Advanced Machine Learning

Size: px
Start display at page:

Download "Advanced Machine Learning"

Transcription

1 Advanced Machine Learning Follow-he-Perturbed Leader MEHRYAR MOHRI COURAN INSIUE & GOOGLE RESEARCH.

2 General Ideas Linear loss: decomposition as a sum along substructures. sum of edge losses in a tree. includes expert setting. sum of edge losses along a path. sum of other substructures losses in a discrete problem. page 2

3 FPL General linear decision problem: w t 2 W R N player selects,. x t 2 X R N player incurs loss, sup w x apple R. player receives,. Objective: minimize cumulative loss or regret. M(x) = argmin Notation:. w t x t X {x: kxk 1 apple X 1 } w2w w2w,x2x w x l 1 -diam(w) apple W 1 (Kalai and Vempala, 2004) page 3

4 FL Follow the Leader (FL): use play). at every round (aka fictitious FL problem: Suppose and consider a sequence 0 starting with and then alternating and. hen, 1/2 M N =2 FL incurs loss 1 at every round, overall. any single expert incurs loss overall. /2 ( 1 0 ) ( 0 1 ) page 4

5 FPL Algorithms Additive bound Follow the Perturbed Leader (FPL):. Multiplicative bound Follow the Perturbed Leader (FPL*): p t U([0, 1/ ] N ) w t = argmin w2w P t 1 s=1 w x s + w p t = M(x 1:t 1 + p t ). p t f(x) = 2 e kxk 1 Laplacian with density. w t = argmin w2w P t 1 s=1 w x s + w p t = M(x 1:t 1 + p t ). (Hannan 1957; Kalai and Vempala, 2004) page 5

6 FPL - Bound >0 heorem: fix. hen, the expected cumulative loss of additive FPL( ) is bounded as follows For = E[L ] apple L min + RX 1 + W 1. r W1 RX 1 E[L ] apple L min +2 p X 1 W 1 R. page 6

7 FPL* - Bound >0 heorem: fix and assume that. hen, the expected cumulative loss of (multiplicative) FPL*( /2X 1 ) is bounded as follows For =min q E[L ] apple L min +4 1/2X 1, L min q W, X R N + E[L ] apple (1 + )L min + 2X 1W 1 (1 + log N) W 1 (1 + log N)/X 1 L min X 1W 1 (1 + log N)+4X 1 W 1 (1 + log N).. page 7

8 Proof Outline Be the perturbed leader (BPL): w t = M(x 1:t + p t ). 1. Bound on regret of BPL: E[R (BPL)] apple W Bound on difference of regrets of FPL and BPL: E[M(x 1:t 1 + p 1 ) x t ] E[M(x 1:t + p 1 ) x t ]. 3. Difference of expectations small because similar distributions. page 8

9 Proof: BL Regret Lemma 1: P M(x 1:t) x t apple M(x 1: ) x 1:. Proof: case =1 is clear. By induction, X+1 M(x 1:t ) x t apple M(x 1: ) x 1: + M(x 1: +1 ) x +1 apple M(x 1: +1 ) x 1: + M(x 1: +1 ) x +1 (induction) (def. of M(x 1: ) as minimizer) = M(x 1: +1 ) x 1: +1. page 9

10 Proof: BPL Regret p 0 =0 Lemma 2: let. hen, the following holds: X X M(x 1:t + p t ) x t apple M(x 1: ) x 1: + W 1 kp t p t 1 k 1. hus, Proof: use Lemma 1 with x 0 t = x t + p t p t 1 X M(x 1:t + p t ) (x t + p t p t 1 ) apple M(x 1: + p ) (x 1: + p ) X M(x 1:t + p t ) x t apple M(x 1: ) x 1: + apple M(x 1: ) x 1: + W 1, then apple M(x 1: ) (x 1: + p ) X = M(x 1: ) x 1: + M(x 1: ) p t p t 1. X M(x1: ) M(x 1:t + p t ) p t p t 1 X p t p t 1 1. page 10

11 Proof: FPL vs. BPL Regrets p t = p 1 t>0 X M(x 1:t + p 1 ) x t apple M(x 1: ) x 1: + W 1 kp 1 k 1. Proof: for the expected loss, we can just choose all, which yields: hus, X E[M(x 1:t 1 + p 1 ) x t ] = apple X E[M(x 1:t 1 + p 1 ) x t ] E[M(x 1:t + p 1 ) x t ]+E[M(x 1:t + p 1 ) x t ] X h E[M(x 1:t 1 + p 1 ) x t ] E[M(x 1:t + p 1 ) x t ] i + L min + W 1 kp 1 k 1. for page 11

12 Proof: FPL By definition of the perturbation,. x 1:t + p 1 x 1:t 1 + p 1 Now, and both follow a uniform distribution over a cube. hus, wo cubes and overlap over at least the fraction : if but then for at least one i, most. kp 1 k 1 apple 1 E[M(x 1:t 1 + p 1 ) x t ] E[M(x 1:t + p 1 ) x t ] apple R(1 fraction of overlap). [0, 1/ ] N v +[0, 1/ ] N (1 kvk 1 ) x 2 [0, 1/ ] N x 62 v +[0, 1/ ] N x i 62 v i +[0, 1/ ] N v i 0 v i 1/ v i +1/, which has probability at v i mass page 12

13 Proof: FPL hus, E[M(x 1:t 1 + p 1 ) x t ] E[M(x 1:t + p 1 ) x t ] apple R kx t k 1 apple R X 1. And, E[R ] apple R X 1 + W 1. page 13

14 Proof: FPL* Lemma 3: E[M(x 1:t 1 + p 1 ) x t ] apple e X 1 E[M(x 1:t + p 1 ) x t ]. Proof: E[M(x 1:t 1 + p 1 ) x t ] Z = M(x 1:t 1 + u) x t dµ(u) R Z N = M(x 1:t + v) x t dµ(x t + v) (change of var. v = u + x t ) R Z N = M(x 1:t + v) x t e kx t+vk 1 kvk 1 {z } d(v) R N applee X 1 apple e X 1 E[M(x 1:t + p 1 ) x t ]. page 14

15 Proof: FPL* apple 1/X 1 For,, thus, X E[M(x 1:t 1 + p 1 ) x t ] apple hus, h i E[kp 1 k 1 ]=E max p 1,i i2[1,n] e X 1 apple (1 + 2 X 1 ) = apple apple 2 =2 X (1 + 2 X 1 )E[M(x 1:t + p 1 ) x t ] X Z +1 0 Z +1 0 Z u 0 apple 2u + N (1 + 2 X 1 )(L min + W 1 E[kp 1 k 1 ]). h i Pr max p 1,i >t dt i2[1,n] h i Pr max p 1,i >t dt i2[1,n] h i Pr max p 1,i >t dt + i2[1,n] Z +1 u =2u + N e u Pr apple h i p 1,1 >t dt 2(1 + log N) Z +1 u h i Pr max p 1,i >t dt i2[1,n] (best choice of u). page 15

16 Expert Setting W 1 =1X 1 = N R =1,, and ; for FLP*( ), E[L ] apple (1 + 2N )L min + 2(1+log(N). More favorable bound: x t! x t,1 e 1...x t,n e N. new L min N = old L min. E[L old ] apple E[L new N]. new guarantee: for FLP*( ), E[L ] apple (1 + 2 )L min + 2(1+log(N)). E[R ] apple 2 p 2L min (1 + log(n)). page 16

17 RWM = FPL Let FPL( ) be an instance of the general FPL algorithm with a perturbation defined by apple log( log(u1 )) p 1 =,..., log( log(u > N )), where u j is drawn according to the uniform distribution over [0, 1]. hen, FPL( ) and RWM( ) coincide. page 17

18 References Nicolò Cesa-Bianchi, Alex Conconi, Claudio Gentile: On the Generalization Ability of On-Line Learning Algorithms. IEEE ransactions on Information heory 50(9): Nicolò Cesa-Bianchi and Gábor Lugosi. Prediction, learning, and games. Cambridge University Press, Yoav Freund and Robert Schapire. Large margin classification using the perceptron algorithm. In Proceedings of COL ACM Press, Adam. Kalai, Santosh Vempala. Efficient algorithms for online decision problems. J. Comput. Syst. Sci. 71(3): Nick Littlestone. From On-Line to Batch Learning. COL 1989: Nick Littlestone. "Learning Quickly When Irrelevant Attributes Abound: A New Linear-threshold Algorithm" Machine Learning (2) page 18

19 References Nick Littlestone, Manfred K. Warmuth: he Weighted Majority Algorithm. FOCS 1989: om Mitchell. Machine Learning, McGraw Hill, Novikoff, A. B. (1962). On convergence proofs on perceptrons. Symposium on the Mathematical heory of Automata, 12, Polytechnic Institute of Brooklyn. page 19

Foundations of Machine Learning On-Line Learning. Mehryar Mohri Courant Institute and Google Research

Foundations of Machine Learning On-Line Learning. Mehryar Mohri Courant Institute and Google Research Foundations of Machine Learning On-Line Learning Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Motivation PAC learning: distribution fixed over time (training and test). IID assumption.

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Learning with Large Expert Spaces MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Problem Learning guarantees: R T = O( p T log N). informative even for N very large.

More information

Learning with Large Number of Experts: Component Hedge Algorithm

Learning with Large Number of Experts: Component Hedge Algorithm Learning with Large Number of Experts: Component Hedge Algorithm Giulia DeSalvo and Vitaly Kuznetsov Courant Institute March 24th, 215 1 / 3 Learning with Large Number of Experts Regret of RWM is O( T

More information

Perceptron Mistake Bounds

Perceptron Mistake Bounds Perceptron Mistake Bounds Mehryar Mohri, and Afshin Rostamizadeh Google Research Courant Institute of Mathematical Sciences Abstract. We present a brief survey of existing mistake bounds and introduce

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Learning and Games MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Outline Normal form games Nash equilibrium von Neumann s minimax theorem Correlated equilibrium Internal

More information

Learning, Games, and Networks

Learning, Games, and Networks Learning, Games, and Networks Abhishek Sinha Laboratory for Information and Decision Systems MIT ML Talk Series @CNRG December 12, 2016 1 / 44 Outline 1 Prediction With Experts Advice 2 Application to

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Online Convex Optimization MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Outline Online projected sub-gradient descent. Exponentiated Gradient (EG). Mirror descent.

More information

Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs

Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs Elad Hazan IBM Almaden 650 Harry Rd, San Jose, CA 95120 hazan@us.ibm.com Satyen Kale Microsoft Research 1 Microsoft Way, Redmond,

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Bandit Problems MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Multi-Armed Bandit Problem Problem: which arm of a K-slot machine should a gambler pull to maximize his

More information

Exponential Weights on the Hypercube in Polynomial Time

Exponential Weights on the Hypercube in Polynomial Time European Workshop on Reinforcement Learning 14 (2018) October 2018, Lille, France. Exponential Weights on the Hypercube in Polynomial Time College of Information and Computer Sciences University of Massachusetts

More information

New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

New bounds on the price of bandit feedback for mistake-bounded online multiclass learning Journal of Machine Learning Research 1 8, 2017 Algorithmic Learning Theory 2017 New bounds on the price of bandit feedback for mistake-bounded online multiclass learning Philip M. Long Google, 1600 Amphitheatre

More information

From Bandits to Experts: A Tale of Domination and Independence

From Bandits to Experts: A Tale of Domination and Independence From Bandits to Experts: A Tale of Domination and Independence Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Domination and Independence 1 / 1 From Bandits to Experts: A

More information

Online Submodular Minimization

Online Submodular Minimization Journal of Machine Learning Research 13 (2012) 2903-2922 Submitted 12/11; Revised 7/12; Published 10/12 Online Submodular Minimization Elad Hazan echnion - Israel Inst. of ech. echnion City Haifa, 32000,

More information

Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs

Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs Elad Hazan IBM Almaden Research Center 650 Harry Rd San Jose, CA 95120 ehazan@cs.princeton.edu Satyen Kale Yahoo! Research 4301

More information

Efficient learning by implicit exploration in bandit problems with side observations

Efficient learning by implicit exploration in bandit problems with side observations Efficient learning by implicit exploration in bandit problems with side observations omáš Kocák Gergely Neu Michal Valko Rémi Munos SequeL team, INRIA Lille Nord Europe, France {tomas.kocak,gergely.neu,michal.valko,remi.munos}@inria.fr

More information

On the Generalization Ability of Online Strongly Convex Programming Algorithms

On the Generalization Ability of Online Strongly Convex Programming Algorithms On the Generalization Ability of Online Strongly Convex Programming Algorithms Sham M. Kakade I Chicago Chicago, IL 60637 sham@tti-c.org Ambuj ewari I Chicago Chicago, IL 60637 tewari@tti-c.org Abstract

More information

Agnostic Online learnability

Agnostic Online learnability Technical Report TTIC-TR-2008-2 October 2008 Agnostic Online learnability Shai Shalev-Shwartz Toyota Technological Institute Chicago shai@tti-c.org ABSTRACT We study a fundamental question. What classes

More information

arxiv: v2 [cs.lg] 19 Oct 2018

arxiv: v2 [cs.lg] 19 Oct 2018 Learning in Non-convex Games with an Optimization Oracle arxiv:1810.07362v2 [cs.lg] 19 Oct 2018 Alon Gonen Elad Hazan Abstract We consider adversarial online learning in a non-convex setting under the

More information

Tutorial: PART 1. Online Convex Optimization, A Game- Theoretic Approach to Learning.

Tutorial: PART 1. Online Convex Optimization, A Game- Theoretic Approach to Learning. Tutorial: PART 1 Online Convex Optimization, A Game- Theoretic Approach to Learning http://www.cs.princeton.edu/~ehazan/tutorial/tutorial.htm Elad Hazan Princeton University Satyen Kale Yahoo Research

More information

Online Learning for Time Series Prediction

Online Learning for Time Series Prediction Online Learning for Time Series Prediction Joint work with Vitaly Kuznetsov (Google Research) MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Motivation Time series prediction: stock values.

More information

A survey: The convex optimization approach to regret minimization

A survey: The convex optimization approach to regret minimization A survey: The convex optimization approach to regret minimization Elad Hazan September 10, 2009 WORKING DRAFT Abstract A well studied and general setting for prediction and decision making is regret minimization

More information

On-Line Learning with Path Experts and Non-Additive Losses

On-Line Learning with Path Experts and Non-Additive Losses On-Line Learning with Path Experts and Non-Additive Losses Joint work with Corinna Cortes (Google Research) Vitaly Kuznetsov (Courant Institute) Manfred Warmuth (UC Santa Cruz) MEHRYAR MOHRI MOHRI@ COURANT

More information

Full-information Online Learning

Full-information Online Learning Introduction Expert Advice OCO LM A DA NANJING UNIVERSITY Full-information Lijun Zhang Nanjing University, China June 2, 2017 Outline Introduction Expert Advice OCO 1 Introduction Definitions Regret 2

More information

Time Series Prediction & Online Learning

Time Series Prediction & Online Learning Time Series Prediction & Online Learning Joint work with Vitaly Kuznetsov (Google Research) MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Motivation Time series prediction: stock values. earthquakes.

More information

The Online Approach to Machine Learning

The Online Approach to Machine Learning The Online Approach to Machine Learning Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Online Approach to ML 1 / 53 Summary 1 My beautiful regret 2 A supposedly fun game I

More information

Defensive forecasting for optimal prediction with expert advice

Defensive forecasting for optimal prediction with expert advice Defensive forecasting for optimal prediction with expert advice Vladimir Vovk $25 Peter Paul $0 $50 Peter $0 Paul $100 The Game-Theoretic Probability and Finance Project Working Paper #20 August 11, 2007

More information

Theory and Applications of A Repeated Game Playing Algorithm. Rob Schapire Princeton University [currently visiting Yahoo!

Theory and Applications of A Repeated Game Playing Algorithm. Rob Schapire Princeton University [currently visiting Yahoo! Theory and Applications of A Repeated Game Playing Algorithm Rob Schapire Princeton University [currently visiting Yahoo! Research] Learning Is (Often) Just a Game some learning problems: learn from training

More information

Minimax strategy for prediction with expert advice under stochastic assumptions

Minimax strategy for prediction with expert advice under stochastic assumptions Minimax strategy for prediction ith expert advice under stochastic assumptions Wojciech Kotłosi Poznań University of Technology, Poland otlosi@cs.put.poznan.pl Abstract We consider the setting of prediction

More information

Game Theory, On-line Prediction and Boosting

Game Theory, On-line Prediction and Boosting roceedings of the Ninth Annual Conference on Computational Learning heory, 996. Game heory, On-line rediction and Boosting Yoav Freund Robert E. Schapire A& Laboratories 600 Mountain Avenue Murray Hill,

More information

A Drifting-Games Analysis for Online Learning and Applications to Boosting

A Drifting-Games Analysis for Online Learning and Applications to Boosting A Drifting-Games Analysis for Online Learning and Applications to Boosting Haipeng Luo Department of Computer Science Princeton University Princeton, NJ 08540 haipengl@cs.princeton.edu Robert E. Schapire

More information

Introduction to Machine Learning Lecture 11. Mehryar Mohri Courant Institute and Google Research

Introduction to Machine Learning Lecture 11. Mehryar Mohri Courant Institute and Google Research Introduction to Machine Learning Lecture 11 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Boosting Mehryar Mohri - Introduction to Machine Learning page 2 Boosting Ideas Main idea:

More information

The Algorithmic Foundations of Adaptive Data Analysis November, Lecture The Multiplicative Weights Algorithm

The Algorithmic Foundations of Adaptive Data Analysis November, Lecture The Multiplicative Weights Algorithm he Algorithmic Foundations of Adaptive Data Analysis November, 207 Lecture 5-6 Lecturer: Aaron Roth Scribe: Aaron Roth he Multiplicative Weights Algorithm In this lecture, we define and analyze a classic,

More information

The No-Regret Framework for Online Learning

The No-Regret Framework for Online Learning The No-Regret Framework for Online Learning A Tutorial Introduction Nahum Shimkin Technion Israel Institute of Technology Haifa, Israel Stochastic Processes in Engineering IIT Mumbai, March 2013 N. Shimkin,

More information

Online Forest Density Estimation

Online Forest Density Estimation Online Forest Density Estimation Frédéric Koriche CRIL - CNRS UMR 8188, Univ. Artois koriche@cril.fr UAI 16 1 Outline 1 Probabilistic Graphical Models 2 Online Density Estimation 3 Online Forest Density

More information

Online Learning with Feedback Graphs

Online Learning with Feedback Graphs Online Learning with Feedback Graphs Nicolò Cesa-Bianchi Università degli Studi di Milano Joint work with: Noga Alon (Tel-Aviv University) Ofer Dekel (Microsoft Research) Tomer Koren (Technion and Microsoft

More information

Lecture 14: Approachability and regret minimization Ramesh Johari May 23, 2007

Lecture 14: Approachability and regret minimization Ramesh Johari May 23, 2007 MS&E 336 Lecture 4: Approachability and regret minimization Ramesh Johari May 23, 2007 In this lecture we use Blackwell s approachability theorem to formulate both external and internal regret minimizing

More information

Online Learning. Jordan Boyd-Graber. University of Colorado Boulder LECTURE 21. Slides adapted from Mohri

Online Learning. Jordan Boyd-Graber. University of Colorado Boulder LECTURE 21. Slides adapted from Mohri Online Learning Jordan Boyd-Graber University of Colorado Boulder LECTURE 21 Slides adapted from Mohri Jordan Boyd-Graber Boulder Online Learning 1 of 31 Motivation PAC learning: distribution fixed over

More information

Advanced Machine Learning

Advanced Machine Learning Advanced Machine Learning Deep Boosting MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Outline Model selection. Deep boosting. theory. algorithm. experiments. page 2 Model Selection Problem:

More information

Classification. Jordan Boyd-Graber University of Maryland WEIGHTED MAJORITY. Slides adapted from Mohri. Jordan Boyd-Graber UMD Classification 1 / 13

Classification. Jordan Boyd-Graber University of Maryland WEIGHTED MAJORITY. Slides adapted from Mohri. Jordan Boyd-Graber UMD Classification 1 / 13 Classification Jordan Boyd-Graber University of Maryland WEIGHTED MAJORITY Slides adapted from Mohri Jordan Boyd-Graber UMD Classification 1 / 13 Beyond Binary Classification Before we ve talked about

More information

Online Learning and Online Convex Optimization

Online Learning and Online Convex Optimization Online Learning and Online Convex Optimization Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Online Learning 1 / 49 Summary 1 My beautiful regret 2 A supposedly fun game

More information

Adaptive Online Prediction by Following the Perturbed Leader

Adaptive Online Prediction by Following the Perturbed Leader Journal of Machine Learning Research 6 (2005) 639 660 Submitted 10/04; Revised 3/05; Published 4/05 Adaptive Online Prediction by Following the Perturbed Leader Marcus Hutter Jan Poland IDSIA, Galleria

More information

Optimization for Machine Learning

Optimization for Machine Learning Optimization for Machine Learning Editors: Suvrit Sra suvrit@gmail.com Max Planck Insitute for Biological Cybernetics 72076 Tübingen, Germany Sebastian Nowozin Microsoft Research Cambridge, CB3 0FB, United

More information

Online Learning of Probabilistic Graphical Models

Online Learning of Probabilistic Graphical Models 1/34 Online Learning of Probabilistic Graphical Models Frédéric Koriche CRIL - CNRS UMR 8188, Univ. Artois koriche@cril.fr CRIL-U Nankin 2016 Probabilistic Graphical Models 2/34 Outline 1 Probabilistic

More information

Online Learning: Random Averages, Combinatorial Parameters, and Learnability

Online Learning: Random Averages, Combinatorial Parameters, and Learnability Online Learning: Random Averages, Combinatorial Parameters, and Learnability Alexander Rakhlin Department of Statistics University of Pennsylvania Karthik Sridharan Toyota Technological Institute at Chicago

More information

Bandits for Online Optimization

Bandits for Online Optimization Bandits for Online Optimization Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Bandits for Online Optimization 1 / 16 The multiarmed bandit problem... K slot machines Each

More information

From Batch to Transductive Online Learning

From Batch to Transductive Online Learning From Batch to Transductive Online Learning Sham Kakade Toyota Technological Institute Chicago, IL 60637 sham@tti-c.org Adam Tauman Kalai Toyota Technological Institute Chicago, IL 60637 kalai@tti-c.org

More information

Online prediction with expert advise

Online prediction with expert advise Online prediction with expert advise Jyrki Kivinen Australian National University http://axiom.anu.edu.au/~kivinen Contents 1. Online prediction: introductory example, basic setting 2. Classification with

More information

The convex optimization approach to regret minimization

The convex optimization approach to regret minimization The convex optimization approach to regret minimization Elad Hazan Technion - Israel Institute of Technology ehazan@ie.technion.ac.il Abstract A well studied and general setting for prediction and decision

More information

Online Submodular Minimization

Online Submodular Minimization Online Submodular Minimization Elad Hazan IBM Almaden Research Center 650 Harry Rd, San Jose, CA 95120 hazan@us.ibm.com Satyen Kale Yahoo! Research 4301 Great America Parkway, Santa Clara, CA 95054 skale@yahoo-inc.com

More information

Lecture 19: UCB Algorithm and Adversarial Bandit Problem. Announcements Review on stochastic multi-armed bandit problem

Lecture 19: UCB Algorithm and Adversarial Bandit Problem. Announcements Review on stochastic multi-armed bandit problem Lecture 9: UCB Algorithm and Adversarial Bandit Problem EECS598: Prediction and Learning: It s Only a Game Fall 03 Lecture 9: UCB Algorithm and Adversarial Bandit Problem Prof. Jacob Abernethy Scribe:

More information

Tutorial: PART 2. Online Convex Optimization, A Game- Theoretic Approach to Learning

Tutorial: PART 2. Online Convex Optimization, A Game- Theoretic Approach to Learning Tutorial: PART 2 Online Convex Optimization, A Game- Theoretic Approach to Learning Elad Hazan Princeton University Satyen Kale Yahoo Research Exploiting curvature: logarithmic regret Logarithmic regret

More information

The Price of Differential Privacy for Online Learning

The Price of Differential Privacy for Online Learning Naman Agarwal Karan Singh Abstract We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal ( p T ) regret bounds.

More information

Generalization Bounds for Online Learning Algorithms with Pairwise Loss Functions

Generalization Bounds for Online Learning Algorithms with Pairwise Loss Functions JMLR: Workshop and Conference Proceedings vol 3 0 3. 3. 5th Annual Conference on Learning Theory Generalization Bounds for Online Learning Algorithms with Pairwise Loss Functions Yuyang Wang Roni Khardon

More information

Conditional Swap Regret and Conditional Correlated Equilibrium

Conditional Swap Regret and Conditional Correlated Equilibrium Conditional Swap Regret and Conditional Correlated quilibrium Mehryar Mohri Courant Institute and Google 251 Mercer Street New York, NY 10012 mohri@cims.nyu.edu Scott Yang Courant Institute 251 Mercer

More information

Adaptive Sampling Under Low Noise Conditions 1

Adaptive Sampling Under Low Noise Conditions 1 Manuscrit auteur, publié dans "41èmes Journées de Statistique, SFdS, Bordeaux (2009)" Adaptive Sampling Under Low Noise Conditions 1 Nicolò Cesa-Bianchi Dipartimento di Scienze dell Informazione Università

More information

Applications of on-line prediction. in telecommunication problems

Applications of on-line prediction. in telecommunication problems Applications of on-line prediction in telecommunication problems Gábor Lugosi Pompeu Fabra University, Barcelona based on joint work with András György and Tamás Linder 1 Outline On-line prediction; Some

More information

Online Learning Class 12, 20 March 2006 Andrea Caponnetto, Sanmay Das

Online Learning Class 12, 20 March 2006 Andrea Caponnetto, Sanmay Das Online Learning 9.520 Class 12, 20 March 2006 Andrea Caponnetto, Sanmay Das About this class Goal To introduce the general setting of online learning. To describe an online version of the RLS algorithm

More information

Lecture 8. Instructor: Haipeng Luo

Lecture 8. Instructor: Haipeng Luo Lecture 8 Instructor: Haipeng Luo Boosting and AdaBoost In this lecture we discuss the connection between boosting and online learning. Boosting is not only one of the most fundamental theories in machine

More information

Adaptive Online Gradient Descent

Adaptive Online Gradient Descent University of Pennsylvania ScholarlyCommons Statistics Papers Wharton Faculty Research 6-4-2007 Adaptive Online Gradient Descent Peter Bartlett Elad Hazan Alexander Rakhlin University of Pennsylvania Follow

More information

Machine Learning Ensemble Learning I Hamid R. Rabiee Jafar Muhammadi, Alireza Ghasemi Spring /

Machine Learning Ensemble Learning I Hamid R. Rabiee Jafar Muhammadi, Alireza Ghasemi Spring / Machine Learning Ensemble Learning I Hamid R. Rabiee Jafar Muhammadi, Alireza Ghasemi Spring 2015 http://ce.sharif.edu/courses/93-94/2/ce717-1 / Agenda Combining Classifiers Empirical view Theoretical

More information

Optimization, Learning, and Games with Predictable Sequences

Optimization, Learning, and Games with Predictable Sequences Optimization, Learning, and Games with Predictable Sequences Alexander Rakhlin University of Pennsylvania Karthik Sridharan University of Pennsylvania Abstract We provide several applications of Optimistic

More information

Worst-Case Analysis of the Perceptron and Exponentiated Update Algorithms

Worst-Case Analysis of the Perceptron and Exponentiated Update Algorithms Worst-Case Analysis of the Perceptron and Exponentiated Update Algorithms Tom Bylander Division of Computer Science The University of Texas at San Antonio San Antonio, Texas 7849 bylander@cs.utsa.edu April

More information

Gambling in a rigged casino: The adversarial multi-armed bandit problem

Gambling in a rigged casino: The adversarial multi-armed bandit problem Gambling in a rigged casino: The adversarial multi-armed bandit problem Peter Auer Institute for Theoretical Computer Science University of Technology Graz A-8010 Graz (Austria) pauer@igi.tu-graz.ac.at

More information

CS264: Beyond Worst-Case Analysis Lecture #20: From Unknown Input Distributions to Instance Optimality

CS264: Beyond Worst-Case Analysis Lecture #20: From Unknown Input Distributions to Instance Optimality CS264: Beyond Worst-Case Analysis Lecture #20: From Unknown Input Distributions to Instance Optimality Tim Roughgarden December 3, 2014 1 Preamble This lecture closes the loop on the course s circle of

More information

An Online Convex Optimization Approach to Blackwell s Approachability

An Online Convex Optimization Approach to Blackwell s Approachability Journal of Machine Learning Research 17 (2016) 1-23 Submitted 7/15; Revised 6/16; Published 8/16 An Online Convex Optimization Approach to Blackwell s Approachability Nahum Shimkin Faculty of Electrical

More information

Move from Perturbed scheme to exponential weighting average

Move from Perturbed scheme to exponential weighting average Move from Perturbed scheme to exponential weighting average Chunyang Xiao Abstract In an online decision problem, one makes decisions often with a pool of decisions sequence called experts but without

More information

Experts in a Markov Decision Process

Experts in a Markov Decision Process University of Pennsylvania ScholarlyCommons Statistics Papers Wharton Faculty Research 2004 Experts in a Markov Decision Process Eyal Even-Dar Sham Kakade University of Pennsylvania Yishay Mansour Follow

More information

Online Learning and Sequential Decision Making

Online Learning and Sequential Decision Making Online Learning and Sequential Decision Making Emilie Kaufmann CNRS & CRIStAL, Inria SequeL, emilie.kaufmann@univ-lille.fr Research School, ENS Lyon, Novembre 12-13th 2018 Emilie Kaufmann Online Learning

More information

Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization

Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization JMLR: Workshop and Conference Proceedings vol (2010) 1 16 24th Annual Conference on Learning heory Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization

More information

Lecture 3: Lower Bounds for Bandit Algorithms

Lecture 3: Lower Bounds for Bandit Algorithms CMSC 858G: Bandits, Experts and Games 09/19/16 Lecture 3: Lower Bounds for Bandit Algorithms Instructor: Alex Slivkins Scribed by: Soham De & Karthik A Sankararaman 1 Lower Bounds In this lecture (and

More information

Online combinatorial optimization with stochastic decision sets and adversarial losses

Online combinatorial optimization with stochastic decision sets and adversarial losses Online combinatorial optimization with stochastic decision sets and adversarial losses Gergely Neu Michal Valko SequeL team, INRIA Lille Nord urope, France {gergely.neu,michal.valko}@inria.fr Abstract

More information

No-Regret Algorithms for Unconstrained Online Convex Optimization

No-Regret Algorithms for Unconstrained Online Convex Optimization No-Regret Algorithms for Unconstrained Online Convex Optimization Matthew Streeter Duolingo, Inc. Pittsburgh, PA 153 matt@duolingo.com H. Brendan McMahan Google, Inc. Seattle, WA 98103 mcmahan@google.com

More information

Online Learning for Non-Stationary A/B Tests

Online Learning for Non-Stationary A/B Tests CIKM 18, October 22-26, 218, Torino, Italy Online Learning for Non-Stationary A/B Tests Andrés Muñoz Medina Google AI New York, NY ammedina@google.com Sergei Vassilvitiskii Google AI New York, NY sergeiv@google.com

More information

Regret Minimization With Concept Drift

Regret Minimization With Concept Drift Regret Minimization With Concept Drift Koby Crammer he echnion koby@ee.technion.ac.il Yishay Mansour el Aviv University mansour@cs.tau.ac.il Eyal Even-Dar Google Research evendar@google.com Jennifer Wortman

More information

Online Learning, Mistake Bounds, Perceptron Algorithm

Online Learning, Mistake Bounds, Perceptron Algorithm Online Learning, Mistake Bounds, Perceptron Algorithm 1 Online Learning So far the focus of the course has been on batch learning, where algorithms are presented with a sample of training data, from which

More information

Improved Bounds for Online Learning Over the Permutahedron and Other Ranking Polytopes

Improved Bounds for Online Learning Over the Permutahedron and Other Ranking Polytopes Improved Bounds for Online Learning Over the Permutahedron and Other Ranking Polytopes Nir Ailon Department of Computer Science, echnion II, Haifa, Israel nailon@cs.technion.ac.il Abstract Consider the

More information

Learning for Contextual Bandits

Learning for Contextual Bandits Learning for Contextual Bandits Alina Beygelzimer 1 John Langford 2 IBM Research 1 Yahoo! Research 2 NYC ML Meetup, Sept 21, 2010 Example of Learning through Exploration Repeatedly: 1. A user comes to

More information

Introduction to Machine Learning Lecture 13. Mehryar Mohri Courant Institute and Google Research

Introduction to Machine Learning Lecture 13. Mehryar Mohri Courant Institute and Google Research Introduction to Machine Learning Lecture 13 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Multi-Class Classification Mehryar Mohri - Introduction to Machine Learning page 2 Motivation

More information

Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm

Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm Jacob Steinhardt Percy Liang Stanford University, 353 Serra Street, Stanford, CA 94305 USA JSTEINHARDT@CS.STANFORD.EDU PLIANG@CS.STANFORD.EDU Abstract We present an adaptive variant of the exponentiated

More information

Better Algorithms for Benign Bandits

Better Algorithms for Benign Bandits Better Algorithms for Benign Bandits Elad Hazan IBM Almaden 650 Harry Rd, San Jose, CA 95120 hazan@us.ibm.com Satyen Kale Microsoft Research One Microsoft Way, Redmond, WA 98052 satyen.kale@microsoft.com

More information

Adaptive Game Playing Using Multiplicative Weights

Adaptive Game Playing Using Multiplicative Weights Games and Economic Behavior 29, 79 03 (999 Article ID game.999.0738, available online at http://www.idealibrary.com on Adaptive Game Playing Using Multiplicative Weights Yoav Freund and Robert E. Schapire

More information

Explore no more: Improved high-probability regret bounds for non-stochastic bandits

Explore no more: Improved high-probability regret bounds for non-stochastic bandits Explore no more: Improved high-probability regret bounds for non-stochastic bandits Gergely Neu SequeL team INRIA Lille Nord Europe gergely.neu@gmail.com Abstract This work addresses the problem of regret

More information

Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm

Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm Jacob Steinhardt Percy Liang Stanford University {jsteinhardt,pliang}@cs.stanford.edu Jun 11, 2013 J. Steinhardt & P. Liang (Stanford)

More information

Deep Boosting. Joint work with Corinna Cortes (Google Research) Umar Syed (Google Research) COURANT INSTITUTE & GOOGLE RESEARCH.

Deep Boosting. Joint work with Corinna Cortes (Google Research) Umar Syed (Google Research) COURANT INSTITUTE & GOOGLE RESEARCH. Deep Boosting Joint work with Corinna Cortes (Google Research) Umar Syed (Google Research) MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Ensemble Methods in ML Combining several base classifiers

More information

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I. Sébastien Bubeck Theory Group

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I. Sébastien Bubeck Theory Group Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I Sébastien Bubeck Theory Group i.i.d. multi-armed bandit, Robbins [1952] i.i.d. multi-armed bandit, Robbins [1952] Known

More information

No-regret algorithms for structured prediction problems

No-regret algorithms for structured prediction problems No-regret algorithms for structured prediction problems Geoffrey J. Gordon December 21, 2005 CMU-CALD-05-112 School of Computer Science Carnegie-Mellon University Pittsburgh, PA 15213 Abstract No-regret

More information

Online Aggregation of Unbounded Signed Losses Using Shifting Experts

Online Aggregation of Unbounded Signed Losses Using Shifting Experts Proceedings of Machine Learning Research 60: 5, 207 Conformal and Probabilistic Prediction and Applications Online Aggregation of Unbounded Signed Losses Using Shifting Experts Vladimir V. V yugin Institute

More information

Foundations of Machine Learning Multi-Class Classification. Mehryar Mohri Courant Institute and Google Research

Foundations of Machine Learning Multi-Class Classification. Mehryar Mohri Courant Institute and Google Research Foundations of Machine Learning Multi-Class Classification Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Motivation Real-world problems often have multiple classes: text, speech,

More information

Online Learning with Feedback Graphs

Online Learning with Feedback Graphs Online Learning with Feedback Graphs Claudio Gentile INRIA and Google NY clagentile@gmailcom NYC March 6th, 2018 1 Content of this lecture Regret analysis of sequential prediction problems lying between

More information

A simpler unified analysis of Budget Perceptrons

A simpler unified analysis of Budget Perceptrons Ilya Sutskever University of Toronto, 6 King s College Rd., Toronto, Ontario, M5S 3G4, Canada ILYA@CS.UTORONTO.CA Abstract The kernel Perceptron is an appealing online learning algorithm that has a drawback:

More information

Convex Repeated Games and Fenchel Duality

Convex Repeated Games and Fenchel Duality Convex Repeated Games and Fenchel Duality Shai Shalev-Shwartz 1 and Yoram Singer 1,2 1 School of Computer Sci. & Eng., he Hebrew University, Jerusalem 91904, Israel 2 Google Inc. 1600 Amphitheater Parkway,

More information

Using Additive Expert Ensembles to Cope with Concept Drift

Using Additive Expert Ensembles to Cope with Concept Drift Jeremy Z. Kolter and Marcus A. Maloof {jzk, maloof}@cs.georgetown.edu Department of Computer Science, Georgetown University, Washington, DC 20057-1232, USA Abstract We consider online learning where the

More information

Ensemble Methods for Structured Prediction

Ensemble Methods for Structured Prediction Ensemble Methods for Structured Prediction Corinna Cortes Google Research, 111 8th Avenue, New York, NY 10011 Vitaly Kuznetsov Courant Institute of Mathematical Sciences, 251 Mercer Street, New York, NY

More information

Minimax Policies for Combinatorial Prediction Games

Minimax Policies for Combinatorial Prediction Games Minimax Policies for Combinatorial Prediction Games Jean-Yves Audibert Imagine, Univ. Paris Est, and Sierra, CNRS/ENS/INRIA, Paris, France audibert@imagine.enpc.fr Sébastien Bubeck Centre de Recerca Matemàtica

More information

Lecture 4: Lower Bounds (ending); Thompson Sampling

Lecture 4: Lower Bounds (ending); Thompson Sampling CMSC 858G: Bandits, Experts and Games 09/12/16 Lecture 4: Lower Bounds (ending); Thompson Sampling Instructor: Alex Slivkins Scribed by: Guowei Sun,Cheng Jie 1 Lower bounds on regret (ending) Recap from

More information

On Minimaxity of Follow the Leader Strategy in the Stochastic Setting

On Minimaxity of Follow the Leader Strategy in the Stochastic Setting On Minimaxity of Follow the Leader Strategy in the Stochastic Setting Wojciech Kot lowsi Poznań University of Technology, Poland wotlowsi@cs.put.poznan.pl Abstract. We consider the setting of prediction

More information

Foundations of Machine Learning

Foundations of Machine Learning Introduction to ML Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu page 1 Logistics Prerequisites: basics in linear algebra, probability, and analysis of algorithms. Workload: about

More information

Learning Hurdles for Sleeping Experts

Learning Hurdles for Sleeping Experts Learning Hurdles for Sleeping Experts Varun Kanade EECS, University of California Berkeley, CA, USA vkanade@eecs.berkeley.edu Thomas Steinke SEAS, Harvard University Cambridge, MA, USA tsteinke@fas.harvard.edu

More information

Perceptron (Theory) + Linear Regression

Perceptron (Theory) + Linear Regression 10601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Perceptron (Theory) Linear Regression Matt Gormley Lecture 6 Feb. 5, 2018 1 Q&A

More information

CS 395T Computational Learning Theory. Scribe: Rahul Suri

CS 395T Computational Learning Theory. Scribe: Rahul Suri CS 395T Computational Learning Theory Lecture 6: September 19, 007 Lecturer: Adam Klivans Scribe: Rahul Suri 6.1 Overview In Lecture 5, we showed that for any DNF formula f with n variables and s terms

More information