such that rev c1,, rev c8 induce all 8 binary labelings on S with respect to r.
43 revenue 2-bidder MBA pseudo-dimension Lemma Fix v i S. Then rev v i c is piecewise linear with one discontinuity, with a slope of 2 followed by a constant function with value i i min v 1 m, v 2 m. min v 1 i m, v 2 i m c i c
44 revenue Case 1: r 3 < min v 1 3 m, v 2 3 m min v 2 3 m, v 2 3 m r 3 c i c
45 Case 1: r 3 < min v 1 3 m, v 2 3 m rev v 3(c) increasing rev v 3 c = min v 1 3 m, v 2 3 m c 3 c
46 Case 1: r 3 < min v 1 3 m, v 2 3 m rev v 3(c) increasing rev v 3 c = min v 3 1 m, v 3 2 m rev v 2(c) increasing rev v 2 c = min v 2 1 m, v 2 2 m c 3 c 2 c
47 Case 1: r 3 < min v 1 3 m, v 2 3 m rev v 3(c) increasing rev v 3 c = min v 1 3 m, v 2 3 m rev v 2(c) increasing rev v 2 c = min v 1 2 m, v 2 2 m rev v 1(c) increasing rev v 1 c = min v 1 1 m, v 2 1 m c 3 c 2 c 1 c
48 Case 1: r 3 < min v 1 3 m, v 2 3 m rev v 3(c) increasing rev v 3 c = min v 1 3 m, v 2 3 m rev v 2(c) increasing rev v 2 c = min v 1 2 m, v 2 2 m rev v 1(c) increasing rev v 1 c = min v 1 1 m, v 2 1 m c 3 c 2 c 1 c We need: rev v 3(c) increasing rev v 2(c) increasing rev v 1(c) increasing This is impossible, so we reach a contradiction. Therefore, no set of size 3 can be shattered by the class of 2-bidder MBA revenue functions, so the pseudo-dimension is at most 2.
49 Summary Analyzed the sample complexity of learning over a hierarchy of deterministic combinatorial auctions Uncovered structural properties of these auctions revenue functions along the way Of independent interest beyond sample complexity results
arxiv: v1 [cs.lg] 13 Jun 2016
Sample Complexity of Automated Mechanism Design Maria-Florina Balcan Tuomas Sandholm Ellen Vitercik June 15, 2016 arxiv:1606.04145v1 [cs.lg] 13 Jun 2016 Abstract The design of revenue-maximizing combinatorial
More informationIntroduction to Auction Design via Machine Learning
Introduction to Auction Design via Machine Learning Ellen Vitercik December 4, 2017 CMU 10-715 Advanced Introduction to Machine Learning Ad auctions contribute a huge portion of large internet companies
More informationGame Theory: Spring 2017
Game Theory: Spring 2017 Ulle Endriss Institute for Logic, Language and Computation University of Amsterdam Ulle Endriss 1 Plan for Today In this second lecture on mechanism design we are going to generalise
More informationLecture 4. 1 Examples of Mechanism Design Problems
CSCI699: Topics in Learning and Game Theory Lecture 4 Lecturer: Shaddin Dughmi Scribes: Haifeng Xu,Reem Alfayez 1 Examples of Mechanism Design Problems Example 1: Single Item Auctions. There is a single
More informationCPS 173 Mechanism design. Vincent Conitzer
CPS 173 Mechanism design Vincent Conitzer conitzer@cs.duke.edu edu Mechanism design: setting The center has a set of outcomes O that she can choose from Allocations of tasks/resources, joint plans, Each
More informationRedistribution Mechanisms for Assignment of Heterogeneous Objects
Redistribution Mechanisms for Assignment of Heterogeneous Objects Sujit Gujar Dept of Computer Science and Automation Indian Institute of Science Bangalore, India sujit@csa.iisc.ernet.in Y Narahari Dept
More informationQuery and Computational Complexity of Combinatorial Auctions
Query and Computational Complexity of Combinatorial Auctions Jan Vondrák IBM Almaden Research Center San Jose, CA Algorithmic Frontiers, EPFL, June 2012 Jan Vondrák (IBM Almaden) Combinatorial auctions
More informationSolution: Since the prices are decreasing, we consider all the nested options {1,..., i}. Given such a set, the expected revenue is.
Problem 1: Choice models and assortment optimization Consider a MNL choice model over five products with prices (p1,..., p5) = (7, 6, 4, 3, 2) and preference weights (i.e., MNL parameters) (v1,..., v5)
More informationVickrey Auction VCG Characterization. Mechanism Design. Algorithmic Game Theory. Alexander Skopalik Algorithmic Game Theory 2013 Mechanism Design
Algorithmic Game Theory Vickrey Auction Vickrey-Clarke-Groves Mechanisms Characterization of IC Mechanisms Mechanisms with Money Player preferences are quantifiable. Common currency enables utility transfer
More informationOn Random Sampling Auctions for Digital Goods
On Random Sampling Auctions for Digital Goods Saeed Alaei Azarakhsh Malekian Aravind Srinivasan Saeed Alaei, Azarakhsh Malekian, Aravind Srinivasan Random Sampling Auctions... 1 Outline Background 1 Background
More informationAlgorithmic Game Theory Introduction to Mechanism Design
Algorithmic Game Theory Introduction to Mechanism Design Makis Arsenis National Technical University of Athens April 216 Makis Arsenis (NTUA) AGT April 216 1 / 41 Outline 1 Social Choice Social Choice
More informationPayment Rules for Combinatorial Auctions via Structural Support Vector Machines
Payment Rules for Combinatorial Auctions via Structural Support Vector Machines Felix Fischer Harvard University joint work with Paul Dütting (EPFL), Petch Jirapinyo (Harvard), John Lai (Harvard), Ben
More informationVickrey Auction. Mechanism Design. Algorithmic Game Theory. Alexander Skopalik Algorithmic Game Theory 2013 Mechanism Design
Algorithmic Game Theory Vickrey Auction Vickrey-Clarke-Groves Mechanisms Mechanisms with Money Player preferences are quantifiable. Common currency enables utility transfer between players. Preference
More informationWelfare Maximization in Combinatorial Auctions
Welfare Maximization in Combinatorial Auctions Professor Greenwald 2018-03-14 We introduce the VCG mechanism, a direct auction for multiple goods, and argue that it is both welfare-imizing and DSIC. 1
More informationCombinatorial Auction-Based Allocation of Virtual Machine Instances in Clouds
Combinatorial Auction-Based Allocation of Virtual Machine Instances in Clouds Sharrukh Zaman and Daniel Grosu Department of Computer Science Wayne State University Detroit, Michigan 48202, USA sharrukh@wayne.edu,
More informationMechanism Design and Truthful Algorithms
Mechanism Design and Truthful Algorithms Ocan Sankur 13/06/2013 Ocan Sankur (ULB) Mechanism Design and Truthful Algorithms June 13, 2013 1 / 25 Mechanism Design Mechanism design is about designing games
More informationCS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 11: Ironing and Approximate Mechanism Design in Single-Parameter Bayesian Settings
CS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 11: Ironing and Approximate Mechanism Design in Single-Parameter Bayesian Settings Instructor: Shaddin Dughmi Outline 1 Recap 2 Non-regular
More informationAPPLIED MECHANISM DESIGN FOR SOCIAL GOOD
APPLIED MECHANISM DESIGN FOR SOCIAL GOOD JOHN P DICKERSON Lecture #3 09/06/2016 CMSC828M Tuesdays & Thursdays 12:30pm 1:45pm REMINDER: SEND ME TOP 3 PRESENTATION PREFERENCES! I LL POST THE SCHEDULE TODAY
More informationKnapsack Auctions. Sept. 18, 2018
Knapsack Auctions Sept. 18, 2018 aaacehicbvdlssnafj34rpuvdelmsigvskmkoasxbtcuk9ghncfmjpn26gqszibsevojbvwvny4ucevsnx/jpm1cww8mndnnxu69x08ylcqyvo2v1bx1jc3svnl7z3dv3zw47mg4fzi0ccxi0forjixy0lzumdjlbegrz0jxh93kfvebceljfq8mcxejnoa0pbgplxnmwxxs2tu49ho16lagvjl/8hpoua6dckkhrizrtt2zytwtgeaysqtsaqvanvnlbdfoi8ivzkjkvm0lys2qubqzmi07qsqjwim0ih1noyqidlpzqvn4qpuahrhqjys4u393zcischl5ujjfus56ufif109veovmlcepihzpb4upgyqgetowoijgxsaaicyo3hxiiriik51hwydgl568tdqnum3v7bulsvo6ikmejsejqaibxiimuaut0ayypijn8arejcfjxxg3pualk0brcwt+wpj8acrvmze=
More informationA Theory of Expressiveness in Mechanisms
A Theory of Expressiveness in Mechanisms Michael Benisch, Norman Sadeh, and Tuomas Sandholm December 2007 CMU-CS-07-178 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 This work
More informationMotivation. Game Theory 24. Mechanism Design. Setting. Preference relations contain no information about by how much one candidate is preferred.
Motivation Game Theory 24. Mechanism Design Preference relations contain no information about by how much one candidate is preferred. Idea: Use money to measure this. Albert-Ludwigs-Universität Freiburg
More informationGame Theory. Lecture Notes By Y. Narahari. Department of Computer Science and Automation Indian Institute of Science Bangalore, India July 2012
Game Theory Lecture Notes By Y. Narahari Department of Computer Science and Automation Indian Institute of Science Bangalore, India July 2012 The Vickrey-Clarke-Groves Mechanisms Note: This is a only a
More informationLecture 10: Profit Maximization
CS294 P29 Algorithmic Game Theory November, 2 Lecture : Profit Maximization Lecturer: Christos Papadimitriou Scribe: Di Wang Lecture given by George Pierrakos. In this lecture we will cover. Characterization
More informationCombinatorial Auctions with Structural SVMs
Designing Incentive Compatible Payment Rules for Combinatorial Auctions with Structural SVMs A thesis presented by Pichayut Jirapinyo To Computer Science in partial fulfillment of the honors requirements
More informationCS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 7: Prior-Free Multi-Parameter Mechanism Design. Instructor: Shaddin Dughmi
CS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 7: Prior-Free Multi-Parameter Mechanism Design Instructor: Shaddin Dughmi Outline 1 Multi-Parameter Problems and Examples 2 The VCG Mechanism
More informationLecture 6: Communication Complexity of Auctions
Algorithmic Game Theory October 13, 2008 Lecture 6: Communication Complexity of Auctions Lecturer: Sébastien Lahaie Scribe: Rajat Dixit, Sébastien Lahaie In this lecture we examine the amount of communication
More informationMechanism Design with Approximate Valuations. Alessandro Chiesa Silvio Micali Zeyuan Allen Zhu
Mechanism Design with Approximate Valuations Alessandro Chiesa Silvio Micali Zeyuan Allen Zhu May 1, 2012 RQE presentation Recall 1 2 3 n Recall mechanism 1 2 3 n Recall outcome mechanism 1 2 3 n Rolex
More informationOn Greedy Algorithms and Approximate Matroids
On Greedy Algorithms and Approximate Matroids a riff on Paul Milgrom s Prices and Auctions in Markets with Complex Constraints Tim Roughgarden (Stanford University) 1 A 50-Year-Old Puzzle Persistent mystery:
More informationLecture 10: Mechanisms, Complexity, and Approximation
CS94 P9: Topics Algorithmic Game Theory November 8, 011 Lecture 10: Mechanisms, Complexity, and Approximation Lecturer: Christos Papadimitriou Scribe: Faraz Tavakoli It is possible to characterize a Mechanism
More informationModule 18: VCG Mechanism
Module 18: VCG Mechanism Information conomics c 515) George Georgiadis Society comprising of n agents. Set A of alternatives from which to choose. Agent i receives valuation v i x) if alternative x 2 A
More informationEECS 495: Combinatorial Optimization Lecture Manolis, Nima Mechanism Design with Rounding
EECS 495: Combinatorial Optimization Lecture Manolis, Nima Mechanism Design with Rounding Motivation Make a social choice that (approximately) maximizes the social welfare subject to the economic constraints
More informationCore-selecting package auctions. Han Dong, Hajir Roozbehani
Core-selecting package auctions Han Dong, Hair Roozbehani 11.11.2008 Direct Impression to the paper proposes QoS for mechanism design connects stable matching with mechanism analyses theorem deeply and
More informationWorst-Case Optimal Redistribution of VCG Payments in Multi-Unit Auctions
Worst-Case Optimal Redistribution of VCG Payments in Multi-Unit Auctions Mingyu Guo Duke University Dept. of Computer Science Durham, NC, USA mingyu@cs.duke.edu Vincent Conitzer Duke University Dept. of
More informationCS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 1: Introduction and Class Overview. Instructor: Shaddin Dughmi
CS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 1: Introduction and Class Overview Instructor: Shaddin Dughmi Outline 1 Teaser 2 Course Goals and Administrivia 3 Algorithmic Mechanism Design
More informationCS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 12: Approximate Mechanism Design in Multi-Parameter Bayesian Settings
CS599: Algorithm Design in Strategic Settings Fall 2012 Lecture 12: Approximate Mechanism Design in Multi-Parameter Bayesian Settings Instructor: Shaddin Dughmi Administrivia HW1 graded, solutions on website
More informationSequential Bidding in the Bailey-Cavallo Mechanism
Sequential Bidding in the Bailey-Cavallo Mechanism Krzysztof R. Apt 1,2 and Evangelos Markakis 2 1 CWI, Science Park 123, 1098 XG Amsterdam 2 Institute of Logic, Language and Computation, University of
More informationSimplified Mechanisms
Simplified Mechanisms A study on the applications to sponsored search by: Hajir Roozbehani, Dong Han Outline Properties of the Core Why Simplification? Simplification Theorems GSP vs VCG Package auctions
More informationComputing Optimal Outcomes under an Expressive Representation of Settings with Externalities
Computing Optimal Outcomes under an Expressive Representation of Settings with Externalities Vincent Conitzer Department of Computer Science Duke University Durham, NC 27708, USA conitzer@cs.duke.edu Tuomas
More informationMulti-object auctions (and matching with money)
(and matching with money) Introduction Many auctions have to assign multiple heterogenous objects among a group of heterogenous buyers Examples: Electricity auctions (HS C 18:00), auctions of government
More informationLecture 10: Mechanism Design
Computational Game Theory Spring Semester, 2009/10 Lecture 10: Mechanism Design Lecturer: Yishay Mansour Scribe: Vera Vsevolozhsky, Nadav Wexler 10.1 Mechanisms with money 10.1.1 Introduction As we have
More informationVickrey-Clarke-Groves Mechanisms
Vickrey-Clarke-Groves Mechanisms Jonathan Levin 1 Economics 285 Market Design Winter 2009 1 These slides are based on Paul Milgrom s. onathan Levin VCG Mechanisms Winter 2009 1 / 23 Motivation We consider
More informationLearning to Branch. Ellen Vitercik. Joint work with Nina Balcan, Travis Dick, and Tuomas Sandholm. Published in ICML 2018
Learning to Branch Ellen Vitercik Joint work with Nina Balcan, Travis Dick, and Tuomas Sandholm Published in ICML 2018 1 Integer Programs (IPs) a maximize subject to c x Ax b x {0,1} n 2 Facility location
More informationLimits on Computationally Efficient VCG-Based Mechanisms for Combinatorial Auctions and Public Projects
Limits on Computationally Efficient VCG-Based Mechanisms for Combinatorial Auctions and Public Projects Thesis by David Buchfuhrer In Partial Fulfillment of the Requirements for the Degree of Doctor of
More informationExtending characterizations of truthful mechanisms from subdomains to domains
Extending characterizations of truthful mechanisms from subdomains to domains Angelina Vidali University of Vienna, Department of Informatics December 2011 Angelina Vidali (Uni. Wien) Extending characterizations
More informationFans economy and all-pay auctions with proportional allocations
Fans economy and all-pay auctions with proportional allocations Pingzhong Tang and Yulong Zeng and Song Zuo Institute for Interdisciplinary Information Sciences Tsinghua University, Beijing, China kenshinping@gmail.com,cengyl3@mails.tsinghua.edu.cn,songzuo.z@gmail.com
More informationAlgorithmic Game Theory and Applications
Algorithmic Game Theory and Applications Lecture 18: Auctions and Mechanism Design II: a little social choice theory, the VCG Mechanism, and Market Equilibria Kousha Etessami Reminder: Food for Thought:
More informationAlgorithmic Mechanism Design
Noam Nisan, Amir Ronen - 1st part - Seminar Talk by Andreas Geiger Fakultät für Informatik Universität Karlsruhe (TH) May 5, 2007 Overview Organization Introduction Motivation Introduction to Mechanism
More informationUndominated Groves Mechanisms
Journal of Artificial Intelligence Research 46 (2013) 129-163 Submitted 09/12; published 01/13 Mingyu Guo University of Liverpool, UK Evangelos Markakis Athens University of Economics and Business, Greece
More informationAutomated mechanism design. Vincent Conitzer
Automated mechanism design Vincent Conitzer conitzer@cs.duke.edu General vs. specific mechanisms Mechanisms such as Clarke (VCG) mechanism are very general but will instantiate to something specific in
More informationMechanisms for Multi-Unit Auctions
Journal of Artificial Intelligence Research 37 (2010) 85-98 Submitted 10/09; published 2/10 Mechanisms for Multi-Unit Auctions Shahar Dobzinski Computer Science Department, Cornell University Ithaca, NY
More informationNETS 412: Algorithmic Game Theory March 28 and 30, Lecture Approximation in Mechanism Design. X(v) = arg max v i (a)
NETS 412: Algorithmic Game Theory March 28 and 30, 2017 Lecture 16+17 Lecturer: Aaron Roth Scribe: Aaron Roth Approximation in Mechanism Design In the last lecture, we asked how far we can go beyond the
More informationA Review of Auction Theory: Sequential Auctions and Vickrey Auctions
A Review of Auction Theory: and Vickrey Daniel R. 1 1 Department of Economics University of Maryland, College Park. September 2017 / Econ415 . Vickrey s. Vickrey. Example Two goods, one per bidder Suppose
More informationRevenue Monotonicity in Combinatorial Auctions
Revenue Monotonicity in Combinatorial Auctions Baharak Rastegari, Anne Condon and Kevin Leyton-Brown Department of Computer Science, University of British Columbia 2366 Main Mall, Vancouver, B.C., Canada,
More informationCS 598RM: Algorithmic Game Theory, Spring Practice Exam Solutions
CS 598RM: Algorithmic Game Theory, Spring 2017 1. Answer the following. Practice Exam Solutions Agents 1 and 2 are bargaining over how to split a dollar. Each agent simultaneously demands share he would
More informationWelfare Undominated Groves Mechanisms
Welfare Undominated Groves Mechanisms Krzysztof Apt 1,2, Vincent Conitzer 3, Mingyu Guo 3, and Evangelos Markakis 1 1 Centre for Math and Computer Science (CWI, Amsterdam, The Netherlands {apt, vangelis}@cwi.nl
More informationCS 573: Algorithmic Game Theory Lecture date: April 11, 2008
CS 573: Algorithmic Game Theory Lecture date: April 11, 2008 Instructor: Chandra Chekuri Scribe: Hannaneh Hajishirzi Contents 1 Sponsored Search Auctions 1 1.1 VCG Mechanism......................................
More informationEconomics and Computation
Economics and Computation ECON 425/563 and CPSC 455/555 Professor Dirk Bergemann and Professor Joan Feigenbaum Combinatorial Auctions In case of any questions and/or remarks on these lecture notes, please
More informationMechanism Design II. Terence Johnson. University of Notre Dame. Terence Johnson (ND) Mechanism Design II 1 / 30
Mechanism Design II Terence Johnson University of Notre Dame Terence Johnson (ND) Mechanism Design II 1 / 30 Mechanism Design Recall: game theory takes the players/actions/payoffs as given, and makes predictions
More informationOptimal Auctions with Correlated Bidders are Easy
Optimal Auctions with Correlated Bidders are Easy Shahar Dobzinski Department of Computer Science Cornell Unversity shahar@cs.cornell.edu Robert Kleinberg Department of Computer Science Cornell Unversity
More informationGame Theory: introduction and applications to computer networks
Game Theory: introduction and applications to computer networks Introduction Giovanni Neglia INRIA EPI Maestro February 04 Part of the slides are based on a previous course with D. Figueiredo (UFRJ) and
More informationMechanism Design. Christoph Schottmüller / 27
Mechanism Design Christoph Schottmüller 2015-02-25 1 / 27 Outline 1 Bayesian implementation and revelation principle 2 Expected externality mechanism 3 Review questions and exercises 2 / 27 Bayesian implementation
More informationThe Competition Complexity of Auctions: Bulow-Klemperer Results for Multidimensional Bidders
The : Bulow-Klemperer Results for Multidimensional Bidders Oxford, Spring 2017 Alon Eden, Michal Feldman, Ophir Friedler @ Tel-Aviv University Inbal Talgam-Cohen, Marie Curie Postdoc @ Hebrew University
More informationOn Ascending Vickrey Auctions for Heterogeneous Objects
On Ascending Vickrey Auctions for Heterogeneous Objects Sven de Vries James Schummer Rakesh Vohra (Zentrum Mathematik, Munich) (Kellogg School of Management, Northwestern) (Kellogg School of Management,
More informationEfficient Money Burning in General Domains
Efficient Money Burning in General Domains Dimitris Fotakis 1, Dimitris Tsipras 2, Christos Tzamos 2, and Emmanouil Zampetakis 2 1 School of Electrical and Computer Engineering, National Technical University
More informationOn the Impossibility of Black-Box Truthfulness Without Priors
On the Impossibility of Black-Box Truthfulness Without Priors Nicole Immorlica Brendan Lucier Abstract We consider the problem of converting an arbitrary approximation algorithm for a singleparameter social
More informationGame Theory. Lecture Notes By Y. Narahari. Department of Computer Science and Automation Indian Institute of Science Bangalore, India July 2012
Game Theory Lecture Notes By Y. Narahari Department of Computer Science and Automation Indian Institute of Science Bangalore, India July 2012 Myerson Optimal Auction Note: This is a only a draft version,
More informationMechanism Design. Terence Johnson. December 7, University of Notre Dame. Terence Johnson (ND) Mechanism Design December 7, / 44
Mechanism Design Terence Johnson University of Notre Dame December 7, 2017 Terence Johnson (ND) Mechanism Design December 7, 2017 1 / 44 Market Design vs Mechanism Design In Market Design, we have a very
More informationTropical Geometry in Economics
Tropical Geometry in Economics Josephine Yu School of Mathematics, Georgia Tech joint work with: Ngoc Mai Tran UT Austin and Hausdorff Center for Mathematics in Bonn ARC 10 Georgia Tech October 24, 2016
More informationMechanism Design Tutorial David C. Parkes, Harvard University Indo-US Lectures Week in Machine Learning, Game Theory and Optimization
1 Mechanism Design Tutorial David C. Parkes, Harvard University Indo-US Lectures Week in Machine Learning, Game Theory and Optimization 2 Outline Classical mechanism design Preliminaries (DRMs, revelation
More informationApproximately Revenue-Maximizing Auctions for Deliberative Agents
Approximately Revenue-Maximizing Auctions for Deliberative Agents L. Elisa Celis ecelis@cs.washington.edu University of Washington Anna R. Karlin karlin@cs.washington.edu University of Washington Kevin
More informationCS364B: Frontiers in Mechanism Design Lecture #2: Unit-Demand Bidders and Walrasian Equilibria
CS364B: Frontiers in Mechanism Design Lecture #2: Unit-Demand Bidders and Walrasian Equilibria Tim Roughgarden January 8, 2014 1 Bidders with Unit-Demand Valuations 1.1 The Setting Last lecture we discussed
More information2 Making the Exponential Mechanism Exactly Truthful Without
CIS 700 Differential Privacy in Game Theory and Mechanism Design January 31, 2014 Lecture 3 Lecturer: Aaron Roth Scribe: Aaron Roth Privacy as a Tool for Mechanism Design for arbitrary objective functions)
More informationEfficiency and strategy-proofness in object assignment problems with multi-demand preferences
Efficiency and strategy-proofness in object assignment problems with multi-demand preferences Tomoya Kazumura and Shigehiro Serizawa February 23, 2016 Abstract We consider the problem of allocating sets
More informationIncentive Compatible Regression Learning
Incentive Compatible Regression Learning Ofer Dekel 1 Felix Fischer 2 Ariel D. Procaccia 1 1 School of Computer Science and Engineering The Hebrew University of Jerusalem 2 Institut für Informatik Ludwig-Maximilians-Universität
More informationAutomated Mechanism Design
Computationally Feasible Approaches to Automated Mechanism Design by Mingyu Guo Department of Computer Science Duke University Date: Approved: Vincent Conitzer, Advisor Kamesh Munagala David Parkes Ronald
More informationMechanism Design: Bayesian Incentive Compatibility
May 30, 2013 Setup X : finite set of public alternatives X = {x 1,..., x K } Θ i : the set of possible types for player i, F i is the marginal distribution of θ i. We assume types are independently distributed.
More informationFans economy and all-pay auctions with proportional allocations
Fans economy and all-pay auctions with proportional allocations Pingzhong Tang and Yulong Zeng and Song Zuo Institute for Interdisciplinary Information Sciences Tsinghua University, Beijing, China kenshinping@gmail.com,cengyl13@mails.tsinghua.edu.cn,songzuo.z@gmail.com
More informationStability and Incentive Compatibility in a Kernel-Based Combinatorial Auction
Stability and Incentive Compatibility in a Kernel-Based Combinatorial Auction Sébastien Lahaie Yahoo! Research New York, NY 10018 lahaies@yahoo-inc.com Abstract We present the design and analysis of an
More informationThe Computational Complexity of Truthfulness in Combinatorial Auctions
The Computational Complexity of Truthfulness in Combinatorial Auctions Shahar Dobzinski, Cornell University Jan Vondrák, IBM Almaden Research Center One of the fundamental questions of Algorithmic Mechanism
More informationOn the Complexity of Computing an Equilibrium in Combinatorial Auctions
On the Complexity of Computing an Equilibrium in Combinatorial Auctions Shahar Dobzinski Hu Fu Robert Kleinberg April 8, 2014 Abstract We study combinatorial auctions where each item is sold separately
More informationRandomized Truthful Auctions of Digital Goods are Randomizations over Truthful Auctions
Randomized Truthful Auctions of Digital Goods are Randomizations over Truthful Auctions Aranyak ehta Georgia Institute of Technology 802, Atlantic Dr. Atlanta, USA aranyak@cc.gatech.edu Vijay V. Vazirani
More informationMechanism Design for Multiagent Systems
Mechanism Design for Multiagent Systems Vincent Conitzer Assistant Professor of Computer Science and Economics Duke University conitzer@cs.duke.edu Introduction Often, decisions must be taken based on
More informationIntroduction to Mechanism Design
Introduction to Mechanism Design Xianwen Shi University of Toronto Minischool on Variational Problems in Economics September 2014 Introduction to Mechanism Design September 2014 1 / 75 Mechanism Design
More informationTwo hours UNIVERSITY OF MANCHESTER SCHOOL OF COMPUTER SCIENCE. Date: Thursday 17th May 2018 Time: 09:45-11:45. Please answer all Questions.
COMP 34120 Two hours UNIVERSITY OF MANCHESTER SCHOOL OF COMPUTER SCIENCE AI and Games Date: Thursday 17th May 2018 Time: 09:45-11:45 Please answer all Questions. Use a SEPARATE answerbook for each SECTION
More informationVasilis Syrgkanis Microsoft Research NYC
Vasilis Syrgkanis Microsoft Research NYC 1 Large Scale Decentralized-Distributed Systems Multitude of Diverse Users with Different Objectives Large Scale Decentralized-Distributed Systems Multitude of
More informationMechanism Design for Resource Bounded Agents
Mechanism Design for Resource Bounded Agents International Conference on Multi-Agent Systems, ICMAS 2000 Noa E. Kfir-Dahav Dov Monderer Moshe Tennenholtz Faculty of Industrial Engineering and Management
More informationEfficiency-Revenue Trade-offs in Auctions
Efficiency-Revenue Trade-offs in Auctions Ilias Diakonikolas 1, Christos Papadimitriou 1, George Pierrakos 1, and Yaron Singer 2 1 UC Berkeley, EECS, {ilias,christos,georgios}@cs.berkeley.edu 2 Google,
More informationGraph Theoretic Characterization of Revenue Equivalence
Graph Theoretic Characterization of University of Twente joint work with Birgit Heydenreich Rudolf Müller Rakesh Vohra Optimization and Capitalism Kantorovich [... ] problems of which I shall speak, relating
More informationarxiv: v1 [cs.gt] 11 Jun 2015
The Pseudo-Dimension of Near-Optimal Auctions JAMIE MORGENSTERN TIM ROUGHGARDEN June 2, 205 arxiv:506.03684v [cs.gt] Jun 205 Abstract This paper develops a general approach, rooted in statistical learning
More informationSelling in Exclusive Markets: Some Observations on Prior-free Mechanism Design
Selling in Exclusive Markets: Some Observations on Prior-free Mechanism Design Anna R. Karlin 1 C. Thach Nguyen 1 Yuval Peres 2 March 1, 2012 Abstract We consider prior-free benchmarks in non-matroid settings.
More informationOptimal False-name-proof Single-Item Redistribution Mechanisms
Optimal False-name-proof Single-Item Redistribution Mechanisms Shunsuke Tsuruta 1, Masaaki Oka 1, Taiki Todo 1, Yujiro Kawasaki 1, Mingyu Guo 2, Yuko Sakurai 1, and Makoto Yokoo 1 1 Kyushu University,
More informationMulti-object auction design: revenue maximization with no wastage
Multi-object auction design: revenue maximization with no wastage Tomoya Kazumura Graduate School of Economics, Osaka University Debasis Mishra Indian Statistical Institute, Delhi Shigehiro Serizawa ISER,
More informationCollusion-Resilient Revenue In Combinatorial Auctions
Collusion-Resilient Revenue In Combinatorial Auctions Silvio Micali and Paul Valiant December 11, 2007 Abstract Little is known about generating revenue in combinatorial auctions in particular, the VCG
More informationNTU IO (I) : Auction Theory and Mechanism Design II Groves Mechanism and AGV Mechansim. u i (x, t i, θ i ) = V i (x, θ i ) + t i,
Meng-Yu Liang NTU O : Auction Theory and Mechanism Design Groves Mechanism and AGV Mechansim + 1 players. Types are drawn from independent distribution P i on [θ i, θ i ] with strictly positive and differentiable
More informationTruthful Auction for Cooperative Communications with Revenue Maximization
Truthful Auction for Cooperative Communications with Maximization Dejun Yang, Xi Fang, and Guoliang Xue Abstract Auction theory has been applied to cooperative communications to either efficiently allocate
More informationResilient Mechanisms For Truly Combinatorial Auctions
Resilient Mechanisms For Truly Combinatorial Auctions Silvio Micali and Paul Valiant November 7, 2008 Abstract Dominant-strategy truthfulness is traditionally considered the best possible solution concept
More informationVC dimension and Model Selection
VC dimension and Model Selection Overview PAC model: review VC dimension: Definition Examples Sample: Lower bound Upper bound!!! Model Selection Introduction to Machine Learning 2 PAC model: Setting A
More informationOnline Auctions with Re-usable Goods
Online Auctions with Re-usable Goods Mohammad T. Hajiaghayi Robert D. Kleinberg Mohammad Mahdian David C. Parkes ABSTRACT This paper concerns the design of mechanisms for online scheduling in which agents
More informationCompetitiveness via Consensus
Competitiveness via Consensus Andrew V Goldberg goldberg@microsoftcom Jason D Hartline hartline@cswashingtonedu Abstract We introduce the following consensus estimate problem Several processors hold private
More informationTruthful and Fair Resource Allocation
Truthful and Fair Resource Allocation The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters. Citation Accessed Citable Link Terms of
More information