An Introduction to Game-theoretic Online Learning Tim van Erven
|
|
- Opal Curtis
- 7 years ago
- Views:
Transcription
1 General Mathematics Colloquium Leiden, December 4, 2014 An Introduction to Game-theoretic Online Learning Tim van Erven
2 Statistics Bayesian Statistics Frequentist Statistics
3 Statistics Bayesian Statistics Frequentist Statistics A. was here
4 Statistics Bayesian Statistics Frequentist Statistics Rogue Factions
5 Statistics Bayesian Statistics Frequentist Statistics Rogue Factions Adversarial Bandits
6 Statistics Bayesian Statistics Frequentist Statistics Rogue Factions Adversarial Bandits Game-theoretic Online Learning You are here
7 Outline Introduction to Online Learning Game-theoretic Model Regression example: Electricity Classification example: Spam Three algorithms Tuning the Learning Rate
8 Game-Theoretic Online Learning Predict data that arrive one by one Model: repeated game against an adversary Applications: spam detection data compression online convex optimization predicting electricity consumption predicting air pollution levels...
9 Repeated Game (Informally) Sequentially predict outcomes Measure quality of prediction by loss Before predicting, get predictions (=advice) from experts Goal: to predict as well as the best expert over rounds. Data and Advice can be adversarial
10 Repeated Game Every round : 1. Get expert predictions 2. Predict 3. Outcome is revealed 4. Measure losses
11 Repeated Game Every round : 1. Get expert predictions 2. Predict 3. Outcome is revealed 4. Measure losses Best expert: Goal: minimize regret
12 Outline Introduction to Online Learning Game-theoretic Model Regression example: Electricity Classification example: Spam Three algorithms Tuning the Learning Rate
13 Regression Example: Electricity Électricité de France: predict electricity demand one day ahead, every day Experts: complicated regression models Loss: [Devaine, Gaillard, Goude, Stoltz, 2013]
14 Regression Example: Electricity Électricité de France: predict electricity demand one day ahead, every day Experts: complicated regression models Loss: [Devaine, Gaillard, Goude, Stoltz, 2013] Best model after one year: How much worse are we?
15 Outline Introduction to Online Learning Game-theoretic Model Regression example: Electricity Classification example: Spam Three algorithms Tuning the Learning Rate
16 Example: Spam Detection spam ham spam ham ham spam spam ham spam spam
17 Classification Example: Spam Experts: spam detection algorithms Messages: Predictions: Loss: Regret: extra mistakes we make over best algorithm on messages
18 Outline Introduction to Online Learning Three algorithms: 1. Halving 2. Follow the Leader (FTL) 3. Follow the Regularized Leader (FTRL) Tuning the Learning Rate
19 A First Algorithm: Halving Suppose one of the spam detectors is perfect Keep track of experts without mistakes so far: Halving algorithm: Theorem: regret
20 A First Algorithm: Halving Theorem: regret Does not grow with Proof: Suppose halving makes mistakes, regret = Every mistake eliminates at least half of is at most mistakes
21 Outline Introduction to Online Learning Three algorithms: 1. Halving 2. Follow the Leader (FTL) 3. Follow the Regularized Leader (FTRL) Tuning the Learning Rate
22 Follow the Leader Want to remove unrealistic assumption that one expert is perfect FTL: copy the leader's prediction The leader at time : (break ties randomly) where expert k is cumulative loss for
23 FTL Works with Perfect Expert Theorem: Suppose one of the spam detectors is perfect. Then Expected regret Proof: Expected regret = E[nr. mistakes] - 0 Worst case: experts get one loss in turn E[nr. mistakes]
24 FTL: More Good News No assumption of perfect expert Theorem: regret
25 FTL: More Good News No assumption of perfect expert Theorem: regret Proof sketch: No leader change: our loss = loss of leader, so the regret stays the same Leader change: our regret increases at most by 1 (range of losses)
26 FTL: More Good News No assumption of perfect expert Theorem: regret Proof sketch: No leader change: our loss = loss of leader, so the regret stays the same Leader change, our regret increases at most by 1 (range of losses) Works well for i.i.d. losses, because the leader changes only finitely many times w.h.p.
27 FTL on IID Losses 4 experts with Bernoulli 0.1, 0.2, 0.3, 0.4 losses; regret = O(log K)
28 FTL Worst-case Losses
29 FTL Worst-case Losses Two experts with tie/leader change every round: Expert Expert FTL 1/2 1 1/2 1 1/2 1 Both experts have cumulative loss: Regret is linear in Problem: FTL too sure of itself when no ties!
30 Outline Introduction to Online Learning Three algorithms: 1. Halving 2. Follow the Leader (FTL) 3. Follow the Regularized Leader (FTRL) Tuning the Learning Rate
31 Solution: Be Less Sure! Pull FTL choices towards uniform distribution Follow the Leader: leader: as distribution: Follow the Regularized Leader: add penalty for being away from uniform; Kullback-Leibler divergence in this talk
32 The Learning Rate Follow the Regularized Leader: Very sensitive to choice of learning rate Follow the Leader Don't learn at all
33 Outline Introduction to Online Learning Three algorithms Tuning the Learning Rate: Safe tuning The Price of Robustness Learning the Learning Rate
34 The Worst-case Safe Learning Rate Theorem: For FTRL regret regret No (probabilistic) assumptions about data! Optimal is standard in online learning
35 Outline Introduction to Online Learning Three algorithms Tuning the Learning Rate: Safe tuning The Price of Robustness Learning the Learning Rate
36 The Price of Robustness Safe tuning does much worse than FTL on i.i.d. losses
37 The Price of Robustness Method Special Case of FTRL Perfect Expert Data IID Data Worst-case Data Halving no undefined undefined Follow the Leader FTRL with Worstcase Safe Tuning (very large) (small) Can we adapt to optimal eta automatically?
38 Outline Introduction to Online Learning Three algorithms Tuning the Learning Rate: Safe tuning The Price of Robustness Learning the Learning Rate
39 A Failed Approach: Being Meta We want Idea: meta-problem Expert 1: FTL Expert 2: FTRL with Safe Tuning
40 A Failed Approach: Being Meta We want Idea: meta-problem Expert 1: FTL Expert 2: FTRL with Safe Tuning Regret Best of both worlds if meta-regret small!
41 A Failed Approach: Being Meta We want Idea: meta-problem Expert 1: FTL Expert 2: FTRL with Safe Tuning Regret Best of both worlds if meta-regret small! If and, then is too big!
42 Partial Progress Safe tuning: Regret Improvement for small losses: Regret
43 Partial Progress Safe tuning: Regret Improvement for small losses: Regret variance of Variance Bounds: Cesa-Bianchi, Mansour, Stoltz, 2007 ve, Grünwald, Koolen, De Rooij, 2011 De Rooij, ve, Grünwald, Koolen, 2014
44 Partial Progress Safe tuning: Regret Improvement for small losses: Regret variance of Variance Bounds:
45 Regret is a Difficult Function 1/2 All the previous solutions could potentially end up in wrong local minimum
46 Regret is a Difficult Function 2/2 Regret as a function of T for fixed is nonmonotonic. This means some may look very bad for a while, but end up being very good after all How do we see which 's are good? Use (best-possible) monotonic lower-bound per
47 Learning the Learning Rate Koolen, ve, Grünwald, 2014
48 Learning the Learning Rate Track performance for grid of learning rates Switch between them Pay for switching, but not too much Running time as fast as for single fixed does not depend on size of grid
49 Learning the Learning Rate Theorems: } As good as all previous methods For all interesting : polylog(k,t)
50 Learning the Learning Rate Koolen, ve, Grünwald, 2014
51 The Price of Robustness Method Special Case of FTRL Perfect Expert Data IID Data Worst-case Data Compared to Optimal Follow the Leader (very large) no useful guarantees FTRL with Worst-case Safe Tuning (small) no useful guarantees LLR polylog(k,t) factor Can we adapt to optimal eta automatically? Yes!
52 Statistics Summary Bayesian Statistics Frequentist Statistics Rogue Factions Adversarial Bandits Game-theoretic Online Learning Game-theoretic Online Learning You are here e.g. electricity forecasting, spam detection Three algorithms: Halving, Follow the (Regularized) Leader Tuning the Learning Rate: Safe tuning pays the Price of Robustness Learning the learning rate adapts to the optimal learning rate automatically
53 Future Work So far: compete with the best expert Online Convex Optimization: compete with the best convex combination of experts Future work: extend LLR to online convex optimization
54 References Cesa-Bianchi and Lugosi. Prediction, learning, and games Cesa-Bianchi, Mansour, Stoltz. Improved second-order bounds for prediction with expert advice. Machine Learning, 66(2/3): , Devaine, Gaillard, Goude, Stoltz. Forecasting electricity consumption by aggregating specialized experts. Machine Learning, 90(2): , Van Erven, Grünwald, Koolen and De Rooij. Adaptive Hedge. NIPS, De Rooij, Van Erven, Grünwald, Koolen. Follow the Leader If You Can, Hedge If You Must. Journal of Machine Learning Research, Koolen, Van Erven, Grünwald. Learning the Learning Rate for Prediction with Expert Advice. NIPS, 2014.
Week 1: Introduction to Online Learning
Week 1: Introduction to Online Learning 1 Introduction This is written based on Prediction, Learning, and Games (ISBN: 2184189 / -21-8418-9 Cesa-Bianchi, Nicolo; Lugosi, Gabor 1.1 A Gentle Start Consider
More informationSimple and efficient online algorithms for real world applications
Simple and efficient online algorithms for real world applications Università degli Studi di Milano Milano, Italy Talk @ Centro de Visión por Computador Something about me PhD in Robotics at LIRA-Lab,
More informationAchieving All with No Parameters: AdaNormalHedge
JMLR: Workshop and Conference Proceedings vol 40:1 19, 2015 Achieving All with No Parameters: AdaNormalHedge Haipeng Luo Department of Computer Science, Princeton University Robert E. Schapire Microsoft
More informationFoundations of Machine Learning On-Line Learning. Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu
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 information1 Introduction. 2 Prediction with Expert Advice. Online Learning 9.520 Lecture 09
1 Introduction Most of the course is concerned with the batch learning problem. In this lecture, however, we look at a different model, called online. Let us first compare and contrast the two. In batch
More informationUn point de vue bayésien pour des algorithmes de bandit plus performants
Un point de vue bayésien pour des algorithmes de bandit plus performants Emilie Kaufmann, Telecom ParisTech Rencontre des Jeunes Statisticiens, Aussois, 28 août 2013 Emilie Kaufmann (Telecom ParisTech)
More informationOnline Algorithms: Learning & Optimization with No Regret.
Online Algorithms: Learning & Optimization with No Regret. Daniel Golovin 1 The Setup Optimization: Model the problem (objective, constraints) Pick best decision from a feasible set. Learning: Model the
More informationFollow the Leader with Dropout Perturbations
JMLR: Worshop and Conference Proceedings vol 35: 26, 204 Follow the Leader with Dropout Perturbations Tim van Erven Département de Mathématiques, Université Paris-Sud, France Wojciech Kotłowsi Institute
More informationOnline Learning with Switching Costs and Other Adaptive Adversaries
Online Learning with Switching Costs and Other Adaptive Adversaries Nicolò Cesa-Bianchi Università degli Studi di Milano Italy Ofer Dekel Microsoft Research USA Ohad Shamir Microsoft Research and the Weizmann
More informationIntroduction to Online Learning Theory
Introduction to Online Learning Theory Wojciech Kot lowski Institute of Computing Science, Poznań University of Technology IDSS, 04.06.2013 1 / 53 Outline 1 Example: Online (Stochastic) Gradient Descent
More informationOnline Learning. 1 Online Learning and Mistake Bounds for Finite Hypothesis Classes
Advanced Course in Machine Learning Spring 2011 Online Learning Lecturer: Shai Shalev-Shwartz Scribe: Shai Shalev-Shwartz In this lecture we describe a different model of learning which is called online
More informationAdaptive Online Gradient Descent
Adaptive Online Gradient Descent Peter L Bartlett Division of Computer Science Department of Statistics UC Berkeley Berkeley, CA 94709 bartlett@csberkeleyedu Elad Hazan IBM Almaden Research Center 650
More information1 Portfolio Selection
COS 5: Theoretical Machine Learning Lecturer: Rob Schapire Lecture # Scribe: Nadia Heninger April 8, 008 Portfolio Selection Last time we discussed our model of the stock market N stocks start on day with
More informationStrongly Adaptive Online Learning
Amit Daniely Alon Gonen Shai Shalev-Shwartz The Hebrew University AMIT.DANIELY@MAIL.HUJI.AC.IL ALONGNN@CS.HUJI.AC.IL SHAIS@CS.HUJI.AC.IL Abstract Strongly adaptive algorithms are algorithms whose performance
More informationHow To Calculate Electricity Load Data
Combining Forecasts for Short Term Electricity Load Forecasting Weight 0.0 0.2 0.4 0.6 0.8 1.0 0 1000 2000 3000 4000 5000 Step M. Devaine, P. Gaillard, Y.Goude, G. Stoltz ENS Paris - EDF R&D - CNRS, INRIA
More informationFind-The-Number. 1 Find-The-Number With Comps
Find-The-Number 1 Find-The-Number With Comps Consider the following two-person game, which we call Find-The-Number with Comps. Player A (for answerer) has a number x between 1 and 1000. Player Q (for questioner)
More informationTrading regret rate for computational efficiency in online learning with limited feedback
Trading regret rate for computational efficiency in online learning with limited feedback Shai Shalev-Shwartz TTI-C Hebrew University On-line Learning with Limited Feedback Workshop, 2009 June 2009 Shai
More informationOnline Learning and Online Convex Optimization. Contents
Foundations and Trends R in Machine Learning Vol. 4, No. 2 (2011) 107 194 c 2012 S. Shalev-Shwartz DOI: 10.1561/2200000018 Online Learning and Online Convex Optimization By Shai Shalev-Shwartz Contents
More informationThe Advantages and Disadvantages of Online Linear Optimization
LINEAR PROGRAMMING WITH ONLINE LEARNING TATSIANA LEVINA, YURI LEVIN, JEFF MCGILL, AND MIKHAIL NEDIAK SCHOOL OF BUSINESS, QUEEN S UNIVERSITY, 143 UNION ST., KINGSTON, ON, K7L 3N6, CANADA E-MAIL:{TLEVIN,YLEVIN,JMCGILL,MNEDIAK}@BUSINESS.QUEENSU.CA
More informationBasics of Statistical Machine Learning
CS761 Spring 2013 Advanced Machine Learning Basics of Statistical Machine Learning Lecturer: Xiaojin Zhu jerryzhu@cs.wisc.edu Modern machine learning is rooted in statistics. You will find many familiar
More informationUCLA. Department of Economics Ph. D. Preliminary Exam Micro-Economic Theory
UCLA Department of Economics Ph. D. Preliminary Exam Micro-Economic Theory (SPRING 2011) Instructions: You have 4 hours for the exam Answer any 5 out of the 6 questions. All questions are weighted equally.
More informationBig Data - Lecture 1 Optimization reminders
Big Data - Lecture 1 Optimization reminders S. Gadat Toulouse, Octobre 2014 Big Data - Lecture 1 Optimization reminders S. Gadat Toulouse, Octobre 2014 Schedule Introduction Major issues Examples Mathematics
More informationCS229T/STAT231: Statistical Learning Theory (Winter 2015)
CS229T/STAT231: Statistical Learning Theory (Winter 2015) Percy Liang Last updated Wed Oct 14 2015 20:32 These lecture notes will be updated periodically as the course goes on. Please let us know if you
More informationDynamics and Equilibria
Dynamics and Equilibria Sergiu Hart Presidential Address, GAMES 2008 (July 2008) Revised and Expanded (November 2009) Revised (2010, 2011, 2012, 2013) SERGIU HART c 2008 p. 1 DYNAMICS AND EQUILIBRIA Sergiu
More informationThe p-norm generalization of the LMS algorithm for adaptive filtering
The p-norm generalization of the LMS algorithm for adaptive filtering Jyrki Kivinen University of Helsinki Manfred Warmuth University of California, Santa Cruz Babak Hassibi California Institute of Technology
More informationGovernment of Russian Federation. Faculty of Computer Science School of Data Analysis and Artificial Intelligence
Government of Russian Federation Federal State Autonomous Educational Institution of High Professional Education National Research University «Higher School of Economics» Faculty of Computer Science School
More informationLARGE CLASSES OF EXPERTS
LARGE CLASSES OF EXPERTS Csaba Szepesvári University of Alberta CMPUT 654 E-mail: szepesva@ualberta.ca UofA, October 31, 2006 OUTLINE 1 TRACKING THE BEST EXPERT 2 FIXED SHARE FORECASTER 3 VARIABLE-SHARE
More informationMélange de Prédicteurs, Application à la Prévision de. Comsommation Electrique
Mélange de Prédicteurs, Application à la Prévision de Comsommation Electrique Yannig Goude Université Paris-Sud XI - UFR Scientifique d Orsay. EDF R&D, 1 avenue du general de Gaulle, BP 408, 92141 Clamart,
More informationIntroduction to Online Optimization
Princeton University - Department of Operations Research and Financial Engineering Introduction to Online Optimization Sébastien Bubeck December 14, 2011 1 Contents Chapter 1. Introduction 5 1.1. Statistical
More informationOnline Learning with Composite Loss Functions
JMLR: Workshop and Conference Proceedings vol 35:1 18, 2014 Online Learning with Composite Loss Functions Ofer Dekel Microsoft Research Jian Ding University of Chicago Tomer Koren Technion Yuval Peres
More informationOn Attacking Statistical Spam Filters
On Attacking Statistical Spam Filters Gregory L. Wittel and S. Felix Wu Department of Computer Science University of California, Davis One Shields Avenue, Davis, CA 95616 USA Paper review by Deepak Chinavle
More information9th Max-Planck Advanced Course on the Foundations of Computer Science (ADFOCS) Primal-Dual Algorithms for Online Optimization: Lecture 1
9th Max-Planck Advanced Course on the Foundations of Computer Science (ADFOCS) Primal-Dual Algorithms for Online Optimization: Lecture 1 Seffi Naor Computer Science Dept. Technion Haifa, Israel Introduction
More informationOptimal Strategies and Minimax Lower Bounds for Online Convex Games
Optimal Strategies and Minimax Lower Bounds for Online Convex Games Jacob Abernethy UC Berkeley jake@csberkeleyedu Alexander Rakhlin UC Berkeley rakhlin@csberkeleyedu Abstract A number of learning problems
More informationHow to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal
How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal Jacob Abernethy University of Michigan jabernet@umich.edu Rafael M. Frongillo Microsoft Research raf@cs.berkeley.edu
More informationOptimal Online-list Batch Scheduling
Optimal Online-list Batch Scheduling Jacob Jan Paulus a,, Deshi Ye b, Guochuan Zhang b a University of Twente, P.O. box 217, 7500AE Enschede, The Netherlands b Zhejiang University, Hangzhou 310027, China
More informationBayesian logistic betting strategy against probability forecasting. Akimichi Takemura, Univ. Tokyo. November 12, 2012
Bayesian logistic betting strategy against probability forecasting Akimichi Takemura, Univ. Tokyo (joint with Masayuki Kumon, Jing Li and Kei Takeuchi) November 12, 2012 arxiv:1204.3496. To appear in Stochastic
More informationInterior-Point Methods for Full-Information and Bandit Online Learning
4164 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 58, NO. 7, JULY 2012 Interior-Point Methods for Full-Information and Bandit Online Learning Jacob D. Abernethy, Elad Hazan, and Alexander Rakhlin Abstract
More informationInteractive Machine Learning. Maria-Florina Balcan
Interactive Machine Learning Maria-Florina Balcan Machine Learning Image Classification Document Categorization Speech Recognition Protein Classification Branch Prediction Fraud Detection Spam Detection
More information1 Maximum likelihood estimation
COS 424: Interacting with Data Lecturer: David Blei Lecture #4 Scribes: Wei Ho, Michael Ye February 14, 2008 1 Maximum likelihood estimation 1.1 MLE of a Bernoulli random variable (coin flips) Given N
More informationNotes from Week 1: Algorithms for sequential prediction
CS 683 Learning, Games, and Electronic Markets Spring 2007 Notes from Week 1: Algorithms for sequential prediction Instructor: Robert Kleinberg 22-26 Jan 2007 1 Introduction In this course we will be looking
More informationA Game Theoretical Framework for Adversarial Learning
A Game Theoretical Framework for Adversarial Learning Murat Kantarcioglu University of Texas at Dallas Richardson, TX 75083, USA muratk@utdallas Chris Clifton Purdue University West Lafayette, IN 47907,
More informationMaster s Theory Exam Spring 2006
Spring 2006 This exam contains 7 questions. You should attempt them all. Each question is divided into parts to help lead you through the material. You should attempt to complete as much of each problem
More informationRevenue Optimization against Strategic Buyers
Revenue Optimization against Strategic Buyers Mehryar Mohri Courant Institute of Mathematical Sciences 251 Mercer Street New York, NY, 10012 Andrés Muñoz Medina Google Research 111 8th Avenue New York,
More informationDiscrete Math in Computer Science Homework 7 Solutions (Max Points: 80)
Discrete Math in Computer Science Homework 7 Solutions (Max Points: 80) CS 30, Winter 2016 by Prasad Jayanti 1. (10 points) Here is the famous Monty Hall Puzzle. Suppose you are on a game show, and you
More informationSection 1.3 P 1 = 1 2. = 1 4 2 8. P n = 1 P 3 = Continuing in this fashion, it should seem reasonable that, for any n = 1, 2, 3,..., = 1 2 4.
Difference Equations to Differential Equations Section. The Sum of a Sequence This section considers the problem of adding together the terms of a sequence. Of course, this is a problem only if more than
More informationProbabilistic Models for Big Data. Alex Davies and Roger Frigola University of Cambridge 13th February 2014
Probabilistic Models for Big Data Alex Davies and Roger Frigola University of Cambridge 13th February 2014 The State of Big Data Why probabilistic models for Big Data? 1. If you don t have to worry about
More informationLecture Notes on Online Learning DRAFT
Lecture Notes on Online Learning DRAFT Alexander Rakhlin These lecture notes contain material presented in the Statistical Learning Theory course at UC Berkeley, Spring 08. Various parts of these notes
More informationMachine Learning in Spam Filtering
Machine Learning in Spam Filtering A Crash Course in ML Konstantin Tretyakov kt@ut.ee Institute of Computer Science, University of Tartu Overview Spam is Evil ML for Spam Filtering: General Idea, Problems.
More informationMachine Learning Final Project Spam Email Filtering
Machine Learning Final Project Spam Email Filtering March 2013 Shahar Yifrah Guy Lev Table of Content 1. OVERVIEW... 3 2. DATASET... 3 2.1 SOURCE... 3 2.2 CREATION OF TRAINING AND TEST SETS... 4 2.3 FEATURE
More informationUsing Generalized Forecasts for Online Currency Conversion
Using Generalized Forecasts for Online Currency Conversion Kazuo Iwama and Kouki Yonezawa School of Informatics Kyoto University Kyoto 606-8501, Japan {iwama,yonezawa}@kuis.kyoto-u.ac.jp Abstract. El-Yaniv
More informationCSC2420 Fall 2012: Algorithm Design, Analysis and Theory
CSC2420 Fall 2012: Algorithm Design, Analysis and Theory Allan Borodin November 15, 2012; Lecture 10 1 / 27 Randomized online bipartite matching and the adwords problem. We briefly return to online algorithms
More informationOnline Network Revenue Management using Thompson Sampling
Online Network Revenue Management using Thompson Sampling Kris Johnson Ferreira David Simchi-Levi He Wang Working Paper 16-031 Online Network Revenue Management using Thompson Sampling Kris Johnson Ferreira
More information4.1 Introduction - Online Learning Model
Computational Learning Foundations Fall semester, 2010 Lecture 4: November 7, 2010 Lecturer: Yishay Mansour Scribes: Elad Liebman, Yuval Rochman & Allon Wagner 1 4.1 Introduction - Online Learning Model
More informationIntoduction to the Fifth Workshop Game-Theoretic Probability and Related Topics
Intoduction to the Fifth Workshop Game-Theoretic Probability and Related Topics Glenn Shafer 13 November 2014 1. Basics of game-theoretic probability 2. Probability-free finance 3. Prediction Glenn Shafer
More informationMonotone multi-armed bandit allocations
JMLR: Workshop and Conference Proceedings 19 (2011) 829 833 24th Annual Conference on Learning Theory Monotone multi-armed bandit allocations Aleksandrs Slivkins Microsoft Research Silicon Valley, Mountain
More informationA Potential-based Framework for Online Multi-class Learning with Partial Feedback
A Potential-based Framework for Online Multi-class Learning with Partial Feedback Shijun Wang Rong Jin Hamed Valizadegan Radiology and Imaging Sciences Computer Science and Engineering Computer Science
More informationHow to Use Expert Advice
NICOLÒ CESA-BIANCHI Università di Milano, Milan, Italy YOAV FREUND AT&T Labs, Florham Park, New Jersey DAVID HAUSSLER AND DAVID P. HELMBOLD University of California, Santa Cruz, Santa Cruz, California
More informationFalse Discovery Rates
False Discovery Rates John D. Storey Princeton University, Princeton, USA January 2010 Multiple Hypothesis Testing In hypothesis testing, statistical significance is typically based on calculations involving
More informationOnline Lazy Updates for Portfolio Selection with Transaction Costs
Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence Online Lazy Updates for Portfolio Selection with Transaction Costs Puja Das, Nicholas Johnson, and Arindam Banerjee Department
More informationREAL TIME OPERATING SYSTEMS. Lesson-18:
REAL TIME OPERATING SYSTEMS Lesson-18: Round Robin Time Slicing of tasks of equal priorities 1 1. Common scheduling models 2 Common scheduling models Cooperative Scheduling of ready tasks in a circular
More informationNetwork Security A Decision and Game-Theoretic Approach
Network Security A Decision and Game-Theoretic Approach Tansu Alpcan Deutsche Telekom Laboratories, Technical University of Berlin, Germany and Tamer Ba ar University of Illinois at Urbana-Champaign, USA
More informationEnsemble Methods. Knowledge Discovery and Data Mining 2 (VU) (707.004) Roman Kern. KTI, TU Graz 2015-03-05
Ensemble Methods Knowledge Discovery and Data Mining 2 (VU) (707004) Roman Kern KTI, TU Graz 2015-03-05 Roman Kern (KTI, TU Graz) Ensemble Methods 2015-03-05 1 / 38 Outline 1 Introduction 2 Classification
More information6.207/14.15: Networks Lecture 15: Repeated Games and Cooperation
6.207/14.15: Networks Lecture 15: Repeated Games and Cooperation Daron Acemoglu and Asu Ozdaglar MIT November 2, 2009 1 Introduction Outline The problem of cooperation Finitely-repeated prisoner s dilemma
More informationMonotonicity Hints. Abstract
Monotonicity Hints Joseph Sill Computation and Neural Systems program California Institute of Technology email: joe@cs.caltech.edu Yaser S. Abu-Mostafa EE and CS Deptartments California Institute of Technology
More informationLearning from Data: Naive Bayes
Semester 1 http://www.anc.ed.ac.uk/ amos/lfd/ Naive Bayes Typical example: Bayesian Spam Filter. Naive means naive. Bayesian methods can be much more sophisticated. Basic assumption: conditional independence.
More informationDecision Analysis. Here is the statement of the problem:
Decision Analysis Formal decision analysis is often used when a decision must be made under conditions of significant uncertainty. SmartDrill can assist management with any of a variety of decision analysis
More informationInference of Probability Distributions for Trust and Security applications
Inference of Probability Distributions for Trust and Security applications Vladimiro Sassone Based on joint work with Mogens Nielsen & Catuscia Palamidessi Outline 2 Outline Motivations 2 Outline Motivations
More informationGI01/M055 Supervised Learning Proximal Methods
GI01/M055 Supervised Learning Proximal Methods Massimiliano Pontil (based on notes by Luca Baldassarre) (UCL) Proximal Methods 1 / 20 Today s Plan Problem setting Convex analysis concepts Proximal operators
More informationMoral Hazard. Itay Goldstein. Wharton School, University of Pennsylvania
Moral Hazard Itay Goldstein Wharton School, University of Pennsylvania 1 Principal-Agent Problem Basic problem in corporate finance: separation of ownership and control: o The owners of the firm are typically
More informationOnline Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret Raman Arora Toyota Technological Institute at Chicago, Chicago, IL 60637, USA Ofer Dekel Microsoft Research, 1 Microsoft
More informationBusiness Statistics 41000: Probability 1
Business Statistics 41000: Probability 1 Drew D. Creal University of Chicago, Booth School of Business Week 3: January 24 and 25, 2014 1 Class information Drew D. Creal Email: dcreal@chicagobooth.edu Office:
More informationAnalysis of Micromouse Maze Solving Algorithms
1 Analysis of Micromouse Maze Solving Algorithms David M. Willardson ECE 557: Learning from Data, Spring 2001 Abstract This project involves a simulation of a mouse that is to find its way through a maze.
More informationRegret Minimization for Reserve Prices in Second-Price Auctions
Regret Minimization for Reserve Prices in Second-Price Auctions Nicolò Cesa-Bianchi Università degli Studi di Milano Joint work with: Claudio Gentile (Varese) and Yishay Mansour (Tel-Aviv) N. Cesa-Bianchi
More informationSorting revisited. Build the binary search tree: O(n^2) Traverse the binary tree: O(n) Total: O(n^2) + O(n) = O(n^2)
Sorting revisited How did we use a binary search tree to sort an array of elements? Tree Sort Algorithm Given: An array of elements to sort 1. Build a binary search tree out of the elements 2. Traverse
More informationInsurance Analytics - analýza dat a prediktivní modelování v pojišťovnictví. Pavel Kříž. Seminář z aktuárských věd MFF 4.
Insurance Analytics - analýza dat a prediktivní modelování v pojišťovnictví Pavel Kříž Seminář z aktuárských věd MFF 4. dubna 2014 Summary 1. Application areas of Insurance Analytics 2. Insurance Analytics
More informationThe Union-Find Problem Kruskal s algorithm for finding an MST presented us with a problem in data-structure design. As we looked at each edge,
The Union-Find Problem Kruskal s algorithm for finding an MST presented us with a problem in data-structure design. As we looked at each edge, cheapest first, we had to determine whether its two endpoints
More informationStatistical Machine Learning
Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 4: classical linear and quadratic discriminants. 1 / 25 Linear separation For two classes in R d : simple idea: separate the classes
More informationAN ANALYSIS OF A WAR-LIKE CARD GAME. Introduction
AN ANALYSIS OF A WAR-LIKE CARD GAME BORIS ALEXEEV AND JACOB TSIMERMAN Abstract. In his book Mathematical Mind-Benders, Peter Winkler poses the following open problem, originally due to the first author:
More informationMonte Carlo Methods in Finance
Author: Yiyang Yang Advisor: Pr. Xiaolin Li, Pr. Zari Rachev Department of Applied Mathematics and Statistics State University of New York at Stony Brook October 2, 2012 Outline Introduction 1 Introduction
More informationThe Multiplicative Weights Update method
Chapter 2 The Multiplicative Weights Update method The Multiplicative Weights method is a simple idea which has been repeatedly discovered in fields as diverse as Machine Learning, Optimization, and Game
More informationList of Publications by Claudio Gentile
List of Publications by Claudio Gentile Claudio Gentile DiSTA, University of Insubria, Italy claudio.gentile@uninsubria.it November 6, 2013 Abstract Contains the list of publications by Claudio Gentile,
More informationLinear Models for Classification
Linear Models for Classification Sumeet Agarwal, EEL709 (Most figures from Bishop, PRML) Approaches to classification Discriminant function: Directly assigns each data point x to a particular class Ci
More information1 Error in Euler s Method
1 Error in Euler s Method Experience with Euler s 1 method raises some interesting questions about numerical approximations for the solutions of differential equations. 1. What determines the amount of
More informationDescription. Textbook. Grading. Objective
EC151.02 Statistics for Business and Economics (MWF 8:00-8:50) Instructor: Chiu Yu Ko Office: 462D, 21 Campenalla Way Phone: 2-6093 Email: kocb@bc.edu Office Hours: by appointment Description This course
More informationDecision Making under Uncertainty
6.825 Techniques in Artificial Intelligence Decision Making under Uncertainty How to make one decision in the face of uncertainty Lecture 19 1 In the next two lectures, we ll look at the question of how
More informationLinear Classification. Volker Tresp Summer 2015
Linear Classification Volker Tresp Summer 2015 1 Classification Classification is the central task of pattern recognition Sensors supply information about an object: to which class do the object belong
More information10-601. Machine Learning. http://www.cs.cmu.edu/afs/cs/academic/class/10601-f10/index.html
10-601 Machine Learning http://www.cs.cmu.edu/afs/cs/academic/class/10601-f10/index.html Course data All up-to-date info is on the course web page: http://www.cs.cmu.edu/afs/cs/academic/class/10601-f10/index.html
More information14.1 Rent-or-buy problem
CS787: Advanced Algorithms Lecture 14: Online algorithms We now shift focus to a different kind of algorithmic problem where we need to perform some optimization without knowing the input in advance. Algorithms
More informationThe Assumption(s) of Normality
The Assumption(s) of Normality Copyright 2000, 2011, J. Toby Mordkoff This is very complicated, so I ll provide two versions. At a minimum, you should know the short one. It would be great if you knew
More informationPractical Online Active Learning for Classification
Practical Online Active Learning for Classification Claire Monteleoni Department of Computer Science and Engineering University of California, San Diego cmontel@cs.ucsd.edu Matti Kääriäinen Department
More informationRandomized algorithms
Randomized algorithms March 10, 2005 1 What are randomized algorithms? Algorithms which use random numbers to make decisions during the executions of the algorithm. Why would we want to do this?? Deterministic
More informationComputational Game Theory and Clustering
Computational Game Theory and Clustering Martin Hoefer mhoefer@mpi-inf.mpg.de 1 Computational Game Theory? 2 Complexity and Computation of Equilibrium 3 Bounding Inefficiencies 4 Conclusion Computational
More informationQuestion 2 Naïve Bayes (16 points)
Question 2 Naïve Bayes (16 points) About 2/3 of your email is spam so you downloaded an open source spam filter based on word occurrences that uses the Naive Bayes classifier. Assume you collected the
More informationFilterBoost: Regression and Classification on Large Datasets
FilterBoost: Regression and Classification on Large Datasets Joseph K. Bradley Machine Learning Department Carnegie Mellon University Pittsburgh, PA 523 jkbradle@cs.cmu.edu Robert E. Schapire Department
More informationMeasuring the Performance of an Agent
25 Measuring the Performance of an Agent The rational agent that we are aiming at should be successful in the task it is performing To assess the success we need to have a performance measure What is rational
More informationNotes V General Equilibrium: Positive Theory. 1 Walrasian Equilibrium and Excess Demand
Notes V General Equilibrium: Positive Theory In this lecture we go on considering a general equilibrium model of a private ownership economy. In contrast to the Notes IV, we focus on positive issues such
More informationCONTENTS OF DAY 2. II. Why Random Sampling is Important 9 A myth, an urban legend, and the real reason NOTES FOR SUMMER STATISTICS INSTITUTE COURSE
1 2 CONTENTS OF DAY 2 I. More Precise Definition of Simple Random Sample 3 Connection with independent random variables 3 Problems with small populations 8 II. Why Random Sampling is Important 9 A myth,
More information2DI36 Statistics. 2DI36 Part II (Chapter 7 of MR)
2DI36 Statistics 2DI36 Part II (Chapter 7 of MR) What Have we Done so Far? Last time we introduced the concept of a dataset and seen how we can represent it in various ways But, how did this dataset came
More informationBig Data Big Knowledge?
EBPI Epidemiology, Biostatistics and Prevention Institute Big Data Big Knowledge? Torsten Hothorn 2015-03-06 The end of theory The End of Theory: The Data Deluge Makes the Scientific Method Obsolete (Chris
More informationThe Effects of Start Prices on the Performance of the Certainty Equivalent Pricing Policy
BMI Paper The Effects of Start Prices on the Performance of the Certainty Equivalent Pricing Policy Faculty of Sciences VU University Amsterdam De Boelelaan 1081 1081 HV Amsterdam Netherlands Author: R.D.R.
More information