Incentive Compatible Regression Learning
|
|
- Abigayle Thomas
- 5 years ago
- Views:
Transcription
1 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 München 19th ACM-SIAM Symposium on Discrete Algorithms
2 Motivation Goal: learn from information held by strategic agents Agents have different interests and different ideas of a good output Manipulation to improve result, leads to bias in the training data Machine learning and (algorithmic) mechanism design Two interrelated issues: sampling and manipulation This talk: regression learning Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 2
3 Outline The Model Regression Learning The Learning Game Mechanism Design (in One Slide) Three Levels of Generality Degenerate Distributions Uniform Distributions General Distributions Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 3
4 Regression Learning Input space X Target function o : X R, distribution ρ over X (both unknown) Hypothesis space F of functions f : X R Loss function l : R 2 R Absolute loss l(a, b) = a b Squared loss l(a, b) = (a b) 2 Risk (disutility) R(f) = E x ρ [l(f(x), o(x))] associated with f F Regression learning Given training set S = {(x j, o(x j ))} j=1,...,m, x j sampled i.i.d. from ρ, find h argmin f F R(f) Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 4
5 Regression Learning with Strategic Agents Input space X Set N of strategic agents Target functions o i : X R, i N Distributions ρ i over X, i N Hypothesis space F Risk R i (f) = E x ρi [l(f(x), o i (x))] Goal: minimize E J [R J (h)], where J is a random variable distributed uniformly over N (i.e., maximize social welfare) Training set? Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 5
6 The Learning Game Agent i controls x ij, j = 1,..., m, sampled i.i.d. from ρ i y ij = o i (x ij ) is private information Agent i reveals ŷ ij, j = 1,..., m True sample S = {S i : i N}, S i = {(x ij, y ij ) : 1 j m} Training set Ŝ = {Ŝ i : i N}, Ŝ i = {(x ij, ŷ ij ) : 1 j m} Empirical Risk ˆR(f, S) = 1 S (x,y) S l(f(x), y) Empirical Risk Minimization (ERM): minimize ˆR(f, Ŝ) Two issues: sampling and manipulation Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 6
7 Mechanism Design Terminology ERM is a social choice function economically efficient, i.e., maximizes social welfare Mechanism: social choice function plus a payment function strategyproof if agent i cannot increase payoff (i.e., decrease sum of risk and payment) by revealing a ŷ ij y ij group strategyproof if no group can (weakly) increase the payoff of all members Why strategyproofness? Otherwise: no well-defined input to the learning problem, no theoretical guarantees Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 7
8 Degenerate Distributions: ERM with Absolute Loss Distribution ρ i degenerate at x i Agent i holds y i = o i (x i ) and reveals ŷ i Ŝ = {(x i, ŷ i ) : i N} h = argmin f F ˆR(f, Ŝ) = argminf F i N l(f(x i ), ŷ i ) Agent i incurs cost R i (h) = ˆR(h, Si ) = l(h(x i ), y i ) Theorem: If l is the absolute loss and F is convex, then ERM is group strategyproof. Actually: if we don t get the (real) best fit, then somebody must have lied and lost Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 8
9 ERM with Superlinear Loss Theorem: If l is superlinear, F is convex, not full on x 1,....x n, and contains at least two functions, then ERM is not strategyproof. Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 9
10 ERM with Superlinear Loss Theorem: If l is superlinear, F is convex, not full on x 1,....x n, and contains at least two functions, then ERM is not strategyproof. Example: X = R, F are the constant functions, l(a, b) = (a b) 2, N = {1, 2} Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 9
11 ERM with Superlinear Loss Theorem: If l is superlinear, F is convex, not full on x 1,....x n, and contains at least two functions, then ERM is not strategyproof. Example: X = R, F are the constant functions, l(a, b) = (a b) 2, N = {1, 2} Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 9
12 ERM with Superlinear Loss Theorem: If l is superlinear, F is convex, not full on x 1,....x n, and contains at least two functions, then ERM is not strategyproof. Example: X = R, F are the constant functions, l(a, b) = (a b) 2, N = {1, 2} Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 9
13 Uniform Distributions Distribution ρ i discrete, uniform over {x i1,..., x im } Agent i holds y ij = o i (x ij ) and reveals ŷ ij, j = 1,..., m ERM computes h = argmin f F ˆR(h, Ŝ) Agent i incurs cost R i (h) = ˆR(h, Si ) = 1 m m j=1 l(h(x ij), y ij ) Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 10
14 Uniform Distributions Distribution ρ i discrete, uniform over {x i1,..., x im } Agent i holds y ij = o i (x ij ) and reveals ŷ ij, j = 1,..., m ERM computes h = argmin f F ˆR(h, Ŝ) Agent i incurs cost R i (h) = ˆR(h, Si ) = 1 m m j=1 l(h(x ij), y ij ) ERM with absolute loss no longer strategyproof 1 0 Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 10
15 Uniform Distributions Distribution ρ i discrete, uniform over {x i1,..., x im } Agent i holds y ij = o i (x ij ) and reveals ŷ ij, j = 1,..., m ERM computes h = argmin f F ˆR(h, Ŝ) Agent i incurs cost R i (h) = ˆR(h, Si ) = 1 m m j=1 l(h(x ij), y ij ) ERM with absolute loss no longer strategyproof 1 0 Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 10
16 Uniform Distributions Distribution ρ i discrete, uniform over {x i1,..., x im } Agent i holds y ij = o i (x ij ) and reveals ŷ ij, j = 1,..., m ERM computes h = argmin f F ˆR(h, Ŝ) Agent i incurs cost R i (h) = ˆR(h, Si ) = 1 m m j=1 l(h(x ij), y ij ) ERM with absolute loss no longer strategyproof 1 0 Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 10
17 VCG to the Rescue General Mechanism due to Vickrey (1961), Clarke (1971), and Groves (1973) Perform ERM (recall: it is economically efficient) Agent i pays j i ˆR j (h, Ŝ), incurs total cost ˆR(h, Si ) + j i ˆR(h, Ŝ j ) Good news: strategyproof for any loss function Bad news in general: not group strategyproof, payments problematic in our case: payments not bounded, no obvious way to ensure individual rationality Is there a (group) strategyproof mechanism without payments? Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 11
18 Mechanisms without Payments Absolute loss function Relax efficiency requirement, consider α-efficient mechanisms Theorem (upper bound): There exists a 3-efficient, group strategyproof mechanism for constant functions over R k and homogeneous linear functions over R Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 12
19 Mechanisms without Payments Absolute loss function Relax efficiency requirement, consider α-efficient mechanisms Theorem (upper bound): There exists a 3-efficient, group strategyproof mechanism for constant functions over R k and homogeneous linear functions over R Theorem (lower bound): There is no (3 ε)-efficient, strategyproof mechanism for constant or homogeneous linear functions over R k for any k and any ε > 0 Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 12
20 Mechanisms without Payments Absolute loss function Relax efficiency requirement, consider α-efficient mechanisms Theorem (upper bound): There exists a 3-efficient, group strategyproof mechanism for constant functions over R k and homogeneous linear functions over R Theorem (lower bound): There is no (3 ε)-efficient, strategyproof mechanism for constant or homogeneous linear functions over R k for any k and any ε > 0 Conjecture: There is no α-efficient, strategyproof mechanism without payments for homogeneous linear functions over R k for k 2 and any α Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 12
21 Generalization Assume that for all f F, (a). for all i N, ˆRi (f, S) R i (f) ε 2 and (b). ˆR(f, S) 1 n i N R i (f) ε 2 Then the following holds for any mechanism: If (group) strategyproof under uniform distributions, then ε-(group) strategyproof under general distributions If α-efficient under uniform distributions, then α-efficient under general distributions up to an additive factor of ε If F has bounded complexity and sample size is Θ( log(1/δ) ε 2 ), then (a) holds with probability 1 δ (b) holds if (a) holds for all i, increasing the sample size by a log N factor Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 13
22 Discussion For m large enough, any loss function, any function class: VCG is ε-strategyproof with probability 1 δ For m large enough, absolute loss, constant functions: there exists a mechanism without payments that is ε-group strategyproof and 3-efficient (up to additive ε) Future work: Settle impossibility conjecture for homogeneous linear functions over R k Extend to other settings, e.g. classification Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 14
23 Thank you for your attention! Dekel, Fischer, Procaccia Incentive Compatible Regression Learning 15
Algorithmic Stability and Generalization Christoph Lampert
Algorithmic Stability and Generalization Christoph Lampert November 28, 2018 1 / 32 IST Austria (Institute of Science and Technology Austria) institute for basic research opened in 2009 located in outskirts
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 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 informationTighter Bounds for Facility Games
Tighter Bounds for Facility Games Pinyan Lu 1, Yajun Wang 1, and Yuan Zhou 1 Microsoft Research Asia {pinyanl, yajunw}@microsoft.com Carnegie Mellon University yuanzhou@cs.cmu.edu Abstract. In one dimensional
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 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 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 informationMechanism Design: Dominant Strategies
May 20, 2014 Some Motivation Previously we considered the problem of matching workers with firms We considered some different institutions for tackling the incentive problem arising from asymmetric information
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 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 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 information12. Structural Risk Minimization. ECE 830 & CS 761, Spring 2016
12. Structural Risk Minimization ECE 830 & CS 761, Spring 2016 1 / 23 General setup for statistical learning theory We observe training examples {x i, y i } n i=1 x i = features X y i = labels / responses
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 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 informationOn Decentralized Incentive Compatible Mechanisms for Partially Informed Environments
On Decentralized Incentive Compatible Mechanisms for Partially Informed Environments by Ahuva Mu alem June 2005 presented by Ariel Kleiner and Neil Mehta Contributions Brings the concept of Nash Implementation
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 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 informationIntroduction to Machine Learning (67577) Lecture 3
Introduction to Machine Learning (67577) Lecture 3 Shai Shalev-Shwartz School of CS and Engineering, The Hebrew University of Jerusalem General Learning Model and Bias-Complexity tradeoff Shai Shalev-Shwartz
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 informationMechanism Design: Basic Concepts
Advanced Microeconomic Theory: Economics 521b Spring 2011 Juuso Välimäki Mechanism Design: Basic Concepts The setup is similar to that of a Bayesian game. The ingredients are: 1. Set of players, i {1,
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 informationWinner-Imposing Strategyproof Mechanisms for Multiple Facility Location Games
Winner-Imposing Strategyproof Mechanisms for Multiple Facility Location Games Dimitris Fotakis and Christos Tzamos School of Electrical and Computer Engineering, National Technical University of Athens,
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 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 informationDistributed Algorithmic Mechanism Design: Recent Results and Future Directions
Distributed Algorithmic Mechanism Design: Recent Results and Future Directions Joan Feigenbaum Yale Scott Shenker ICSI Slides: http://www.cs.yale.edu/~jf/dialm02.{ppt,pdf} Paper: http://www.cs.yale.edu/~jf/fs.{ps,pdf}
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 informationThe Sample Complexity of Revenue Maximization in the Hierarchy of Deterministic Combinatorial Auctions
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 Combinatorial
More informationIFT Lecture 7 Elements of statistical learning theory
IFT 6085 - Lecture 7 Elements of statistical learning theory This version of the notes has not yet been thoroughly checked. Please report any bugs to the scribes or instructor. Scribe(s): Brady Neal and
More informationIntroduction to Machine Learning (67577) Lecture 7
Introduction to Machine Learning (67577) Lecture 7 Shai Shalev-Shwartz School of CS and Engineering, The Hebrew University of Jerusalem Solving Convex Problems using SGD and RLM Shai Shalev-Shwartz (Hebrew
More informationLecture 2 Machine Learning Review
Lecture 2 Machine Learning Review CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago March 29, 2017 Things we will look at today Formal Setup for Supervised Learning Things
More informationRobust Mechanism Design and Robust Implementation
Robust Mechanism Design and Robust Implementation joint work with Stephen Morris August 2009 Barcelona Introduction mechanism design and implementation literatures are theoretical successes mechanisms
More informationCOMP 551 Applied Machine Learning Lecture 2: Linear Regression
COMP 551 Applied Machine Learning Lecture 2: Linear Regression Instructor: Herke van Hoof (herke.vanhoof@mail.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise
More informationSetting Lower Bounds on Truthfulness
Setting Lower Bounds on Truthfulness Ahuva Mu alem Michael Schapira Abstract We present and discuss general techniques for proving inapproximability results for truthful mechanisms. We make use of these
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 informationCOMP 551 Applied Machine Learning Lecture 2: Linear regression
COMP 551 Applied Machine Learning Lecture 2: Linear regression Instructor: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551 Unless otherwise noted, all material posted for this
More informationAn Introduction to Statistical Machine Learning - Theoretical Aspects -
An Introduction to Statistical Machine Learning - Theoretical Aspects - Samy Bengio bengio@idiap.ch Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP) CP 592, rue du Simplon 4 1920 Martigny,
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 informationThe Perceptron algorithm
The Perceptron algorithm Tirgul 3 November 2016 Agnostic PAC Learnability A hypothesis class H is agnostic PAC learnable if there exists a function m H : 0,1 2 N and a learning algorithm with the following
More informationIntroduction to Machine Learning
Introduction to Machine Learning Machine Learning: Jordan Boyd-Graber University of Maryland SUPPORT VECTOR MACHINES Slides adapted from Tom Mitchell, Eric Xing, and Lauren Hannah Machine Learning: Jordan
More informationSupport Vector Machines
Support Vector Machines Jordan Boyd-Graber University of Colorado Boulder LECTURE 7 Slides adapted from Tom Mitchell, Eric Xing, and Lauren Hannah Jordan Boyd-Graber Boulder Support Vector Machines 1 of
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 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 informationNoncooperative Games, Couplings Constraints, and Partial Effi ciency
Noncooperative Games, Couplings Constraints, and Partial Effi ciency Sjur Didrik Flåm University of Bergen, Norway Background Customary Nash equilibrium has no coupling constraints. Here: coupling constraints
More informationPre-Bayesian Games. Krzysztof R. Apt. CWI, Amsterdam, the Netherlands, University of Amsterdam. (so not Krzystof and definitely not Krystof)
Pre-Bayesian Games Krzysztof R. Apt (so not Krzystof and definitely not Krystof) CWI, Amsterdam, the Netherlands, University of Amsterdam Pre-Bayesian Games p. 1/1 Pre-Bayesian Games (Hyafil, Boutilier
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 informationMachine Learning: Chenhao Tan University of Colorado Boulder LECTURE 9
Machine Learning: Chenhao Tan University of Colorado Boulder LECTURE 9 Slides adapted from Jordan Boyd-Graber Machine Learning: Chenhao Tan Boulder 1 of 39 Recap Supervised learning Previously: KNN, naïve
More informationSum of Us: Truthful Self-Selection
Sum of Us: Truthful Self-Selection Noga Alon Felix Fischer Ariel D. Procaccia Moshe Tennenholtz Abstract We consider directed graphs over a set of n agents, where an edge (i, j is taken to mean that agent
More informationSupervised Machine Learning (Spring 2014) Homework 2, sample solutions
58669 Supervised Machine Learning (Spring 014) Homework, sample solutions Credit for the solutions goes to mainly to Panu Luosto and Joonas Paalasmaa, with some additional contributions by Jyrki Kivinen
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 informationSupport vector machines Lecture 4
Support vector machines Lecture 4 David Sontag New York University Slides adapted from Luke Zettlemoyer, Vibhav Gogate, and Carlos Guestrin Q: What does the Perceptron mistake bound tell us? Theorem: The
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 informationVoting and Mechanism Design
José M Vidal Department of Computer Science and Engineering, University of South Carolina March 26, 2010 Abstract Voting, Mechanism design, and distributed algorithmics mechanism design. Chapter 8. Voting
More informationarxiv: v1 [cs.gt] 27 May 2018
Strategyproof Linear Regression in High Dimensions Yiling Chen Chara Podimata Ariel D. Procaccia Nisarg Shah May 29, 2018 arxiv:1805.10693v1 [cs.gt] 27 May 2018 Abstract This paper is part of an emerging
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 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 informationCombinatorial Agency of Threshold Functions
Combinatorial Agency of Threshold Functions Shaili Jain 1 and David C. Parkes 2 1 Yale University, New Haven, CT shaili.jain@yale.edu 2 Harvard University, Cambridge, MA parkes@eecs.harvard.edu Abstract.
More informationGeneralization, Overfitting, and Model Selection
Generalization, Overfitting, and Model Selection Sample Complexity Results for Supervised Classification Maria-Florina (Nina) Balcan 10/03/2016 Two Core Aspects of Machine Learning Algorithm Design. How
More informationCorrelated Equilibrium in Games with Incomplete Information
Correlated Equilibrium in Games with Incomplete Information Dirk Bergemann and Stephen Morris Econometric Society Summer Meeting June 2012 Robust Predictions Agenda game theoretic predictions are very
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 informationMachine Learning. Lecture 9: Learning Theory. Feng Li.
Machine Learning Lecture 9: Learning Theory Feng Li fli@sdu.edu.cn https://funglee.github.io School of Computer Science and Technology Shandong University Fall 2018 Why Learning Theory How can we tell
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 informationDEPARTMENT OF ECONOMICS YALE UNIVERSITY P.O. Box New Haven, CT
DEPARTMENT OF ECONOMICS YALE UNIVERSITY P.O. Box 208268 New Haven, CT 06520-8268 http://www.econ.yale.edu/ Economics Department Working Paper No. 25 Cowles Foundation Discussion Paper No. 1619 Information
More informationStatistical Machine Learning Hilary Term 2018
Statistical Machine Learning Hilary Term 2018 Pier Francesco Palamara Department of Statistics University of Oxford Slide credits and other course material can be found at: http://www.stats.ox.ac.uk/~palamara/sml18.html
More informationOther-Regarding Preferences: Theory and Evidence
Other-Regarding Preferences: Theory and Evidence June 9, 2009 GENERAL OUTLINE Economic Rationality is Individual Optimization and Group Equilibrium Narrow version: Restrictive Assumptions about Objective
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 informationBayes Correlated Equilibrium and Comparing Information Structures
Bayes Correlated Equilibrium and Comparing Information Structures Dirk Bergemann and Stephen Morris Spring 2013: 521 B Introduction game theoretic predictions are very sensitive to "information structure"
More informationInformation Choice in Macroeconomics and Finance.
Information Choice in Macroeconomics and Finance. Laura Veldkamp New York University, Stern School of Business, CEPR and NBER Spring 2009 1 Veldkamp What information consumes is rather obvious: It consumes
More informationMachine Learning. Model Selection and Validation. Fabio Vandin November 7, 2017
Machine Learning Model Selection and Validation Fabio Vandin November 7, 2017 1 Model Selection When we have to solve a machine learning task: there are different algorithms/classes algorithms have parameters
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 informationMachine Learning. Linear Models. Fabio Vandin October 10, 2017
Machine Learning Linear Models Fabio Vandin October 10, 2017 1 Linear Predictors and Affine Functions Consider X = R d Affine functions: L d = {h w,b : w R d, b R} where ( d ) h w,b (x) = w, x + b = w
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 informationFull Surplus Extraction and Costless Information Revelation in Dynamic Environments. Shunya NODA (University of Tokyo)
Full Surplus Extraction and Costless Information Revelation in Dynamic Environments Shunya NODA (University of Tokyo) Outline 1. Introduction. Two-Period Example 3. Three-Period Example 4. Model 5. Main
More informationMoral hazard in teams
Division of the Humanities and Social Sciences Moral hazard in teams KC Border November 2004 These notes are based on the first part of Moral hazard in teams by Bengt Holmström [1], and fills in the gaps
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 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 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 informationInformation Acquisition in Interdependent Value Auctions
Information Acquisition in Interdependent Value Auctions Dirk Bergemann Xianwen Shi Juuso Välimäki July 16, 2008 Abstract We consider an auction environment with interdependent values. Each bidder can
More informationComputational Properties of Quasi-Strict Equilibrium
Computational roperties of Quasi-Strict Equilibrium Felix Brandt and Felix Fischer Institut für Informatik, Universität München 80538 München, Germany {brandtf,fischerf}@tcs.ifi.lmu.de Abstract. This paper
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 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 informationLecture 3: Introduction to Complexity Regularization
ECE90 Spring 2007 Statistical Learning Theory Instructor: R. Nowak Lecture 3: Introduction to Complexity Regularization We ended the previous lecture with a brief discussion of overfitting. Recall that,
More informationObvious strategyproofness needs monitoring for good approximations (extended abstract)
Obvious strategyproofness needs monitoring for good approximations (extended abstract) Diodato Ferraioli 1 and Carmine Ventre 2 1 DIEM, Università degli Studi di Salerno, Italy. dferraioli@unisa.it 2 CSEE,
More informationLecture 3: Statistical Decision Theory (Part II)
Lecture 3: Statistical Decision Theory (Part II) Hao Helen Zhang Hao Helen Zhang Lecture 3: Statistical Decision Theory (Part II) 1 / 27 Outline of This Note Part I: Statistics Decision Theory (Classical
More informationBayesian Learning (II)
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Bayesian Learning (II) Niels Landwehr Overview Probabilities, expected values, variance Basic concepts of Bayesian learning MAP
More informationMachine Learning. Regularization and Feature Selection. Fabio Vandin November 14, 2017
Machine Learning Regularization and Feature Selection Fabio Vandin November 14, 2017 1 Regularized Loss Minimization Assume h is defined by a vector w = (w 1,..., w d ) T R d (e.g., linear models) Regularization
More informationIntroduction and Models
CSE522, Winter 2011, Learning Theory Lecture 1 and 2-01/04/2011, 01/06/2011 Lecturer: Ofer Dekel Introduction and Models Scribe: Jessica Chang Machine learning algorithms have emerged as the dominant and
More informationStatistical Data Mining and Machine Learning Hilary Term 2016
Statistical Data Mining and Machine Learning Hilary Term 2016 Dino Sejdinovic Department of Statistics Oxford Slides and other materials available at: http://www.stats.ox.ac.uk/~sejdinov/sdmml Naïve Bayes
More informationImproved Bounds on the Dot Product under Random Projection and Random Sign Projection
Improved Bounds on the Dot Product under Random Projection and Random Sign Projection Ata Kabán School of Computer Science The University of Birmingham Birmingham B15 2TT, UK http://www.cs.bham.ac.uk/
More informationWelfare Maximization with Friends-of-Friends Network Externalities
Welfare Maximization with Friends-of-Friends Network Externalities Extended version of a talk at STACS 2015, Munich Wolfgang Dvořák 1 joint work with: Sayan Bhattacharya 2, Monika Henzinger 1, Martin Starnberger
More informationROBUST IMPLEMENTATION: THE CASE OF DIRECT MECHANISMS. Dirk Bergemann and Stephen Morris. March 2006 COWLES FOUNDATION DISCUSSION PAPER NO.
ROBUST IMPLEMENTATION: THE CASE OF DIRECT MECHANISMS By Dirk Bergemann and Stephen Morris March 2006 COWLES FOUNDATION DISCUSSION PAPER NO. 1561 COWLES FOUNDATION FOR RESEARCH IN ECONOMICS YALE UNIVERSITY
More informationStrategyproof Linear Regression in High Dimensions
Strategyproof Linear Regression in High Dimensions YILING CHEN, Harvard University CHARA PODIMATA, Harvard University ARIEL D. PROCACCIA, Carnegie Mellon University NISARG SHAH, University of Toronto This
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 informationClassic Mechanism Design (III)
Parkes Mechanism Design 1 Classic Mechanism Design (III) David C. Parkes Division of Engineering and Applied Science, Harvard University CS 286r Spring 2002 Parkes Mechanism Design 2 Vickrey-Clarke-Groves
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 informationAlgorithmic Game Theory and Economics: A very short introduction. Mysore Park Workshop August, 2012
Algorithmic Game Theory and Economics: A very short introduction Mysore Park Workshop August, 2012 PRELIMINARIES Game Rock Paper Scissors 0,0-1,1 1,-1 1,-1 0,0-1,1-1,1 1,-1 0,0 Strategies of Player A Strategies
More informationInformed Principal in Private-Value Environments
Informed Principal in Private-Value Environments Tymofiy Mylovanov Thomas Tröger University of Bonn June 21, 2008 1/28 Motivation 2/28 Motivation In most applications of mechanism design, the proposer
More informationPAC-learning, VC Dimension and Margin-based Bounds
More details: General: http://www.learning-with-kernels.org/ Example of more complex bounds: http://www.research.ibm.com/people/t/tzhang/papers/jmlr02_cover.ps.gz PAC-learning, VC Dimension and Margin-based
More informationVirtual Robust Implementation and Strategic Revealed Preference
and Strategic Revealed Preference Workshop of Mathematical Economics Celebrating the 60th birthday of Aloisio Araujo IMPA Rio de Janeiro December 2006 Denitions "implementation": requires ALL equilibria
More informationIntroduction to Statistical Learning Theory
Introduction to Statistical Learning Theory Definition Reminder: We are given m samples {(x i, y i )} m i=1 Dm and a hypothesis space H and we wish to return h H minimizing L D (h) = E[l(h(x), y)]. Problem
More informationOverfitting, Bias / Variance Analysis
Overfitting, Bias / Variance Analysis Professor Ameet Talwalkar Professor Ameet Talwalkar CS260 Machine Learning Algorithms February 8, 207 / 40 Outline Administration 2 Review of last lecture 3 Basic
More information