Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
|
|
- Meryl Harmon
- 5 years ago
- Views:
Transcription
1 for Strongly Convex Stochastic Optimization Microsoft Research New England NIPS 2011 Optimization Workshop
2 Stochastic Convex Optimization Setting Goal: Optimize convex function F ( ) over convex domain W Access to unbiased estimates of F subgradients (e.g. by sampling from a training set) Simple and very popular method - stochastic gradient descent (SGD): Initialize w = 0 For t = 1, 2,... Get ĝ t such that E[ĝ t ] F (w t ) w t+1 = Π W (w t η t ĝ t ) With appropriate step-size η t, average w T = 1 T (w w T ) has suboptimality F ( w T ) F (w ) = O(1/ T )
3 Strongly Convex Stochastic Optimization F ( ) is strongly convex: For some λ > 0, F (w ) F (w) + g, w w + λ 2 for all w, w W and all g F (w) w w 2 E.g. regularized learning F (w) = 1 m m i=1 l(w, z i) + λ 2 w 2
4 Strongly Convex Stochastic Optimization Theorem (Hazan et al. (2007); Shalev-Shwartz et al. (2008)) Suppose F is λ-strongly convex ĝ t uniformly bounded By running SGD with step sizes η t = 1 λt, expected suboptimality of average w T = 1 T (w w T ) at most ( ) log(t ) O λt Proof goes through online learning: a more difficult setting where gradients assumed to be provided by an adversary
5 Better Algorithms Hazan and Kale (2010): Propose an algorithm different from SGD, with optimal 1/λT rate (removes the log factor) Juditsky and Nesterov (2010): Independently and a bit later, propose virtually identical algorithm for a somewhat more general setting Important gap: Are these new algorithms actually better than SGD?? If so, we should abandon SGD! (say, for solving support vector machines)
6 Related Work Convergence of SGD very well studied for over 50 years More recent work on non-asymptotic performance (e.g. Bach (2011)) Almost all results are under smoothness assumptions on F - inappropriate for many modern applications E.g. Support Vector Machines: optimize 1 m m [1 y i w, x i ] + + λ 2 w 2 i=1 Any regularized learning framework with non-smooth losses (absolute loss, ɛ-insensitive loss...)
7 This Work We study the convergence rate of SGD for stochastic strongly convex (possibly non-smooth) problems Main Findings:
8 This Work We study the convergence rate of SGD for stochastic strongly convex (possibly non-smooth) problems Main Findings: 1 (Mostly known): If F is strongly convex and smooth, then SGD with and without averaging achieves optimal O(1/T ) rate
9 This Work We study the convergence rate of SGD for stochastic strongly convex (possibly non-smooth) problems Main Findings: 1 (Mostly known): If F is strongly convex and smooth, then SGD with and without averaging achieves optimal O(1/T ) rate 2 If F is non-smooth, SGD with averaging might really have a Θ(log(T )/T ) rate
10 This Work We study the convergence rate of SGD for stochastic strongly convex (possibly non-smooth) problems Main Findings: 1 (Mostly known): If F is strongly convex and smooth, then SGD with and without averaging achieves optimal O(1/T ) rate 2 If F is non-smooth, SGD with averaging might really have a Θ(log(T )/T ) rate 3 By a slight change of averaging step, can recover optimal O(1/T ) rate for SGD - no new algorithm required!
11 This Work We study the convergence rate of SGD for stochastic strongly convex (possibly non-smooth) problems Main Findings: 1 (Mostly known): If F is strongly convex and smooth, then SGD with and without averaging achieves optimal O(1/T ) rate 2 If F is non-smooth, SGD with averaging might really have a Θ(log(T )/T ) rate 3 By a slight change of averaging step, can recover optimal O(1/T ) rate for SGD - no new algorithm required! 4 Corroborate our findings experimentally
12 This Work We study the convergence rate of SGD for stochastic strongly convex (possibly non-smooth) problems Main Findings: 1 (Mostly known): If F is strongly convex and smooth, then SGD with and without averaging achieves optimal O(1/T ) rate 2 If F is non-smooth, SGD with averaging might really have a Θ(log(T )/T ) rate 3 By a slight change of averaging step, can recover optimal O(1/T ) rate for SGD - no new algorithm required! 4 Corroborate our findings experimentally Also: avoiding an online learning analysis leads to weaker conditions on step sizes
13 Smooth F We define F as µ-smooth if for any w W, F (w) F (w ) µ 2 w w 2 Note: we require smoothness only at w
14 Smooth F We define F as µ-smooth if for any w W, F (w) F (w ) µ 2 w w 2 Note: we require smoothness only at w Classical Analysis (Chung 1954, Sacks 1958,...) Suppose F is λ-strongly convex and µ-smooth; E[ ĝ t 2 ] uniformly bounded The last predictor w T returned by SGD with step-size c/λt, c > 1/2 gives ( cµ ) E [F (w T ) F (w )] O λ 2 T
15 Smooth F Proof idea in 3 steps: 1 Strong convexity implies the recursive inequality [ E w t+1 w 2] (1 2η t λ)e[ w t w 2 ] + O(ηt 2 ) 2 Solving the recursion, we get E [ w T w 2] O 3 By smoothness of F, implies Theorem E [F (w T ) F (w )] O For average predictor w T = 1 T (w w T ), ( µ E [F ( w T ) F (w )] O λ ( c ) λ 2 T ( cµ ) λ 2 T ( ) ) c λ T
16 Non-Smooth F When [ F non-smooth, can still show E w T w 2] O(1/T ), but this is insufficient to show O(1/T ) suboptimality On other hand, by an online learning analysis, E [F ( w T ) F (w )] O(log(T )/T ) Maybe log(t ) just artifact of analysis? Answer: NO! Exists stochastic problems where suboptimality of w T is really Θ(log(T )/T )
17 Warm-up Suppose W = [0, 1] F (w) = 1 2 w 2 + w Non-smooth with respect to w = 0 ĝ t = F (w t ) + U[ 2, 2] Can be shown that E[w t ] = Ω ( 1 t ( Therefore, E[ w T ] = Ω 1 T T t=1 1 t But this example is not satisfying... ) ) = Ω( log(t ) T )
18 Second Example W = R (can be easily extended to R d ) { F (w) = 1 2 w 2 w w 0 + 7w w < 0 ĝ t = F (w t ) + U[ 2, 2] Sharp gradient for w 0 makes w t stay at the positive side - same effect as explicit domain constraint in previous example As before, E[w t ] = Ω ( ) 1 t, leading to wt = Ω( log(t ) T )
19 Fixing SGD Conclusion: log(t )/T is inevitable for SGD with averaging Problematic point: averaging step w T = 1 T (w w T ) However, can t prove much for w T in non-smooth case... Solution: do something in between!
20 Fixing SGD α-suffix Averaging For some α (0, 1), define Theorem w α T = w (1 α)t w T αt For SGD with α-suffix averaging, and step size c/λt, c > 1/2, ( ) E[F ( w T α ) F (w )] O log 1 1 α c α λt Proof idea: Combination of online analysis technique with stochastic convergence guarantees on E[ w T w 2 ]
21 Experiments Smooth and Strongly convex F (F(w T ) F(w * )) * T SGD A SGD α SGD L EPOCH GD log 2 (T) Non-Smooth and Strongly Convex F (F(w T ) F(w * )) * T SGD A SGD α SGD L EPOCH GD log 2 (T)
22 Experiments log 2 (F(w T )) ASTRO Training Loss SGD A SGD α SGD L EPOCH GD log 2 (F(w T )) ASTRO Test Loss SGD A SGD α SGD L EPOCH GD log 2 (T) COV1 Training Loss log 2 (T) COV1 Test Loss log 2 (F(w T )) SGD A SGD α SGD L EPOCH GD log 2 (F(w t )) SGD A SGD α SGD L EPOCH GD log 2 (T) log 2 (T)
23 Conclusions and Open Problems SGD performs optimally in the smooth case In non-smooth case, averaging leads to log(t )/T rate - artifact of algorithm, not just the online analysis However, easily fixed by different averaging step - no new algorithm necessary Experiments accord with theory Open questions: Can we show 1/T rate for last predictor?? High probability bounds (not trivial!)
Large-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 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 informationSupport Vector Machines: Training with Stochastic Gradient Descent
Support Vector Machines: Training with Stochastic Gradient Descent Machine Learning Spring 2018 The slides are mainly from Vivek Srikumar 1 Support vector machines Training by maximizing margin The SVM
More information1 Overview. 2 The Gradient Descent Algorithm. AM 221: Advanced Optimization Spring 2016
AM 22: Advanced Optimization Spring 206 Prof. Yaron Singer Lecture 9 February 24th Overview In the previous lecture we reviewed results from multivariate calculus in preparation for our journey into convex
More informationMachine Learning (CSE 446): Pratical issues: optimization and learning
Machine Learning (CSE 446): Pratical issues: optimization and learning John Thickstun guest lecture c 2018 University of Washington cse446-staff@cs.washington.edu 1 / 10 Review 1 / 10 Our running example
More informationIs Greedy Coordinate Descent a Terrible Algorithm?
Is Greedy Coordinate Descent a Terrible Algorithm? Julie Nutini, Mark Schmidt, Issam Laradji, Michael Friedlander, Hoyt Koepke University of British Columbia Optimization and Big Data, 2015 Context: Random
More informationA Robust Option Pricing Problem
IMA 2003 Workshop, March 12-19, 2003 A Robust Option Pricing Problem Laurent El Ghaoui Department of EECS, UC Berkeley 3 Robust optimization standard form: min x sup u U f 0 (x, u) : u U, f i (x, u) 0,
More informationPortfolio Management and Optimal Execution via Convex Optimization
Portfolio Management and Optimal Execution via Convex Optimization Enzo Busseti Stanford University April 9th, 2018 Problems portfolio management choose trades with optimization minimize risk, maximize
More informationAn adaptive cubic regularization algorithm for nonconvex optimization with convex constraints and its function-evaluation complexity
An adaptive cubic regularization algorithm for nonconvex optimization with convex constraints and its function-evaluation complexity Coralia Cartis, Nick Gould and Philippe Toint Department of Mathematics,
More informationSocially-Optimal Design of Crowdsourcing Platforms with Reputation Update Errors
Socially-Optimal Design of Crowdsourcing Platforms with Reputation Update Errors 1 Yuanzhang Xiao, Yu Zhang, and Mihaela van der Schaar Abstract Crowdsourcing systems (e.g. Yahoo! Answers and Amazon Mechanical
More informationLecture 5 Theory of Finance 1
Lecture 5 Theory of Finance 1 Simon Hubbert s.hubbert@bbk.ac.uk January 24, 2007 1 Introduction In the previous lecture we derived the famous Capital Asset Pricing Model (CAPM) for expected asset returns,
More informationMartingale Pricing Theory in Discrete-Time and Discrete-Space Models
IEOR E4707: Foundations of Financial Engineering c 206 by Martin Haugh Martingale Pricing Theory in Discrete-Time and Discrete-Space Models These notes develop the theory of martingale pricing in a discrete-time,
More informationDRAFT. 1 exercise in state (S, t), π(s, t) = 0 do not exercise in state (S, t) Review of the Risk Neutral Stock Dynamics
Chapter 12 American Put Option Recall that the American option has strike K and maturity T and gives the holder the right to exercise at any time in [0, T ]. The American option is not straightforward
More informationIE 495 Lecture 11. The LShaped Method. Prof. Jeff Linderoth. February 19, February 19, 2003 Stochastic Programming Lecture 11 Slide 1
IE 495 Lecture 11 The LShaped Method Prof. Jeff Linderoth February 19, 2003 February 19, 2003 Stochastic Programming Lecture 11 Slide 1 Before We Begin HW#2 $300 $0 http://www.unizh.ch/ior/pages/deutsch/mitglieder/kall/bib/ka-wal-94.pdf
More informationMachine Learning (CSE 446): Learning as Minimizing Loss
Machine Learning (CSE 446): Learning as Minimizing Loss oah Smith c 207 University of Washington nasmith@cs.washington.edu October 23, 207 / 2 Sorry! o office hour for me today. Wednesday is as usual.
More informationBirkbeck MSc/Phd Economics. Advanced Macroeconomics, Spring Lecture 2: The Consumption CAPM and the Equity Premium Puzzle
Birkbeck MSc/Phd Economics Advanced Macroeconomics, Spring 2006 Lecture 2: The Consumption CAPM and the Equity Premium Puzzle 1 Overview This lecture derives the consumption-based capital asset pricing
More informationStability in geometric & functional inequalities
Stability in geometric & functional inequalities A. Figalli The University of Texas at Austin www.ma.utexas.edu/users/figalli/ Alessio Figalli (UT Austin) Stability in geom. & funct. ineq. Krakow, July
More informationOn Existence of Equilibria. Bayesian Allocation-Mechanisms
On Existence of Equilibria in Bayesian Allocation Mechanisms Northwestern University April 23, 2014 Bayesian Allocation Mechanisms In allocation mechanisms, agents choose messages. The messages determine
More informationOnline Appendix Optimal Time-Consistent Government Debt Maturity D. Debortoli, R. Nunes, P. Yared. A. Proofs
Online Appendi Optimal Time-Consistent Government Debt Maturity D. Debortoli, R. Nunes, P. Yared A. Proofs Proof of Proposition 1 The necessity of these conditions is proved in the tet. To prove sufficiency,
More informationCSCI 1951-G Optimization Methods in Finance Part 00: Course Logistics Introduction to Finance Optimization Problems
CSCI 1951-G Optimization Methods in Finance Part 00: Course Logistics Introduction to Finance Optimization Problems January 26, 2018 1 / 24 Basic information All information is available in the syllabus
More informationEllipsoid Method. ellipsoid method. convergence proof. inequality constraints. feasibility problems. Prof. S. Boyd, EE392o, Stanford University
Ellipsoid Method ellipsoid method convergence proof inequality constraints feasibility problems Prof. S. Boyd, EE392o, Stanford University Challenges in cutting-plane methods can be difficult to compute
More information4 Reinforcement Learning Basic Algorithms
Learning in Complex Systems Spring 2011 Lecture Notes Nahum Shimkin 4 Reinforcement Learning Basic Algorithms 4.1 Introduction RL methods essentially deal with the solution of (optimal) control problems
More informationEllipsoid Method. ellipsoid method. convergence proof. inequality constraints. feasibility problems. Prof. S. Boyd, EE364b, Stanford University
Ellipsoid Method ellipsoid method convergence proof inequality constraints feasibility problems Prof. S. Boyd, EE364b, Stanford University Ellipsoid method developed by Shor, Nemirovsky, Yudin in 1970s
More informationScenario Generation and Sampling Methods
Scenario Generation and Sampling Methods Güzin Bayraksan Tito Homem-de-Mello SVAN 2016 IMPA May 9th, 2016 Bayraksan (OSU) & Homem-de-Mello (UAI) Scenario Generation and Sampling SVAN IMPA May 9 1 / 30
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 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 informationOutline. 1 Introduction. 2 Algorithms. 3 Examples. Algorithm 1 General coordinate minimization framework. 1: Choose x 0 R n and set k 0.
Outline Coordinate Minimization Daniel P. Robinson Department of Applied Mathematics and Statistics Johns Hopkins University November 27, 208 Introduction 2 Algorithms Cyclic order with exact minimization
More informationA Stochastic Approximation Algorithm for Making Pricing Decisions in Network Revenue Management Problems
A Stochastic Approximation Algorithm for Making ricing Decisions in Network Revenue Management roblems Sumit Kunnumkal Indian School of Business, Gachibowli, Hyderabad, 500032, India sumit kunnumkal@isb.edu
More informationLecture IV Portfolio management: Efficient portfolios. Introduction to Finance Mathematics Fall Financial mathematics
Lecture IV Portfolio management: Efficient portfolios. Introduction to Finance Mathematics Fall 2014 Reduce the risk, one asset Let us warm up by doing an exercise. We consider an investment with σ 1 =
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 informationELEMENTS OF MONTE CARLO SIMULATION
APPENDIX B ELEMENTS OF MONTE CARLO SIMULATION B. GENERAL CONCEPT The basic idea of Monte Carlo simulation is to create a series of experimental samples using a random number sequence. According to the
More informationRegret Minimization and Correlated Equilibria
Algorithmic Game heory Summer 2017, Week 4 EH Zürich Overview Regret Minimization and Correlated Equilibria Paolo Penna We have seen different type of equilibria and also considered the corresponding price
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 informationPart 3: Trust-region methods for unconstrained optimization. Nick Gould (RAL)
Part 3: Trust-region methods for unconstrained optimization Nick Gould (RAL) minimize x IR n f(x) MSc course on nonlinear optimization UNCONSTRAINED MINIMIZATION minimize x IR n f(x) where the objective
More informationConvergence of trust-region methods based on probabilistic models
Convergence of trust-region methods based on probabilistic models A. S. Bandeira K. Scheinberg L. N. Vicente October 24, 2013 Abstract In this paper we consider the use of probabilistic or random models
More informationImportance Sampling for Fair Policy Selection
Importance Sampling for Fair Policy Selection Shayan Doroudi Carnegie Mellon University Pittsburgh, PA 15213 shayand@cs.cmu.edu Philip S. Thomas Carnegie Mellon University Pittsburgh, PA 15213 philipt@cs.cmu.edu
More informationStrategies for Improving the Efficiency of Monte-Carlo Methods
Strategies for Improving the Efficiency of Monte-Carlo Methods Paul J. Atzberger General comments or corrections should be sent to: paulatz@cims.nyu.edu Introduction The Monte-Carlo method is a useful
More informationFast Convergence of Regress-later Series Estimators
Fast Convergence of Regress-later Series Estimators New Thinking in Finance, London Eric Beutner, Antoon Pelsser, Janina Schweizer Maastricht University & Kleynen Consultants 12 February 2014 Beutner Pelsser
More information6. Martingales. = Zn. Think of Z n+1 as being a gambler s earnings after n+1 games. If the game if fair, then E [ Z n+1 Z n
6. Martingales For casino gamblers, a martingale is a betting strategy where (at even odds) the stake doubled each time the player loses. Players follow this strategy because, since they will eventually
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 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 informationLast Time. Martingale inequalities Martingale convergence theorem Uniformly integrable martingales. Today s lecture: Sections 4.4.1, 5.
MATH136/STAT219 Lecture 21, November 12, 2008 p. 1/11 Last Time Martingale inequalities Martingale convergence theorem Uniformly integrable martingales Today s lecture: Sections 4.4.1, 5.3 MATH136/STAT219
More informationConvergence Analysis of Monte Carlo Calibration of Financial Market Models
Analysis of Monte Carlo Calibration of Financial Market Models Christoph Käbe Universität Trier Workshop on PDE Constrained Optimization of Certain and Uncertain Processes June 03, 2009 Monte Carlo Calibration
More informationAxioma Research Paper No January, Multi-Portfolio Optimization and Fairness in Allocation of Trades
Axioma Research Paper No. 013 January, 2009 Multi-Portfolio Optimization and Fairness in Allocation of Trades When trades from separately managed accounts are pooled for execution, the realized market-impact
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 informationSo we turn now to many-to-one matching with money, which is generally seen as a model of firms hiring workers
Econ 805 Advanced Micro Theory I Dan Quint Fall 2009 Lecture 20 November 13 2008 So far, we ve considered matching markets in settings where there is no money you can t necessarily pay someone to marry
More informationGLOBAL CONVERGENCE OF GENERAL DERIVATIVE-FREE TRUST-REGION ALGORITHMS TO FIRST AND SECOND ORDER CRITICAL POINTS
GLOBAL CONVERGENCE OF GENERAL DERIVATIVE-FREE TRUST-REGION ALGORITHMS TO FIRST AND SECOND ORDER CRITICAL POINTS ANDREW R. CONN, KATYA SCHEINBERG, AND LUíS N. VICENTE Abstract. In this paper we prove global
More informationIEOR E4004: Introduction to OR: Deterministic Models
IEOR E4004: Introduction to OR: Deterministic Models 1 Dynamic Programming Following is a summary of the problems we discussed in class. (We do not include the discussion on the container problem or the
More informationProbability and Stochastics for finance-ii Prof. Joydeep Dutta Department of Humanities and Social Sciences Indian Institute of Technology, Kanpur
Probability and Stochastics for finance-ii Prof. Joydeep Dutta Department of Humanities and Social Sciences Indian Institute of Technology, Kanpur Lecture - 07 Mean-Variance Portfolio Optimization (Part-II)
More informationQuantitative Risk Management
Quantitative Risk Management Asset Allocation and Risk Management Martin B. Haugh Department of Industrial Engineering and Operations Research Columbia University Outline Review of Mean-Variance Analysis
More informationEco504 Spring 2010 C. Sims FINAL EXAM. β t 1 2 φτ2 t subject to (1)
Eco54 Spring 21 C. Sims FINAL EXAM There are three questions that will be equally weighted in grading. Since you may find some questions take longer to answer than others, and partial credit will be given
More informationBuilding Infinite Processes from Regular Conditional Probability Distributions
Chapter 3 Building Infinite Processes from Regular Conditional Probability Distributions Section 3.1 introduces the notion of a probability kernel, which is a useful way of systematizing and extending
More informationDefinition 4.1. In a stochastic process T is called a stopping time if you can tell when it happens.
102 OPTIMAL STOPPING TIME 4. Optimal Stopping Time 4.1. Definitions. On the first day I explained the basic problem using one example in the book. On the second day I explained how the solution to the
More informationFinancial Mathematics III Theory summary
Financial Mathematics III Theory summary Table of Contents Lecture 1... 7 1. State the objective of modern portfolio theory... 7 2. Define the return of an asset... 7 3. How is expected return defined?...
More information4: SINGLE-PERIOD MARKET MODELS
4: SINGLE-PERIOD MARKET MODELS Marek Rutkowski School of Mathematics and Statistics University of Sydney Semester 2, 2016 M. Rutkowski (USydney) Slides 4: Single-Period Market Models 1 / 87 General Single-Period
More informationEquity correlations implied by index options: estimation and model uncertainty analysis
1/18 : estimation and model analysis, EDHEC Business School (joint work with Rama COT) Modeling and managing financial risks Paris, 10 13 January 2011 2/18 Outline 1 2 of multi-asset models Solution to
More informationTugkan Batu and Pongphat Taptagaporn Competitive portfolio selection using stochastic predictions
Tugkan Batu and Pongphat Taptagaporn Competitive portfolio selection using stochastic predictions Book section Original citation: Originally published in Batu, Tugkan and Taptagaporn, Pongphat (216) Competitive
More informationLecture 2: Making Good Sequences of Decisions Given a Model of World. CS234: RL Emma Brunskill Winter 2018
Lecture 2: Making Good Sequences of Decisions Given a Model of World CS234: RL Emma Brunskill Winter 218 Human in the loop exoskeleton work from Steve Collins lab Class Structure Last Time: Introduction
More informationChapter 8. Markowitz Portfolio Theory. 8.1 Expected Returns and Covariance
Chapter 8 Markowitz Portfolio Theory 8.1 Expected Returns and Covariance The main question in portfolio theory is the following: Given an initial capital V (0), and opportunities (buy or sell) in N securities
More informationAggregation with a double non-convex labor supply decision: indivisible private- and public-sector hours
Ekonomia nr 47/2016 123 Ekonomia. Rynek, gospodarka, społeczeństwo 47(2016), s. 123 133 DOI: 10.17451/eko/47/2016/233 ISSN: 0137-3056 www.ekonomia.wne.uw.edu.pl Aggregation with a double non-convex labor
More informationApproximate Composite Minimization: Convergence Rates and Examples
ISMP 2018 - Bordeaux Approximate Composite Minimization: Convergence Rates and S. Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi MLO Lab, EPFL, Switzerland sebastian.stich@epfl.ch July 4, 2018
More informationOption pricing in the stochastic volatility model of Barndorff-Nielsen and Shephard
Option pricing in the stochastic volatility model of Barndorff-Nielsen and Shephard Indifference pricing and the minimal entropy martingale measure Fred Espen Benth Centre of Mathematics for Applications
More informationMonte Carlo Methods in Structuring and Derivatives Pricing
Monte Carlo Methods in Structuring and Derivatives Pricing Prof. Manuela Pedio (guest) 20263 Advanced Tools for Risk Management and Pricing Spring 2017 Outline and objectives The basic Monte Carlo algorithm
More informationChapter 6. Importance sampling. 6.1 The basics
Chapter 6 Importance sampling 6.1 The basics To movtivate our discussion consider the following situation. We want to use Monte Carlo to compute µ E[X]. There is an event E such that P(E) is small but
More informationIEOR E4602: Quantitative Risk Management
IEOR E4602: Quantitative Risk Management Risk Measures Martin Haugh Department of Industrial Engineering and Operations Research Columbia University Email: martin.b.haugh@gmail.com Reference: Chapter 8
More informationOptimal robust bounds for variance options and asymptotically extreme models
Optimal robust bounds for variance options and asymptotically extreme models Alexander Cox 1 Jiajie Wang 2 1 University of Bath 2 Università di Roma La Sapienza Advances in Financial Mathematics, 9th January,
More informationk-layer neural networks: High capacity scoring functions + tips on how to train them
k-layer neural networks: High capacity scoring functions + tips on how to train them A new class of scoring functions Linear scoring function s = W x + b 2-layer Neural Network s 1 = W 1 x + b 1 h = max(0,
More informationGeneral Equilibrium under Uncertainty
General Equilibrium under Uncertainty The Arrow-Debreu Model General Idea: this model is formally identical to the GE model commodities are interpreted as contingent commodities (commodities are contingent
More informationTTIC An Introduction to the Theory of Machine Learning. The Adversarial Multi-armed Bandit Problem Avrim Blum.
TTIC 31250 An Introduction to the Theory of Machine Learning The Adversarial Multi-armed Bandit Problem Avrim Blum Start with recap 1 Algorithm Consider the following setting Each morning, you need to
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 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 informationThe Limiting Distribution for the Number of Symbol Comparisons Used by QuickSort is Nondegenerate (Extended Abstract)
The Limiting Distribution for the Number of Symbol Comparisons Used by QuickSort is Nondegenerate (Extended Abstract) Patrick Bindjeme 1 James Allen Fill 1 1 Department of Applied Mathematics Statistics,
More informationRevenue optimization in AdExchange against strategic advertisers
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 informationModes of Convergence
Moes of Convergence Electrical Engineering 126 (UC Berkeley Spring 2018 There is only one sense in which a sequence of real numbers (a n n N is sai to converge to a limit. Namely, a n a if for every ε
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 informationIn Discrete Time a Local Martingale is a Martingale under an Equivalent Probability Measure
In Discrete Time a Local Martingale is a Martingale under an Equivalent Probability Measure Yuri Kabanov 1,2 1 Laboratoire de Mathématiques, Université de Franche-Comté, 16 Route de Gray, 253 Besançon,
More informationOptimization Problem In Single Period Markets
University of Central Florida Electronic Theses and Dissertations Masters Thesis (Open Access) Optimization Problem In Single Period Markets 2013 Tian Jiang University of Central Florida Find similar works
More informationThe ruin probabilities of a multidimensional perturbed risk model
MATHEMATICAL COMMUNICATIONS 231 Math. Commun. 18(2013, 231 239 The ruin probabilities of a multidimensional perturbed risk model Tatjana Slijepčević-Manger 1, 1 Faculty of Civil Engineering, University
More informationHints on Some of the Exercises
Hints on Some of the Exercises of the book R. Seydel: Tools for Computational Finance. Springer, 00/004/006/009/01. Preparatory Remarks: Some of the hints suggest ideas that may simplify solving the exercises
More informationFinancial Giffen Goods: Examples and Counterexamples
Financial Giffen Goods: Examples and Counterexamples RolfPoulsen and Kourosh Marjani Rasmussen Abstract In the basic Markowitz and Merton models, a stock s weight in efficient portfolios goes up if its
More informationImperfect Information and Market Segmentation Walsh Chapter 5
Imperfect Information and Market Segmentation Walsh Chapter 5 1 Why Does Money Have Real Effects? Add market imperfections to eliminate short-run neutrality of money Imperfect information keeps price from
More informationGeneralising the weak compactness of ω
Generalising the weak compactness of ω Andrew Brooke-Taylor Generalised Baire Spaces Masterclass Royal Netherlands Academy of Arts and Sciences 22 August 2018 Andrew Brooke-Taylor Generalising the weak
More informationEconomics 826 International Finance. Final Exam: April 2007
Economics 826 International Finance Final Exam: April 2007 Answer 3 questions from Part A and 4 questions from Part B. Part A is worth 60%. Part B is worth 40%. You may write in english or french. You
More informationHigh Dimensional Edgeworth Expansion. Applications to Bootstrap and Its Variants
With Applications to Bootstrap and Its Variants Department of Statistics, UC Berkeley Stanford-Berkeley Colloquium, 2016 Francis Ysidro Edgeworth (1845-1926) Peter Gavin Hall (1951-2016) Table of Contents
More informationDisaster risk and its implications for asset pricing Online appendix
Disaster risk and its implications for asset pricing Online appendix Jerry Tsai University of Oxford Jessica A. Wachter University of Pennsylvania December 12, 2014 and NBER A The iid model This section
More informationFinancial Optimization ISE 347/447. Lecture 15. Dr. Ted Ralphs
Financial Optimization ISE 347/447 Lecture 15 Dr. Ted Ralphs ISE 347/447 Lecture 15 1 Reading for This Lecture C&T Chapter 12 ISE 347/447 Lecture 15 2 Stock Market Indices A stock market index is a statistic
More informationIEOR E4703: Monte-Carlo Simulation
IEOR E4703: Monte-Carlo Simulation Other Miscellaneous Topics and Applications of Monte-Carlo Martin Haugh Department of Industrial Engineering and Operations Research Columbia University Email: martin.b.haugh@gmail.com
More information9.1 Principal Component Analysis for Portfolios
Chapter 9 Alpha Trading By the name of the strategies, an alpha trading strategy is to select and trade portfolios so the alpha is maximized. Two important mathematical objects are factor analysis and
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 informationLecture 5: Iterative Combinatorial Auctions
COMS 6998-3: Algorithmic Game Theory October 6, 2008 Lecture 5: Iterative Combinatorial Auctions Lecturer: Sébastien Lahaie Scribe: Sébastien Lahaie In this lecture we examine a procedure that generalizes
More informationLecture 19: March 20
CS71 Randomness & Computation Spring 018 Instructor: Alistair Sinclair Lecture 19: March 0 Disclaimer: These notes have not been subjected to the usual scrutiny accorded to formal publications. They may
More informationarxiv: v1 [math.pr] 6 Apr 2015
Analysis of the Optimal Resource Allocation for a Tandem Queueing System arxiv:1504.01248v1 [math.pr] 6 Apr 2015 Liu Zaiming, Chen Gang, Wu Jinbiao School of Mathematics and Statistics, Central South University,
More informationOptimal energy management and stochastic decomposition
Optimal energy management and stochastic decomposition F. Pacaud P. Carpentier J.P. Chancelier M. De Lara JuMP-dev workshop, 2018 ENPC ParisTech ENSTA ParisTech Efficacity 1/23 Motivation We consider a
More informationPortfolio Optimization. Prof. Daniel P. Palomar
Portfolio Optimization Prof. Daniel P. Palomar The Hong Kong University of Science and Technology (HKUST) MAFS6010R- Portfolio Optimization with R MSc in Financial Mathematics Fall 2018-19, HKUST, Hong
More informationarxiv: v1 [math.oc] 23 Dec 2010
ASYMPTOTIC PROPERTIES OF OPTIMAL TRAJECTORIES IN DYNAMIC PROGRAMMING SYLVAIN SORIN, XAVIER VENEL, GUILLAUME VIGERAL Abstract. We show in a dynamic programming framework that uniform convergence of the
More informationSTOCHASTIC REPUTATION DYNAMICS UNDER DUOPOLY COMPETITION
STOCHASTIC REPUTATION DYNAMICS UNDER DUOPOLY COMPETITION BINGCHAO HUANGFU Abstract This paper studies a dynamic duopoly model of reputation-building in which reputations are treated as capital stocks that
More informationProblem Set 3. Thomas Philippon. April 19, Human Wealth, Financial Wealth and Consumption
Problem Set 3 Thomas Philippon April 19, 2002 1 Human Wealth, Financial Wealth and Consumption The goal of the question is to derive the formulas on p13 of Topic 2. This is a partial equilibrium analysis
More informationComparing Allocations under Asymmetric Information: Coase Theorem Revisited
Comparing Allocations under Asymmetric Information: Coase Theorem Revisited Shingo Ishiguro Graduate School of Economics, Osaka University 1-7 Machikaneyama, Toyonaka, Osaka 560-0043, Japan August 2002
More informationStochastic Integral Representation of One Stochastically Non-smooth Wiener Functional
Bulletin of TICMI Vol. 2, No. 2, 26, 24 36 Stochastic Integral Representation of One Stochastically Non-smooth Wiener Functional Hanna Livinska a and Omar Purtukhia b a Taras Shevchenko National University
More informationDecomposition Methods
Decomposition Methods separable problems, complicating variables primal decomposition dual decomposition complicating constraints general decomposition structures Prof. S. Boyd, EE364b, Stanford University
More information