Tuning bandit algorithms in stochastic environments
|
|
- Loraine Mason
- 5 years ago
- Views:
Transcription
1 Tuning bandit algorithms in stochastic environments Jean-Yves Audibert, CERTIS - Ecole des Ponts Remi Munos, INRIA Futurs Lille Csaba Szepesvári, University of Alberta The 18th International Conference on Algorithmic Learning Theory October 3, 2007, Sendai International Center, Sendai, Japan
2 Contents Bandit problems UCB and Motivation Tuning UCB by using variance estimates Concentration of the regret Finite horizon finite regret (PAC-UCB) Conclusions
3 Exploration vs. Exploitation Two treatments Unknown success probabilities Goal: find the best treatment while losing the smallest number of patients Explore or exploit?
4 Playing Bandits Payoff is 0 or 1 Arm 1: X0 11, X1 12, X0 13, X0 14, X 15, X 16, X 17, Arm 2: X1 21, X1 22, X0 23, X1 24, X1 25, X1 26, X 27,
5 Exploration vs. Exploitation: Some Applications Simple processes: Clinical trials Job shop scheduling (random jobs) What ad to put on a web-page More complex processes (memory): Optimizing production Controlling an inventory Optimal investment Poker
6 Bandit Problems Optimism in the Face of Uncertainty Introduced by Lai and Robbins (1985) (?) i.i.d. payoffs X 11,X 12,,X 1t, X 21,X 22,,X 2t, Principle: Inflated value of an option = maximum expected reward that looks quite possible given the observations so far Select the option with best inflated value
7 Some definitions Payoff is 0 or 1 Now: t=11 T 1 (t-1) = 4 T 2 (t-1) = 6 I 1 = 1, I 2 = 2, Arm 1: X0 11, X1 12, X0 13, X0 14, X 15, X 16, X 17, Arm 2: X1 21, X1 22, X0 23, X1 24, X1 25, X1 26, X 27, ˆR n def = n t=1 X k,t n t=1 X I t,t It (t)
8 Parametric Bandits [Lai&Robbins] X it p i,θi ( ), θ i unknown, t=1,2, Uncertainty set: Reasonable values of θ given the experience so far U i,t ={θ p i,θ (X i,1:ti (t)) is large mod (t,t i (t)) } Inflated values: Z i,t =max{ E θ θ U i,t } Rule: I t = arg max i Z i,t
9 Bounds Upper bound: Lower bound: If an algorithm is uniformly good then..
10 UCB1 Algorithm (Auer et al., 2002) Algorithm: UCB1(b) 1. Try all options once 2. Use option k with the highest index: Regret bound: R n : Expected loss due to not selecting the best option at time step n. Then:
11 Problem #1 When b 2 σ 2, regret should scale with σ 2 and not b 2!
12 UCB1-NORMAL Algorithm: UCB1-NORMAL 1. Try all options once 2. Use option k with the highest index: ˆµ kt + Regret bound: 16ˆσ 2 kt log(t) T k (t 1)
13 Problem #1 The regret of UCB1(b) scales with O(b 2 ) The regret of UCB1-NORMAL scales with O(σ 2 ) but UCB1-NORMAL assumes normally distributed payoffs UCB-Tuned(b): ˆµ kt + min ( b 2 4, σ2 kt Good experimental results No theoretical guarantees ) log(t) T k (t 1)
14 UCB-V Algorithm: UCB-V(b) 1. Try all options once 2. Use option k with the highest index: ˆµ kt + Regret bound: 2.4 σ 2 kt log(t) T k (t 1) + 3blog(t) T k (t 1)
15 Proof The missing bound (hunch.net): ˆµ t µ σ t log(3δ 1 ) t + 3blog(3δ 1 ) t Bounding the sampling times of suboptimal arms (new bound)
16 Can we decrease exploration? Algorithm: UCB-V(b,ζ,c) 1. Try all options once 2. Use option k with the highest index: ˆµ kt + Theorem: 2ζ σ 2 kt log(t) T k (t 1) +c3blog(t) T k (t 1) When ζ<1, the regret will be polynomial for some bandit problems When cζ<1/6, the regret will be polynomial for some bandit problems
17 Concentration bounds Averages concentrate: S n n µ ( O log(δ 1 ) n Does the regret of UCB* concentrate? R n n µ?? R n E[R n ] 1?? ) RISK??
18 Logarithmic regret implies high risk Theorem: Consider the pseudo-regret R n = k=1k T k (n) k. Then for any ζ>1 and z>γ log(n), P(R n >z) C z -ζ (Gaussian tail:p(r n >z) C exp(-z 2 )) Illustration: Two arms; 2 = µ 2 -µ 1 >0. Modes of law of R n at O(log(n)), O( 2 n)! Only happens when the support of the second best arm s distribution overlaps with that of the optimal arm
19 Finite horizon: PAC-UCB Algorithm: PAC-UCB(N) 1. Try all options ones 2. Use option k with the highest index: ˆµ kt + 2 σ 2 kt L t T k (t 1) + 3bL t T k (t 1), L t =log(nk(t k (t 1)+1)) Theorem: At time N with probability 1-1/N, suboptimal plays are bounded by O(log(K N)). Good when N is known beforehand
20 Conclusions Taking into account the variance lessens dependence on the a priori bound b Low expected regret => high risk PAC-UCB: Finite regret, known horizon, exponential concentration of the regret Optimal balance? Other algorithms? Greater generality: look up the paper!
21 Thank you! Questions?
22 References Optimism in the face of uncertainty: Lai, T. L. and Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6:4 22. UCB1 and more: Auer, P., Cesa-Bianchi, N., and Fischer, P. (2002). Finite time analysis of the multiarmed bandit problem. Machine Learning, 47(2-3): Audibert, J., Munos, R., and Szepesvári, Cs. (2007). Tuning bandit algorithms in stochastic environments, ALT-2007.
Monte-Carlo Planning: Introduction and Bandit Basics. Alan Fern
Monte-Carlo Planning: Introduction and Bandit Basics Alan Fern 1 Large Worlds We have considered basic model-based planning algorithms Model-based planning: assumes MDP model is available Methods we learned
More informationMonte-Carlo Planning: Introduction and Bandit Basics. Alan Fern
Monte-Carlo Planning: Introduction and Bandit Basics Alan Fern 1 Large Worlds We have considered basic model-based planning algorithms Model-based planning: assumes MDP model is available Methods we learned
More informationMulti-armed bandit problems
Multi-armed bandit problems Stochastic Decision Theory (2WB12) Arnoud den Boer 13 March 2013 Set-up 13 and 14 March: Lectures. 20 and 21 March: Paper presentations (Four groups, 45 min per group). Before
More informationBandit algorithms for tree search Applications to games, optimization, and planning
Bandit algorithms for tree search Applications to games, optimization, and planning Rémi Munos SequeL project: Sequential Learning http://sequel.futurs.inria.fr/ INRIA Lille - Nord Europe Journées MAS
More informationTreatment Allocations Based on Multi-Armed Bandit Strategies
Treatment Allocations Based on Multi-Armed Bandit Strategies Wei Qian and Yuhong Yang Applied Economics and Statistics, University of Delaware School of Statistics, University of Minnesota Innovative Statistics
More informationAn algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits
JMLR: Workshop and Conference Proceedings vol 49:1 5, 2016 An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits Peter Auer Chair for Information Technology Montanuniversitaet
More informationDynamic Pricing with Varying Cost
Dynamic Pricing with Varying Cost L. Jeff Hong College of Business City University of Hong Kong Joint work with Ying Zhong and Guangwu Liu Outline 1 Introduction 2 Problem Formulation 3 Pricing Policy
More informationMulti-Armed Bandit, Dynamic Environments and Meta-Bandits
Multi-Armed Bandit, Dynamic Environments and Meta-Bandits C. Hartland, S. Gelly, N. Baskiotis, O. Teytaud and M. Sebag Lab. of Computer Science CNRS INRIA Université Paris-Sud, Orsay, France Abstract This
More informationBernoulli Bandits An Empirical Comparison
Bernoulli Bandits An Empirical Comparison Ronoh K.N1,2, Oyamo R.1,2, Milgo E.1,2, Drugan M.1 and Manderick B.1 1- Vrije Universiteit Brussel - Computer Sciences Department - AI Lab Pleinlaan 2 - B-1050
More information1 Bandit View on Noisy Optimization
1 Bandit View on Noisy Optimization Jean-Yves Audibert audibert@certis.enpc.fr Imagine, Université Paris Est; Willow, CNRS/ENS/INRIA Paris, France Sébastien Bubeck sebastien.bubeck@inria.fr Sequel Project,
More informationMonte-Carlo Planning: Basic Principles and Recent Progress
Monte-Carlo Planning: Basic Principles and Recent Progress Alan Fern School of EECS Oregon State University Outline Preliminaries: Markov Decision Processes What is Monte-Carlo Planning? Uniform Monte-Carlo
More informationAdaptive Experiments for Policy Choice. March 8, 2019
Adaptive Experiments for Policy Choice Maximilian Kasy Anja Sautmann March 8, 2019 Introduction The goal of many experiments is to inform policy choices: 1. Job search assistance for refugees: Treatments:
More informationLearning for Revenue Optimization. Andrés Muñoz Medina Renato Paes Leme
Learning for Revenue Optimization Andrés Muñoz Medina Renato Paes Leme How to succeed in business with basic ML? ML $1 $5 $10 $9 Google $35 $1 $8 $7 $7 Revenue $8 $30 $24 $18 $10 $1 $5 Price $7 $8$9$10
More informationMonte-Carlo Planning Look Ahead Trees. Alan Fern
Monte-Carlo Planning Look Ahead Trees Alan Fern 1 Monte-Carlo Planning Outline Single State Case (multi-armed bandits) A basic tool for other algorithms Monte-Carlo Policy Improvement Policy rollout Policy
More informationExploration for sequential decision making Application to games, tree search, optimization, and planning
Exploration for sequential decision making Application to games, tree search, optimization, and planning Rémi Munos SequeL project: Sequential Learning http://sequel.futurs.inria.fr/ INRIA Lille - Nord
More informationBandit Learning with switching costs
Bandit Learning with switching costs Jian Ding, University of Chicago joint with: Ofer Dekel (MSR), Tomer Koren (Technion) and Yuval Peres (MSR) June 2016, Harvard University Online Learning with k -Actions
More informationThe Non-stationary Stochastic Multi-armed Bandit Problem
The Non-stationary Stochastic Multi-armed Bandit Problem Robin Allesiardo, Raphaël Féraud, Odalric-Ambrym Maillard To cite this version: Robin Allesiardo, Raphaël Féraud, Odalric-Ambrym Maillard The Non-stationary
More informationBlazing the trails before beating the path: Sample-efficient Monte-Carlo planning
Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning Jean-Bastien Grill Michal Valko SequeL team, INRIA Lille - Nord Europe, France jean-bastien.grill@inria.fr michal.valko@inria.fr
More informationOptimistic Planning for the Stochastic Knapsack Problem
Optimistic Planning for the Stochastic Knapsack Problem Anonymous Author Anonymous Author 2 Anonymous Author 3 Unknown Institution Unknown Institution 2 Unknown Institution 3 Abstract The stochastic knapsack
More informationHigh Dimensional Bayesian Optimisation and Bandits via Additive Models
1/20 High Dimensional Bayesian Optimisation and Bandits via Additive Models Kirthevasan Kandasamy, Jeff Schneider, Barnabás Póczos ICML 15 July 8 2015 2/20 Bandits & Optimisation Maximum Likelihood inference
More informationApplying Monte Carlo Tree Search to Curling AI
AI 1,a) 2,b) MDP Applying Monte Carlo Tree Search to Curling AI Katsuki Ohto 1,a) Tetsuro Tanaka 2,b) Abstract: We propose an action decision method based on Monte Carlo Tree Search for MDPs with continuous
More informationZooming Algorithm for Lipschitz Bandits
Zooming Algorithm for Lipschitz Bandits Alex Slivkins Microsoft Research New York City Based on joint work with Robert Kleinberg and Eli Upfal (STOC'08) Running examples Dynamic pricing. You release a
More informationThe Irrevocable Multi-Armed Bandit Problem
The Irrevocable Multi-Armed Bandit Problem Ritesh Madan Qualcomm-Flarion Technologies May 27, 2009 Joint work with Vivek Farias (MIT) 2 Multi-Armed Bandit Problem n arms, where each arm i is a Markov Decision
More informationRollout Allocation Strategies for Classification-based Policy Iteration
Rollout Allocation Strategies for Classification-based Policy Iteration V. Gabillon, A. Lazaric & M. Ghavamzadeh firstname.lastname@inria.fr Workshop on Reinforcement Learning and Search in Very Large
More informationFoundations of Artificial Intelligence
Foundations of Artificial Intelligence 44. Monte-Carlo Tree Search: Introduction Thomas Keller Universität Basel May 27, 2016 Board Games: Overview chapter overview: 41. Introduction and State of the Art
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 informationD I S C O N T I N U O U S DEMAND FUNCTIONS: ESTIMATION AND PRICING. Rotterdam May 24, 2018
D I S C O N T I N U O U S DEMAND FUNCTIONS: ESTIMATION AND PRICING Arnoud V. den Boer University of Amsterdam N. Bora Keskin Duke University Rotterdam May 24, 2018 Dynamic pricing and learning: Learning
More informationLecture 7: Bayesian approach to MAB - Gittins index
Advanced Topics in Machine Learning and Algorithmic Game Theory Lecture 7: Bayesian approach to MAB - Gittins index Lecturer: Yishay Mansour Scribe: Mariano Schain 7.1 Introduction In the Bayesian approach
More informationRegret Minimization against Strategic Buyers
Regret Minimization against Strategic Buyers Mehryar Mohri Courant Institute & Google Research Andrés Muñoz Medina Google Research Motivation Online advertisement: revenue of modern search engine and
More informationDynamic Pricing under Finite Space Demand Uncertainty: A Multi-Armed Bandit with Dependent Arms
1 Dynamic Pricing under Finite Space Demand Uncertainty: A Multi-Armed Bandit with Dependent Arms Pouya Tehrani, Yixuan Zhai, Qing Zhao Department of Electrical and Computer Engineering University of California,
More informationReduced-Variance Payoff Estimation in Adversarial Bandit Problems
Reduced-Variance Payoff Estimation in Adversarial Bandit Problems Levente Kocsis and Csaba Szepesvári Computer and Automation Research Institute of the Hungarian Academy of Sciences, Kende u. 13-17, 1111
More informationMulti-armed bandits in dynamic pricing
Multi-armed bandits in dynamic pricing Arnoud den Boer University of Twente, Centrum Wiskunde & Informatica Amsterdam Lancaster, January 11, 2016 Dynamic pricing A firm sells a product, with abundant inventory,
More informationBiasing Monte-Carlo Simulations through RAVE Values
Biasing Monte-Carlo Simulations through RAVE Values Arpad Rimmel, Fabien Teytaud, Olivier Teytaud To cite this version: Arpad Rimmel, Fabien Teytaud, Olivier Teytaud. Biasing Monte-Carlo Simulations through
More informationLarge-Scale SVM Optimization: Taking a Machine Learning Perspective
Large-Scale SVM Optimization: Taking a Machine Learning Perspective Shai Shalev-Shwartz Toyota Technological Institute at Chicago Joint work with Nati Srebro Talk at NEC Labs, Princeton, August, 2008 Shai
More informationLecture 17: More on Markov Decision Processes. Reinforcement learning
Lecture 17: More on Markov Decision Processes. Reinforcement learning Learning a model: maximum likelihood Learning a value function directly Monte Carlo Temporal-difference (TD) learning COMP-424, Lecture
More informationEstimation after Model Selection
Estimation after Model Selection Vanja M. Dukić Department of Health Studies University of Chicago E-Mail: vanja@uchicago.edu Edsel A. Peña* Department of Statistics University of South Carolina E-Mail:
More informationChapter 8: Sampling distributions of estimators Sections
Chapter 8: Sampling distributions of estimators Sections 8.1 Sampling distribution of a statistic 8.2 The Chi-square distributions 8.3 Joint Distribution of the sample mean and sample variance Skip: p.
More informationMVE051/MSG Lecture 7
MVE051/MSG810 2017 Lecture 7 Petter Mostad Chalmers November 20, 2017 The purpose of collecting and analyzing data Purpose: To build and select models for parts of the real world (which can be used for
More informationChapter 7: Estimation Sections
1 / 31 : Estimation Sections 7.1 Statistical Inference Bayesian Methods: 7.2 Prior and Posterior Distributions 7.3 Conjugate Prior Distributions 7.4 Bayes Estimators Frequentist Methods: 7.5 Maximum Likelihood
More informationThe Value of Stochastic Modeling in Two-Stage Stochastic Programs
The Value of Stochastic Modeling in Two-Stage Stochastic Programs Erick Delage, HEC Montréal Sharon Arroyo, The Boeing Cie. Yinyu Ye, Stanford University Tuesday, October 8 th, 2013 1 Delage et al. Value
More informationData-Driven Pricing of Demand Response
Data-Driven Pricing of Demand Response Kia Khezeli Eilyan Bitar Abstract We consider the setting in which an electric power utility seeks to curtail its peak electricity demand by offering a fixed group
More informationThe Sample-Complexity of General Reinforcement Learning
Tor Lattimore Australian National University Marcus Hutter Australian National University Peter Sunehag Australian National University Abstract We present a new algorithm for general reinforcement learning
More informationLecture 5. 1 Online Learning. 1.1 Learning Setup (Perspective of Universe) CSCI699: Topics in Learning & Game Theory
CSCI699: Topics in Learning & Game Theory Lecturer: Shaddin Dughmi Lecture 5 Scribes: Umang Gupta & Anastasia Voloshinov In this lecture, we will give a brief introduction to online learning and then go
More informationMonte-Carlo Planning Look Ahead Trees. Alan Fern
Monte-Carlo Planning Look Ahead Trees Alan Fern 1 Monte-Carlo Planning Outline Single State Case (multi-armed bandits) A basic tool for other algorithms Monte-Carlo Policy Improvement Policy rollout Policy
More informationPoint Estimation. Principle of Unbiased Estimation. When choosing among several different estimators of θ, select one that is unbiased.
Point Estimation Point Estimation Definition A point estimate of a parameter θ is a single number that can be regarded as a sensible value for θ. A point estimate is obtained by selecting a suitable statistic
More informationApplied Statistics I
Applied Statistics I Liang Zhang Department of Mathematics, University of Utah July 14, 2008 Liang Zhang (UofU) Applied Statistics I July 14, 2008 1 / 18 Point Estimation Liang Zhang (UofU) Applied Statistics
More informationChapter 7: Estimation Sections
1 / 40 Chapter 7: Estimation Sections 7.1 Statistical Inference Bayesian Methods: Chapter 7 7.2 Prior and Posterior Distributions 7.3 Conjugate Prior Distributions 7.4 Bayes Estimators Frequentist Methods:
More informationAN ONLINE LEARNING APPROACH TO ALGORITHMIC BIDDING FOR VIRTUAL TRADING
AN ONLINE LEARNING APPROACH TO ALGORITHMIC BIDDING FOR VIRTUAL TRADING Lang Tong School of Electrical & Computer Engineering Cornell University, Ithaca, NY Joint work with Sevi Baltaoglu and Qing Zhao
More informationLecture 11: Bandits with Knapsacks
CMSC 858G: Bandits, Experts and Games 11/14/16 Lecture 11: Bandits with Knapsacks Instructor: Alex Slivkins Scribed by: Mahsa Derakhshan 1 Motivating Example: Dynamic Pricing The basic version of the dynamic
More informationMATH3075/3975 FINANCIAL MATHEMATICS TUTORIAL PROBLEMS
MATH307/37 FINANCIAL MATHEMATICS TUTORIAL PROBLEMS School of Mathematics and Statistics Semester, 04 Tutorial problems should be used to test your mathematical skills and understanding of the lecture material.
More informationA reinforcement learning process in extensive form games
A reinforcement learning process in extensive form games Jean-François Laslier CNRS and Laboratoire d Econométrie de l Ecole Polytechnique, Paris. Bernard Walliser CERAS, Ecole Nationale des Ponts et Chaussées,
More informationConfidence Intervals Introduction
Confidence Intervals Introduction A point estimate provides no information about the precision and reliability of estimation. For example, the sample mean X is a point estimate of the population mean μ
More informationLesson 3: Basic theory of stochastic processes
Lesson 3: Basic theory of stochastic processes Dipartimento di Ingegneria e Scienze dell Informazione e Matematica Università dell Aquila, umberto.triacca@univaq.it Probability space We start with some
More informationMDP Algorithms. Thomas Keller. June 20, University of Basel
MDP Algorithms Thomas Keller University of Basel June 20, 208 Outline of this lecture Markov decision processes Planning via determinization Monte-Carlo methods Monte-Carlo Tree Search Heuristic Search
More informationRisk Measurement in Credit Portfolio Models
9 th DGVFM Scientific Day 30 April 2010 1 Risk Measurement in Credit Portfolio Models 9 th DGVFM Scientific Day 30 April 2010 9 th DGVFM Scientific Day 30 April 2010 2 Quantitative Risk Management Profit
More informationOptimal Search for Parameters in Monte Carlo Simulation for Derivative Pricing
Optimal Search for Parameters in Monte Carlo Simulation for Derivative Pricing Prof. Chuan-Ju Wang Department of Computer Science University of Taipei Joint work with Prof. Ming-Yang Kao March 28, 2014
More informationAsymptotic results discrete time martingales and stochastic algorithms
Asymptotic results discrete time martingales and stochastic algorithms Bernard Bercu Bordeaux University, France IFCAM Summer School Bangalore, India, July 2015 Bernard Bercu Asymptotic results for discrete
More informationDistributed Non-Stochastic Experts
Distributed Non-Stochastic Experts Varun Kanade UC Berkeley vkanade@eecs.berkeley.edu Zhenming Liu Princeton University zhenming@cs.princeton.edu Božidar Radunović Microsoft Research bozidar@microsoft.com
More informationSequential Decision Making
Sequential Decision Making Dynamic programming Christos Dimitrakakis Intelligent Autonomous Systems, IvI, University of Amsterdam, The Netherlands March 18, 2008 Introduction Some examples Dynamic programming
More informationEE641 Digital Image Processing II: Purdue University VISE - October 29,
EE64 Digital Image Processing II: Purdue University VISE - October 9, 004 The EM Algorithm. Suffient Statistics and Exponential Distributions Let p(y θ) be a family of density functions parameterized by
More informationChapter 8: Sampling distributions of estimators Sections
Chapter 8 continued Chapter 8: Sampling distributions of estimators Sections 8.1 Sampling distribution of a statistic 8.2 The Chi-square distributions 8.3 Joint Distribution of the sample mean and sample
More informationAccelerated Stochastic Gradient Descent Praneeth Netrapalli MSR India
Accelerated Stochastic Gradient Descent Praneeth Netrapalli MSR India Presented at OSL workshop, Les Houches, France. Joint work with Prateek Jain, Sham M. Kakade, Rahul Kidambi and Aaron Sidford Linear
More informationCS885 Reinforcement Learning Lecture 3b: May 9, 2018
CS885 Reinforcement Learning Lecture 3b: May 9, 2018 Intro to Reinforcement Learning [SutBar] Sec. 5.1-5.3, 6.1-6.3, 6.5, [Sze] Sec. 3.1, 4.3, [SigBuf] Sec. 2.1-2.5, [RusNor] Sec. 21.1-21.3, CS885 Spring
More informationMA 490. Senior Project
MA 490 Senior Project Project: Prove that the cumulative binomial distributions and the Poisson distributions can be approximated by the Normal distribution and that that approximation gets better as the
More informationCan we have no Nash Equilibria? Can you have more than one Nash Equilibrium? CS 430: Artificial Intelligence Game Theory II (Nash Equilibria)
CS 0: Artificial Intelligence Game Theory II (Nash Equilibria) ACME, a video game hardware manufacturer, has to decide whether its next game machine will use DVDs or CDs Best, a video game software producer,
More informationEFFICIENT MONTE CARLO ALGORITHM FOR PRICING BARRIER OPTIONS
Commun. Korean Math. Soc. 23 (2008), No. 2, pp. 285 294 EFFICIENT MONTE CARLO ALGORITHM FOR PRICING BARRIER OPTIONS Kyoung-Sook Moon Reprinted from the Communications of the Korean Mathematical Society
More informationOptimal Regret Minimization in Posted-Price Auctions with Strategic Buyers
Optimal Regret Minimization in Posted-Price Auctions with Strategic Buyers Mehryar Mohri Courant Institute and Google Research 251 Mercer Street New York, NY 10012 mohri@cims.nyu.edu Andres Muñoz Medina
More informationChapter 4: Asymptotic Properties of MLE (Part 3)
Chapter 4: Asymptotic Properties of MLE (Part 3) Daniel O. Scharfstein 09/30/13 1 / 1 Breakdown of Assumptions Non-Existence of the MLE Multiple Solutions to Maximization Problem Multiple Solutions to
More informationDecision Analysis. Carlos A. Santos Silva June 5 th, 2009
Decision Analysis Carlos A. Santos Silva June 5 th, 2009 What is decision analysis? Often, there is more than one possible solution: Decision depends on the criteria Decision often must be made in uncertain
More informationBandit based Monte-Carlo Planning
Bandit based Monte-Carlo Planning Levente Kocsis and Csaba Szepesvári Computer and Automation Research Institute of the Hungarian Academy of Sciences, Kende u. 13-17, 1111 Budapest, Hungary kocsis@sztaki.hu
More informationLearning the Demand Curve in Posted-Price Digital Goods Auctions
Learning the Demand Curve in Posted-Price Digital Goods Auctions ABSTRACT Meenal Chhabra Rensselaer Polytechnic Inst. Dept. of Computer Science Troy, NY, USA chhabm@cs.rpi.edu Online digital goods auctions
More informationOPTIMAL PORTFOLIO CONTROL WITH TRADING STRATEGIES OF FINITE
Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference 005 Seville, Spain, December 1-15, 005 WeA11.6 OPTIMAL PORTFOLIO CONTROL WITH TRADING STRATEGIES OF
More informationStrategies and Nash Equilibrium. A Whirlwind Tour of Game Theory
Strategies and Nash Equilibrium A Whirlwind Tour of Game Theory (Mostly from Fudenberg & Tirole) Players choose actions, receive rewards based on their own actions and those of the other players. Example,
More informationONLINE LEARNING IN LIMIT ORDER BOOK TRADE EXECUTION
ONLINE LEARNING IN LIMIT ORDER BOOK TRADE EXECUTION Nima Akbarzadeh, Cem Tekin Bilkent University Electrical and Electronics Engineering Department Ankara, Turkey Mihaela van der Schaar Oxford Man Institute
More informationModelling Returns: the CER and the CAPM
Modelling Returns: the CER and the CAPM Carlo Favero Favero () Modelling Returns: the CER and the CAPM 1 / 20 Econometric Modelling of Financial Returns Financial data are mostly observational data: they
More informationINVERSE REWARD DESIGN
INVERSE REWARD DESIGN Dylan Hadfield-Menell, Smith Milli, Pieter Abbeel, Stuart Russell, Anca Dragan University of California, Berkeley Slides by Anthony Chen Inverse Reinforcement Learning (Review) Inverse
More informationElif Özge Özdamar T Reinforcement Learning - Theory and Applications February 14, 2006
On the convergence of Q-learning Elif Özge Özdamar elif.ozdamar@helsinki.fi T-61.6020 Reinforcement Learning - Theory and Applications February 14, 2006 the covergence of stochastic iterative algorithms
More informationInference of Several Log-normal Distributions
Inference of Several Log-normal Distributions Guoyi Zhang 1 and Bose Falk 2 Abstract This research considers several log-normal distributions when variances are heteroscedastic and group sizes are unequal.
More informationMachine Learning for Quantitative Finance
Machine Learning for Quantitative Finance Fast derivative pricing Sofie Reyners Joint work with Jan De Spiegeleer, Dilip Madan and Wim Schoutens Derivative pricing is time-consuming... Vanilla option pricing
More informationEstimating Pricing Kernel via Series Methods
Estimating Pricing Kernel via Series Methods Maria Grith Wolfgang Karl Härdle Melanie Schienle Ladislaus von Bortkiewicz Chair of Statistics Chair of Econometrics C.A.S.E. Center for Applied Statistics
More informationStochastic Dual Dynamic Programming
1 / 43 Stochastic Dual Dynamic Programming Operations Research Anthony Papavasiliou 2 / 43 Contents [ 10.4 of BL], [Pereira, 1991] 1 Recalling the Nested L-Shaped Decomposition 2 Drawbacks of Nested Decomposition
More informationRevenue Management with Incomplete Demand Information
Revenue Management with Incomplete Demand Information Victor F. Araman René Caldentey Stern School of Business, New York University, New York, NY 10012. Abstract Consider a seller who is endowed with a
More informationDynamic Pricing with Limited Supply (extended abstract)
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
More informationDefinition 9.1 A point estimate is any function T (X 1,..., X n ) of a random sample. We often write an estimator of the parameter θ as ˆθ.
9 Point estimation 9.1 Rationale behind point estimation When sampling from a population described by a pdf f(x θ) or probability function P [X = x θ] knowledge of θ gives knowledge of the entire population.
More informationCooperative Games with Monte Carlo Tree Search
Int'l Conf. Artificial Intelligence ICAI'5 99 Cooperative Games with Monte Carlo Tree Search CheeChian Cheng and Norman Carver Department of Computer Science, Southern Illinois University, Carbondale,
More informationChapter 3 Discrete Random Variables and Probability Distributions
Chapter 3 Discrete Random Variables and Probability Distributions Part 2: Mean and Variance of a Discrete Random Variable Section 3.4 1 / 16 Discrete Random Variable - Expected Value In a random experiment,
More informationContents. 1 Introduction. Math 321 Chapter 5 Confidence Intervals. 1 Introduction 1
Math 321 Chapter 5 Confidence Intervals (draft version 2019/04/11-11:17:37) Contents 1 Introduction 1 2 Confidence interval for mean µ 2 2.1 Known variance................................. 2 2.2 Unknown
More informationCharacterization of the Optimum
ECO 317 Economics of Uncertainty Fall Term 2009 Notes for lectures 5. Portfolio Allocation with One Riskless, One Risky Asset Characterization of the Optimum Consider a risk-averse, expected-utility-maximizing
More informationOptimally Thresholded Realized Power Variations for Lévy Jump Diffusion Models
Optimally Thresholded Realized Power Variations for Lévy Jump Diffusion Models José E. Figueroa-López 1 1 Department of Statistics Purdue University University of Missouri-Kansas City Department of Mathematics
More informationCompound Reinforcement Learning: Theory and An Application to Finance
Compound Reinforcement Learning: Theory and An Application to Finance Tohgoroh Matsui 1, Takashi Goto 2, Kiyoshi Izumi 3,4, and Yu Chen 3 1 Chubu University, 1200 Matsumoto-cho, Kasugai, 487-8501 Aichi,
More informationarxiv: v1 [cs.lg] 23 Nov 2014
Revenue Optimization in Posted-Price Auctions with Strategic Buyers arxiv:.0v [cs.lg] Nov 0 Mehryar Mohri Courant Institute and Google Research Mercer Street New York, NY 00 mohri@cims.nyu.edu Abstract
More informationChapter 7: Point Estimation and Sampling Distributions
Chapter 7: Point Estimation and Sampling Distributions Seungchul Baek Department of Statistics, University of South Carolina STAT 509: Statistics for Engineers 1 / 20 Motivation In chapter 3, we learned
More informationReinforcement Learning
Reinforcement Learning Michèle Sebag ; TP : Herilalaina Rakotoarison TAO, CNRS INRIA Université Paris-Sud Nov. 26th, 2018 Credit for slides: Richard Sutton, Freek Stulp, Olivier Pietquin 1 / 90 Where we
More informationLecture 22. Survey Sampling: an Overview
Math 408 - Mathematical Statistics Lecture 22. Survey Sampling: an Overview March 25, 2013 Konstantin Zuev (USC) Math 408, Lecture 22 March 25, 2013 1 / 16 Survey Sampling: What and Why In surveys sampling
More informationSupplementary Material: Strategies for exploration in the domain of losses
1 Supplementary Material: Strategies for exploration in the domain of losses Paul M. Krueger 1,, Robert C. Wilson 2,, and Jonathan D. Cohen 3,4 1 Department of Psychology, University of California, Berkeley
More informationStochastic Approximation Algorithms and Applications
Harold J. Kushner G. George Yin Stochastic Approximation Algorithms and Applications With 24 Figures Springer Contents Preface and Introduction xiii 1 Introduction: Applications and Issues 1 1.0 Outline
More informationAdaptive Control Applied to Financial Market Data
Adaptive Control Applied to Financial Market Data J.Sindelar Charles University, Faculty of Mathematics and Physics and Institute of Information Theory and Automation, Academy of Sciences of the Czech
More informationThe value of foresight
Philip Ernst Department of Statistics, Rice University Support from NSF-DMS-1811936 (co-pi F. Viens) and ONR-N00014-18-1-2192 gratefully acknowledged. IMA Financial and Economic Applications June 11, 2018
More informationu (x) < 0. and if you believe in diminishing return of the wealth, then you would require
Chapter 8 Markowitz Portfolio Theory 8.7 Investor Utility Functions People are always asked the question: would more money make you happier? The answer is usually yes. The next question is how much more
More informationParametric Inference and Dynamic State Recovery from Option Panels. Nicola Fusari
Parametric Inference and Dynamic State Recovery from Option Panels Nicola Fusari Joint work with Torben G. Andersen and Viktor Todorov July 2012 Motivation Under realistic assumptions derivatives are nonredundant
More information