Importance sampling in scenario generation

Size: px
Start display at page:

Download "Importance sampling in scenario generation"

Transcription

1 Importance sampling in scenario generation Václav Kozmík Faculty of Mathematics and Physics Charles University in Prague September 14, 2013

2 Introduction Monte Carlo techniques have received significant attention in past years One of the reasons is so called curse of dimensionality Consider numerical integration scheme (Simpson s rule, trapezoidal rule,... ) The number of function evaluations grows exponentially as the dimension of the integral grows Monte Carlo solution Consider the integral as expectation of the random variable Sample scenarios from the distribution specified by the integrated function The error in such integration does not depend on the dimension, just on the number of scenarios used

3 Scenarios Scenarios are exploited in many areas: numerical integration stochastic optimization statistics tracking models robust optimization scenario analysis artificial intelligence Standard method of generating scenarios is Monte Carlo There are many extensions and variants: Importance sampling Quasi Monte Carlo Stratified sampling

4 Sample Average Approximation We will consider following stochastic programing problem: min {f (x) := E [F (x, ξ)]} x X X R n, nonempty ξ random vector with distribution P supported on Ξ R d F : X Ξ R, finite for every x X and ξ Ξ optimal solution can be rarely calculated precisely approximations are used to find optimal solution Sample Average Approximation (SAA) we have to estimate sample size, test the quality of candidate solution statistical analysis of optimality gap

5 Sample Average Approximation N realizations of ξ, sample ξ 1,..., ξ N historical data Monte Carlo simulations we estimate the expected value by averaging over the sample: min x X ˆf N (x) := 1 N F (x, ξ j ) N ˆfN (x) converges pointwise w.p. 1 to f (x) by LLN under mild conditions the convergence is uniform X compact F (x, ξ) continuous in x integrable dominant g(ξ) to F (x, ξ), x X

6 Convergence denote ˆϑ N the optimal value of the SAA problem and ϑ optimal value of the original problem denote ŜN the set of optimal solutions of the SAA problem and S the true set of optimal solutions Lemma If pointwise LLN holds then lim sup N ˆϑ N ϑ. Theorem Suppose that ˆf N (x) converges to f (x) a.s., as N, uniformly on X. Then ˆϑ N converges to ϑ a.s. as N. Note When S = {x } and mild conditions hold, then for x N Ŝ N : x N x a.s..

7 Example - CVaR Suppose we want to minimize some risk functional instead of just expectation For example CVaR is a coherent risk measure and can be computed by: ( CVaR α [Z] = min u + 1 ) u R α E [Z u] +, where [ ] + max{, 0}, The resulting optimization problem follows: min x X,u R { u + 1 α E [F (x, ξ) u] + }

8 Example - CVaR Suppose we solve this problem using SAA with Monte Carlo sampling We generate a sample of size N, scenarios ξ 1,..., ξ N The optimal u is the (1 α)-quantile of the distribution of ξ 1,..., ξ N The discrete SAA problem takes form min x X,u R u N [ F (x, ξ j ) u ] α N + If α = 0.05 only about 5% of the samples contribute nonzero values to this estimator of CVaR.

9 Importance sampling Aims to solve the issues mentioned in previous example Suppose we want to compute E [F (x, ξ)] with respect to the pdf g(ξ) of the random variable ξ Therefore: E g [F (x, ξ)] = F (x, ξ)g(ξ)dξ Choose another pdf h(ξ) of some random variable and compute: F (x, ξ)g(ξ)dξ = F (x, ξ) g(ξ) h(ξ) h(ξ)dξ = E h [ F (x, ξ) g(ξ) h(ξ) ] Therefore [ E g [F (x, ξ)] = E h F (x, ξ) g(ξ) ] h(ξ)

10 Example We want to calculate I = 1 0 f (x)dx. Let X be a random variable with density f (x) on [0, 1] and 0 otherwise. Standard Monte Carlo estimator forms i.i.d. samples X 1,..., X N and computes: Î = 1 N N X j With importance sampling we draw R 1,..., R N from uniform distribution on [0, 1] and compute I = 1 N N f (R j )

11 Example When is var [I ] var [Î ] var [Î ]? = I (1 I ) ( N 1 var [I ] = 1 N 0 ] var [Î var [I ] = 1 ( I I 2 N = 1 N 1 0 ( 1 f 2 (x)dx f (x)(1 f (x))dx ) 2 ) f (x)dx f 2 (x)dx + I 2 ) Better for reasonable functions f with values in [0, 1]

12 Importance sampling How to choose function h? Evaluate variance: F (x, ξ) 2 g(ξ)2 h(ξ) 2 h(ξ)dξ = F (x, ξ) 2 g(ξ) g(ξ) h(ξ) dξ could be large for certain functions h Generally h should have heavier tails than g Bound the term g(ξ) h(ξ) < M, or bound g with compact support Optimal choice of function h is: Term g(ξ) h(ξ) h (ξ) = F (x, ξ) g(ξ) F (x, ξ) g(ξ)dξ However, this is of no use, since in requires to compute the integral which we are trying to compute

13 Importance sampling In the context of Monte Carlo E g [F (x, ξ)] is replaced with: Sample ξ 1,..., ξ N from distribution with pdf f Compute 1 N F (x, ξ j ) N The importance sampling scheme is as follows: Sample ξ 1,..., ξ N from distribution with pdf h Compute 1 N F (x, ξ j ) g(ξ j ) N h(ξ j ) Function h should be chosen such that the variance of the sum above is minimal

14 Further variance reduction The term w(ξ j ) = g(ξ j ) h(ξ j ) 1 N could be considered as a weight: N F (x, ξ j )w(ξ j ) In expectation, we have E [ w(ξ j ) ] = 1, but the term itself is random and has nonzero [ variance N ] Replace the N = E w(ξ j ) with the actual value: 1 N w(ξ j ) N F (x, ξ j )w(ξ j )

15 Further variance reduction We no longer have the expectation equality: E h 1 N N F (x, ξ j )w(ξ j ) E g 1 w(ξ j ) N N F (x, ξ j ) But we can show consistency: E h 1 N N F (x, ξ j )w(ξ j ) E g [F (x, ξ)], w.p. 1, w(ξ j ) as N. The benefit is usually significant variance reduction over the standard importance sampling scheme

16 Example Consider following mean risk functional with random losses Z: f (Z) = (1 λ) E [Z] + λ CVaR α [Z] λ models our risk aversion Set α to the standard value of 0.05 Suppose Z N (0, 1) What is the best importance sampling scheme? The functional clearly depends on all outcomes of Z However, to compute CVaR, only part of the outcomes is used We can divide the support of the distribution into two atoms: CVaR atom non-cvar atom We expect that the ideal choice depends on both λ and α

17 Example Consider following importance sampling density, which redistributes the weights between the atoms: h(x) = { βt α t φ(x), if x u h 1 β t 1 α t φ(x), if x < u h, where u h is the (1 α)-quantile of normal distribution This leads to the weights of w(x) = φ(x) h(x) How to choose the parameter β? { αt β t, 1 α t if x u h 1 β t, if x < u h.

18 Example 80 Variance as a function of beta Variance ,01 0,05 0,09 0,13 0,17 0,21 0,25 0,29 0,33 0,37 0,41 0,45 0,49 0,53 0,57 0,61 0,65 0,69 0,73 0,77 0,81 0,85 0,89 0,93 0,97 Beta

19 Example 0,35 Optimal beta for given lamda Beta 0,3 0,25 0,2 0,15 0,1 0,05 0 0,01 0,04 0,07 0,1 0,13 0,16 0,19 0,22 0,25 0,28 0,31 0,34 0,37 0,4 0,43 0,46 0,49 0,52 0,55 0,58 0,61 0,64 0,67 0,7 0,73 0,76 0,79 0,82 0,85 0,88 0,91 0,94 0,97 Lambda

20 References Antoch, J.: Simulační metody a statistika, Přednáška na MFF UK Bayraksan, G., Morton, D. (2009): Assessing Solution Quality in Stochastic Programs via Sampling, Tutorials in Operations Research, Informs, pp , ISBN Hesterberg, T. C. (1995): Weighted average importance sampling and defensive mixture distributions, Technometrics 37, pp Shapiro, A., Dentcheva, D., Ruszczynski A. (2009): Lectures on Stochastic Programming: Modeling and Theory, SIAM-Society for Industrial and Applied Mathematics, ISBN

21 Conclusion Thank you for your attention! Václav Kozmík

Asymptotics of minimax stochastic programs

Asymptotics of minimax stochastic programs Asymptotics of minimax stochastic programs Alexander Shapiro Abstract. We discuss in this paper asymptotics of the sample average approximation (SAA) of the optimal value of a minimax stochastic programming

More information

Scenario Generation and Sampling Methods

Scenario Generation and Sampling Methods Scenario Generation and Sampling Methods Tito Homem-de-Mello Güzin Bayraksan SVAN 2016 IMPA 9 13 May 2106 Let s Start with a Recap Sample Average Approximation We want to solve the true problem min {g(x)

More information

Complexity of two and multi-stage stochastic programming problems

Complexity of two and multi-stage stochastic programming problems Complexity of two and multi-stage stochastic programming problems A. Shapiro School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332-0205, USA The concept

More information

Optimization Tools in an Uncertain Environment

Optimization Tools in an Uncertain Environment Optimization Tools in an Uncertain Environment Michael C. Ferris University of Wisconsin, Madison Uncertainty Workshop, Chicago: July 21, 2008 Michael Ferris (University of Wisconsin) Stochastic optimization

More information

Reformulation of chance constrained problems using penalty functions

Reformulation of chance constrained problems using penalty functions Reformulation of chance constrained problems using penalty functions Martin Branda Charles University in Prague Faculty of Mathematics and Physics EURO XXIV July 11-14, 2010, Lisbon Martin Branda (MFF

More information

CVaR and Examples of Deviation Risk Measures

CVaR and Examples of Deviation Risk Measures CVaR and Examples of Deviation Risk Measures Jakub Černý Department of Probability and Mathematical Statistics Stochastic Modelling in Economics and Finance November 10, 2014 1 / 25 Contents CVaR - Dual

More information

Stochastic Optimization One-stage problem

Stochastic Optimization One-stage problem Stochastic Optimization One-stage problem V. Leclère September 28 2017 September 28 2017 1 / Déroulement du cours 1 Problèmes d optimisation stochastique à une étape 2 Problèmes d optimisation stochastique

More information

Sample Average Approximation (SAA) for Stochastic Programs

Sample Average Approximation (SAA) for Stochastic Programs Sample Average Approximation (SAA) for Stochastic Programs with an eye towards computational SAA Dave Morton Industrial Engineering & Management Sciences Northwestern University Outline SAA Results for

More information

A. Shapiro Introduction

A. Shapiro Introduction ESAIM: PROCEEDINGS, December 2003, Vol. 13, 65 73 J.P. Penot, Editor DOI: 10.1051/proc:2003003 MONTE CARLO SAMPLING APPROACH TO STOCHASTIC PROGRAMMING A. Shapiro 1 Abstract. Various stochastic programming

More information

arxiv: v3 [math.oc] 25 Apr 2018

arxiv: v3 [math.oc] 25 Apr 2018 Problem-driven scenario generation: an analytical approach for stochastic programs with tail risk measure Jamie Fairbrother *, Amanda Turner *, and Stein W. Wallace ** * STOR-i Centre for Doctoral Training,

More information

Motivation General concept of CVaR Optimization Comparison. VaR and CVaR. Přemysl Bejda.

Motivation General concept of CVaR Optimization Comparison. VaR and CVaR. Přemysl Bejda. VaR and CVaR Přemysl Bejda premyslbejda@gmail.com 2014 Contents 1 Motivation 2 General concept of CVaR 3 Optimization 4 Comparison Contents 1 Motivation 2 General concept of CVaR 3 Optimization 4 Comparison

More information

Portfolio optimization with stochastic dominance constraints

Portfolio optimization with stochastic dominance constraints Charles University in Prague Faculty of Mathematics and Physics Portfolio optimization with stochastic dominance constraints December 16, 2014 Contents Motivation 1 Motivation 2 3 4 5 Contents Motivation

More information

Stability of optimization problems with stochastic dominance constraints

Stability of optimization problems with stochastic dominance constraints Stability of optimization problems with stochastic dominance constraints D. Dentcheva and W. Römisch Stevens Institute of Technology, Hoboken Humboldt-University Berlin www.math.hu-berlin.de/~romisch SIAM

More information

Upper bound for optimal value of risk averse multistage problems

Upper bound for optimal value of risk averse multistage problems Upper bound for optimal value of risk averse multistage problems Lingquan Ding School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332-0205 Alexander Shapiro School

More information

Online Companion: Risk-Averse Approximate Dynamic Programming with Quantile-Based Risk Measures

Online Companion: Risk-Averse Approximate Dynamic Programming with Quantile-Based Risk Measures Online Companion: Risk-Averse Approximate Dynamic Programming with Quantile-Based Risk Measures Daniel R. Jiang and Warren B. Powell Abstract In this online companion, we provide some additional preliminary

More information

Brief introduction to Markov Chain Monte Carlo

Brief introduction to Markov Chain Monte Carlo Brief introduction to Department of Probability and Mathematical Statistics seminar Stochastic modeling in economics and finance November 7, 2011 Brief introduction to Content 1 and motivation Classical

More information

is a Borel subset of S Θ for each c R (Bertsekas and Shreve, 1978, Proposition 7.36) This always holds in practical applications.

is a Borel subset of S Θ for each c R (Bertsekas and Shreve, 1978, Proposition 7.36) This always holds in practical applications. Stat 811 Lecture Notes The Wald Consistency Theorem Charles J. Geyer April 9, 01 1 Analyticity Assumptions Let { f θ : θ Θ } be a family of subprobability densities 1 with respect to a measure µ on a measurable

More information

Introduction to Algorithmic Trading Strategies Lecture 10

Introduction to Algorithmic Trading Strategies Lecture 10 Introduction to Algorithmic Trading Strategies Lecture 10 Risk Management Haksun Li haksun.li@numericalmethod.com www.numericalmethod.com Outline Value at Risk (VaR) Extreme Value Theory (EVT) References

More information

Bootstrap metody II Kernelové Odhady Hustot

Bootstrap metody II Kernelové Odhady Hustot Bootstrap metody II Kernelové Odhady Hustot Mgr. Rudolf B. Blažek, Ph.D. prof. RNDr. Roman Kotecký, DrSc. Katedra počítačových systémů Katedra teoretické informatiky Fakulta informačních technologií České

More information

Monte Carlo Methods for Stochastic Programming

Monte Carlo Methods for Stochastic Programming IE 495 Lecture 16 Monte Carlo Methods for Stochastic Programming Prof. Jeff Linderoth March 17, 2003 March 17, 2003 Stochastic Programming Lecture 16 Slide 1 Outline Review Jensen's Inequality Edmundson-Madansky

More information

Stochastic Programming Approach to Optimization under Uncertainty

Stochastic Programming Approach to Optimization under Uncertainty Mathematical Programming manuscript No. (will be inserted by the editor) Alexander Shapiro Stochastic Programming Approach to Optimization under Uncertainty Received: date / Accepted: date Abstract In

More information

CSCI-6971 Lecture Notes: Monte Carlo integration

CSCI-6971 Lecture Notes: Monte Carlo integration CSCI-6971 Lecture otes: Monte Carlo integration Kristopher R. Beevers Department of Computer Science Rensselaer Polytechnic Institute beevek@cs.rpi.edu February 21, 2006 1 Overview Consider the following

More information

Simulations. . p.1/25

Simulations. . p.1/25 Simulations Computer simulations of realizations of random variables has become indispensable as supplement to theoretical investigations and practical applications.. p.1/25 Simulations Computer simulations

More information

IEOR E4703: Monte-Carlo Simulation

IEOR E4703: Monte-Carlo Simulation IEOR E4703: Monte-Carlo Simulation Output Analysis for Monte-Carlo Martin Haugh Department of Industrial Engineering and Operations Research Columbia University Email: martin.b.haugh@gmail.com Output Analysis

More information

Introduction to Rare Event Simulation

Introduction to Rare Event Simulation Introduction to Rare Event Simulation Brown University: Summer School on Rare Event Simulation Jose Blanchet Columbia University. Department of Statistics, Department of IEOR. Blanchet (Columbia) 1 / 31

More information

GENERALIZED second-order cone complementarity

GENERALIZED second-order cone complementarity Stochastic Generalized Complementarity Problems in Second-Order Cone: Box-Constrained Minimization Reformulation and Solving Methods Mei-Ju Luo and Yan Zhang Abstract In this paper, we reformulate the

More information

Tutorial on Approximate Bayesian Computation

Tutorial on Approximate Bayesian Computation Tutorial on Approximate Bayesian Computation Michael Gutmann https://sites.google.com/site/michaelgutmann University of Helsinki Aalto University Helsinki Institute for Information Technology 16 May 2016

More information

Risk neutral and risk averse approaches to multistage stochastic programming.

Risk neutral and risk averse approaches to multistage stochastic programming. Risk neutral and risk averse approaches to multistage stochastic programming. A. Shapiro School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332-0205, USA

More information

Distributionally robust simple integer recourse

Distributionally robust simple integer recourse Distributionally robust simple integer recourse Weijun Xie 1 and Shabbir Ahmed 2 1 Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA 24061 2 School of Industrial & Systems

More information

On almost sure rates of convergence for sample average approximations

On almost sure rates of convergence for sample average approximations On almost sure rates of convergence for sample average approximations Dirk Banholzer 1, Jörg Fliege 1, and Ralf Werner 2 1 Department of Mathematical Sciences, University of Southampton, Southampton, SO17

More information

The properties of L p -GMM estimators

The properties of L p -GMM estimators The properties of L p -GMM estimators Robert de Jong and Chirok Han Michigan State University February 2000 Abstract This paper considers Generalized Method of Moment-type estimators for which a criterion

More information

Optimization Problems with Probabilistic Constraints

Optimization Problems with Probabilistic Constraints Optimization Problems with Probabilistic Constraints R. Henrion Weierstrass Institute Berlin 10 th International Conference on Stochastic Programming University of Arizona, Tucson Recommended Reading A.

More information

Math 576: Quantitative Risk Management

Math 576: Quantitative Risk Management Math 576: Quantitative Risk Management Haijun Li lih@math.wsu.edu Department of Mathematics Washington State University Week 11 Haijun Li Math 576: Quantitative Risk Management Week 11 1 / 21 Outline 1

More information

ARTICLE IN PRESS. European Journal of Operational Research (2018) Contents lists available at ScienceDirect

ARTICLE IN PRESS. European Journal of Operational Research (2018) Contents lists available at ScienceDirect ARTICLE I PRESS European Journal of Operational Research 0 0 0 (2018) 1 11 Contents lists available at ScienceDirect European Journal of Operational Research journal homepage: www.elsevier.com/locate/ejor

More information

Problem-driven scenario generation: an analytical approach for stochastic programs with tail risk measure

Problem-driven scenario generation: an analytical approach for stochastic programs with tail risk measure Problem-driven scenario generation: an analytical approach for stochastic programs with tail risk measure Jamie Fairbrother *, Amanda Turner *, and Stein W. Wallace ** * STOR-i Centre for Doctoral Training,

More information

Fall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A.

Fall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A. 1. Let P be a probability measure on a collection of sets A. (a) For each n N, let H n be a set in A such that H n H n+1. Show that P (H n ) monotonically converges to P ( k=1 H k) as n. (b) For each n

More information

Monte Carlo Integration I [RC] Chapter 3

Monte Carlo Integration I [RC] Chapter 3 Aula 3. Monte Carlo Integration I 0 Monte Carlo Integration I [RC] Chapter 3 Anatoli Iambartsev IME-USP Aula 3. Monte Carlo Integration I 1 There is no exact definition of the Monte Carlo methods. In the

More information

1 General problem. 2 Terminalogy. Estimation. Estimate θ. (Pick a plausible distribution from family. ) Or estimate τ = τ(θ).

1 General problem. 2 Terminalogy. Estimation. Estimate θ. (Pick a plausible distribution from family. ) Or estimate τ = τ(θ). Estimation February 3, 206 Debdeep Pati General problem Model: {P θ : θ Θ}. Observe X P θ, θ Θ unknown. Estimate θ. (Pick a plausible distribution from family. ) Or estimate τ = τ(θ). Examples: θ = (µ,

More information

Scenario Generation and Sampling Methods

Scenario Generation and Sampling Methods Scenario Generation and Sampling Methods Güzin Bayraksan Tito Homem-de-Mello SVAN 2016 IMPA May 11th, 2016 Bayraksan (OSU) & Homem-de-Mello (UAI) Scenario Generation and Sampling SVAN IMPA May 11 1 / 33

More information

Inverse Stochastic Dominance Constraints Duality and Methods

Inverse Stochastic Dominance Constraints Duality and Methods Duality and Methods Darinka Dentcheva 1 Andrzej Ruszczyński 2 1 Stevens Institute of Technology Hoboken, New Jersey, USA 2 Rutgers University Piscataway, New Jersey, USA Research supported by NSF awards

More information

Lecture 13: Subsampling vs Bootstrap. Dimitris N. Politis, Joseph P. Romano, Michael Wolf

Lecture 13: Subsampling vs Bootstrap. Dimitris N. Politis, Joseph P. Romano, Michael Wolf Lecture 13: 2011 Bootstrap ) R n x n, θ P)) = τ n ˆθn θ P) Example: ˆθn = X n, τ n = n, θ = EX = µ P) ˆθ = min X n, τ n = n, θ P) = sup{x : F x) 0} ) Define: J n P), the distribution of τ n ˆθ n θ P) under

More information

Computational Complexity of Stochastic Programming: Monte Carlo Sampling Approach

Computational Complexity of Stochastic Programming: Monte Carlo Sampling Approach Proceedings of the International Congress of Mathematicians Hyderabad, India, 2010 Computational Complexity of Stochastic Programming: Monte Carlo Sampling Approach Alexander Shapiro Abstract For a long

More information

Revisiting some results on the complexity of multistage stochastic programs and some extensions

Revisiting some results on the complexity of multistage stochastic programs and some extensions Revisiting some results on the complexity of multistage stochastic programs and some extensions M.M.C.R. Reaiche IMPA, Rio de Janeiro, RJ, Brazil October 30, 2015 Abstract In this work we present explicit

More information

Bayesian Inference for DSGE Models. Lawrence J. Christiano

Bayesian Inference for DSGE Models. Lawrence J. Christiano Bayesian Inference for DSGE Models Lawrence J. Christiano Outline State space-observer form. convenient for model estimation and many other things. Preliminaries. Probabilities. Maximum Likelihood. Bayesian

More information

Stat 451 Lecture Notes Simulating Random Variables

Stat 451 Lecture Notes Simulating Random Variables Stat 451 Lecture Notes 05 12 Simulating Random Variables Ryan Martin UIC www.math.uic.edu/~rgmartin 1 Based on Chapter 6 in Givens & Hoeting, Chapter 22 in Lange, and Chapter 2 in Robert & Casella 2 Updated:

More information

Non-parametric Inference and Resampling

Non-parametric Inference and Resampling Non-parametric Inference and Resampling Exercises by David Wozabal (Last update. Juni 010) 1 Basic Facts about Rank and Order Statistics 1.1 10 students were asked about the amount of time they spend surfing

More information

Bayesian Inference and MCMC

Bayesian Inference and MCMC Bayesian Inference and MCMC Aryan Arbabi Partly based on MCMC slides from CSC412 Fall 2018 1 / 18 Bayesian Inference - Motivation Consider we have a data set D = {x 1,..., x n }. E.g each x i can be the

More information

Aggregate Risk. MFM Practitioner Module: Quantitative Risk Management. John Dodson. February 6, Aggregate Risk. John Dodson.

Aggregate Risk. MFM Practitioner Module: Quantitative Risk Management. John Dodson. February 6, Aggregate Risk. John Dodson. MFM Practitioner Module: Quantitative Risk Management February 6, 2019 As we discussed last semester, the general goal of risk measurement is to come up with a single metric that can be used to make financial

More information

Gradient-Based Adaptive Stochastic Search for Non-Differentiable Optimization

Gradient-Based Adaptive Stochastic Search for Non-Differentiable Optimization Gradient-Based Adaptive Stochastic Search for Non-Differentiable Optimization Enlu Zhou Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign, IL 61801,

More information

Inverse Statistical Learning

Inverse Statistical Learning Inverse Statistical Learning Minimax theory, adaptation and algorithm avec (par ordre d apparition) C. Marteau, M. Chichignoud, C. Brunet and S. Souchet Dijon, le 15 janvier 2014 Inverse Statistical Learning

More information

An Adaptive Partition-based Approach for Solving Two-stage Stochastic Programs with Fixed Recourse

An Adaptive Partition-based Approach for Solving Two-stage Stochastic Programs with Fixed Recourse An Adaptive Partition-based Approach for Solving Two-stage Stochastic Programs with Fixed Recourse Yongjia Song, James Luedtke Virginia Commonwealth University, Richmond, VA, ysong3@vcu.edu University

More information

Bayesian Inference for DSGE Models. Lawrence J. Christiano

Bayesian Inference for DSGE Models. Lawrence J. Christiano Bayesian Inference for DSGE Models Lawrence J. Christiano Outline State space-observer form. convenient for model estimation and many other things. Bayesian inference Bayes rule. Monte Carlo integation.

More information

Robustness in Stochastic Programs with Risk Constraints

Robustness in Stochastic Programs with Risk Constraints Robustness in Stochastic Programs with Risk Constraints Dept. of Probability and Mathematical Statistics, Faculty of Mathematics and Physics Charles University, Prague, Czech Republic www.karlin.mff.cuni.cz/~kopa

More information

A CENTRAL LIMIT THEOREM FOR NESTED OR SLICED LATIN HYPERCUBE DESIGNS

A CENTRAL LIMIT THEOREM FOR NESTED OR SLICED LATIN HYPERCUBE DESIGNS Statistica Sinica 26 (2016), 1117-1128 doi:http://dx.doi.org/10.5705/ss.202015.0240 A CENTRAL LIMIT THEOREM FOR NESTED OR SLICED LATIN HYPERCUBE DESIGNS Xu He and Peter Z. G. Qian Chinese Academy of Sciences

More information

Central-limit approach to risk-aware Markov decision processes

Central-limit approach to risk-aware Markov decision processes Central-limit approach to risk-aware Markov decision processes Jia Yuan Yu Concordia University November 27, 2015 Joint work with Pengqian Yu and Huan Xu. Inventory Management 1 1 Look at current inventory

More information

Approximate Bayesian Computation

Approximate Bayesian Computation Approximate Bayesian Computation Michael Gutmann https://sites.google.com/site/michaelgutmann University of Helsinki and Aalto University 1st December 2015 Content Two parts: 1. The basics of approximate

More information

Methods of evaluating estimators and best unbiased estimators Hamid R. Rabiee

Methods of evaluating estimators and best unbiased estimators Hamid R. Rabiee Stochastic Processes Methods of evaluating estimators and best unbiased estimators Hamid R. Rabiee 1 Outline Methods of Mean Squared Error Bias and Unbiasedness Best Unbiased Estimators CR-Bound for variance

More information

Markov Chain Monte Carlo Methods for Stochastic

Markov Chain Monte Carlo Methods for Stochastic Markov Chain Monte Carlo Methods for Stochastic Optimization i John R. Birge The University of Chicago Booth School of Business Joint work with Nicholas Polson, Chicago Booth. JRBirge U Florida, Nov 2013

More information

Chance constrained optimization - applications, properties and numerical issues

Chance constrained optimization - applications, properties and numerical issues Chance constrained optimization - applications, properties and numerical issues Dr. Abebe Geletu Ilmenau University of Technology Department of Simulation and Optimal Processes (SOP) May 31, 2012 This

More information

On Kusuoka Representation of Law Invariant Risk Measures

On Kusuoka Representation of Law Invariant Risk Measures MATHEMATICS OF OPERATIONS RESEARCH Vol. 38, No. 1, February 213, pp. 142 152 ISSN 364-765X (print) ISSN 1526-5471 (online) http://dx.doi.org/1.1287/moor.112.563 213 INFORMS On Kusuoka Representation of

More information

Bias evaluation and reduction for sample-path optimization

Bias evaluation and reduction for sample-path optimization Bias evaluation and reduction for sample-path optimization 1 1 Department of Computing Science and Operational Research Université de Montréal; CIRRELT Québec, Canada Eigth IMACS Seminar on Monte Carlo

More information

A SECOND ORDER STOCHASTIC DOMINANCE PORTFOLIO EFFICIENCY MEASURE

A SECOND ORDER STOCHASTIC DOMINANCE PORTFOLIO EFFICIENCY MEASURE K Y B E R N E I K A V O L U M E 4 4 ( 2 0 0 8 ), N U M B E R 2, P A G E S 2 4 3 2 5 8 A SECOND ORDER SOCHASIC DOMINANCE PORFOLIO EFFICIENCY MEASURE Miloš Kopa and Petr Chovanec In this paper, we introduce

More information

Bandit Algorithms. Zhifeng Wang ... Department of Statistics Florida State University

Bandit Algorithms. Zhifeng Wang ... Department of Statistics Florida State University Bandit Algorithms Zhifeng Wang Department of Statistics Florida State University Outline Multi-Armed Bandits (MAB) Exploration-First Epsilon-Greedy Softmax UCB Thompson Sampling Adversarial Bandits Exp3

More information

Economics 583: Econometric Theory I A Primer on Asymptotics

Economics 583: Econometric Theory I A Primer on Asymptotics Economics 583: Econometric Theory I A Primer on Asymptotics Eric Zivot January 14, 2013 The two main concepts in asymptotic theory that we will use are Consistency Asymptotic Normality Intuition consistency:

More information

Mathematical Methods for Neurosciences. ENS - Master MVA Paris 6 - Master Maths-Bio ( )

Mathematical Methods for Neurosciences. ENS - Master MVA Paris 6 - Master Maths-Bio ( ) Mathematical Methods for Neurosciences. ENS - Master MVA Paris 6 - Master Maths-Bio (2014-2015) Etienne Tanré - Olivier Faugeras INRIA - Team Tosca October 22nd, 2014 E. Tanré (INRIA - Team Tosca) Mathematical

More information

Exercise 5 Release: Due:

Exercise 5 Release: Due: Stochastic Modeling and Simulation Winter 28 Prof. Dr. I. F. Sbalzarini, Dr. Christoph Zechner (MPI-CBG/CSBD TU Dresden, 87 Dresden, Germany Exercise 5 Release: 8..28 Due: 5..28 Question : Variance of

More information

The University of Hong Kong Department of Statistics and Actuarial Science STAT2802 Statistical Models Tutorial Solutions Solutions to Problems 71-80

The University of Hong Kong Department of Statistics and Actuarial Science STAT2802 Statistical Models Tutorial Solutions Solutions to Problems 71-80 The University of Hong Kong Department of Statistics and Actuarial Science STAT2802 Statistical Models Tutorial Solutions Solutions to Problems 71-80 71. Decide in each case whether the hypothesis is simple

More information

Spatially Smoothed Kernel Density Estimation via Generalized Empirical Likelihood

Spatially Smoothed Kernel Density Estimation via Generalized Empirical Likelihood Spatially Smoothed Kernel Density Estimation via Generalized Empirical Likelihood Kuangyu Wen & Ximing Wu Texas A&M University Info-Metrics Institute Conference: Recent Innovations in Info-Metrics October

More information

arxiv: v2 [math.oc] 18 Nov 2017

arxiv: v2 [math.oc] 18 Nov 2017 DASC: A DECOMPOSITION ALGORITHM FOR MULTISTAGE STOCHASTIC PROGRAMS WITH STRONGLY CONVEX COST FUNCTIONS arxiv:1711.04650v2 [math.oc] 18 Nov 2017 Vincent Guigues School of Applied Mathematics, FGV Praia

More information

Generalized quantiles as risk measures

Generalized quantiles as risk measures Generalized quantiles as risk measures Bellini, Klar, Muller, Rosazza Gianin December 1, 2014 Vorisek Jan Introduction Quantiles q α of a random variable X can be defined as the minimizers of a piecewise

More information

Lecture 7 Introduction to Statistical Decision Theory

Lecture 7 Introduction to Statistical Decision Theory Lecture 7 Introduction to Statistical Decision Theory I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 20, 2016 1 / 55 I-Hsiang Wang IT Lecture 7

More information

Stochastic Mathematical Programs with Equilibrium Constraints, Modeling and Sample Average Approximation

Stochastic Mathematical Programs with Equilibrium Constraints, Modeling and Sample Average Approximation Stochastic Mathematical Programs with Equilibrium Constraints, Modeling and Sample Average Approximation Alexander Shapiro and Huifu Xu Revised June 24, 2005 Abstract. In this paper, we discuss the sample

More information

Lecture 1: August 28

Lecture 1: August 28 36-705: Intermediate Statistics Fall 2017 Lecturer: Siva Balakrishnan Lecture 1: August 28 Our broad goal for the first few lectures is to try to understand the behaviour of sums of independent random

More information

Math 180A. Lecture 16 Friday May 7 th. Expectation. Recall the three main probability density functions so far (1) Uniform (2) Exponential.

Math 180A. Lecture 16 Friday May 7 th. Expectation. Recall the three main probability density functions so far (1) Uniform (2) Exponential. Math 8A Lecture 6 Friday May 7 th Epectation Recall the three main probability density functions so far () Uniform () Eponential (3) Power Law e, ( ), Math 8A Lecture 6 Friday May 7 th Epectation Eample

More information

Generalized Information Reuse for Optimization Under Uncertainty with Non-Sample Average Estimators

Generalized Information Reuse for Optimization Under Uncertainty with Non-Sample Average Estimators Generalized Information Reuse for Optimization Under Uncertainty with Non-Sample Average Estimators Laurence W Cook, Jerome P Jarrett, Karen E Willcox June 14, 2018 Abstract In optimization under uncertainty

More information

II. FOURIER TRANSFORM ON L 1 (R)

II. FOURIER TRANSFORM ON L 1 (R) II. FOURIER TRANSFORM ON L 1 (R) In this chapter we will discuss the Fourier transform of Lebesgue integrable functions defined on R. To fix the notation, we denote L 1 (R) = {f : R C f(t) dt < }. The

More information

Lecture 2. Distributions and Random Variables

Lecture 2. Distributions and Random Variables Lecture 2. Distributions and Random Variables Igor Rychlik Chalmers Department of Mathematical Sciences Probability, Statistics and Risk, MVE300 Chalmers March 2013. Click on red text for extra material.

More information

Gradient-based Adaptive Stochastic Search

Gradient-based Adaptive Stochastic Search 1 / 41 Gradient-based Adaptive Stochastic Search Enlu Zhou H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology November 5, 2014 Outline 2 / 41 1 Introduction

More information

Robust Optimization for Risk Control in Enterprise-wide Optimization

Robust Optimization for Risk Control in Enterprise-wide Optimization Robust Optimization for Risk Control in Enterprise-wide Optimization Juan Pablo Vielma Department of Industrial Engineering University of Pittsburgh EWO Seminar, 011 Pittsburgh, PA Uncertainty in Optimization

More information

The stochastic modeling

The stochastic modeling February 211 Gdansk A schedule of the lecture Generation of randomly arranged numbers Monte Carlo Strong Law of Large Numbers SLLN We use SAS 9 For convenience programs will be given in an appendix Programs

More information

Soumyadip Ghosh. Raghu Pasupathy. IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA. Virginia Tech Blacksburg, VA 24061, USA

Soumyadip Ghosh. Raghu Pasupathy. IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA. Virginia Tech Blacksburg, VA 24061, USA Proceedings of the 2011 Winter Simulation Conference S. Jain, R. R. Creasey, J. Himmelspach, K. P. White, and M. Fu, eds. ON INTERIOR-POINT BASED RETROSPECTIVE APPROXIMATION METHODS FOR SOLVING TWO-STAGE

More information

Estimation and Asymptotics for Buffered Probability of Exceedance

Estimation and Asymptotics for Buffered Probability of Exceedance Estimation and Asymptotics for Buffered Probability of Eceedance Aleander Mafusalov University of Florida mafusalov@ufl.edu Aleander Shapiro Georgia Institute of Technology ashapiro@isye.gatech.edu This

More information

Jitka Dupačová and scenario reduction

Jitka Dupačová and scenario reduction Jitka Dupačová and scenario reduction W. Römisch Humboldt-University Berlin Institute of Mathematics http://www.math.hu-berlin.de/~romisch Session in honor of Jitka Dupačová ICSP 2016, Buzios (Brazil),

More information

Solving Chance-Constrained Stochastic Programs via Sampling and Integer Programming

Solving Chance-Constrained Stochastic Programs via Sampling and Integer Programming IFORMS 2008 c 2008 IFORMS isbn 978-1-877640-23-0 doi 10.1287/educ.1080.0048 Solving Chance-Constrained Stochastic Programs via Sampling and Integer Programming Shabbir Ahmed and Alexander Shapiro H. Milton

More information

36. Multisample U-statistics and jointly distributed U-statistics Lehmann 6.1

36. Multisample U-statistics and jointly distributed U-statistics Lehmann 6.1 36. Multisample U-statistics jointly distributed U-statistics Lehmann 6.1 In this topic, we generalize the idea of U-statistics in two different directions. First, we consider single U-statistics for situations

More information

Differentiation and Integration

Differentiation and Integration Differentiation and Integration (Lectures on Numerical Analysis for Economists II) Jesús Fernández-Villaverde 1 and Pablo Guerrón 2 February 12, 2018 1 University of Pennsylvania 2 Boston College Motivation

More information

Quantifying Stochastic Model Errors via Robust Optimization

Quantifying Stochastic Model Errors via Robust Optimization Quantifying Stochastic Model Errors via Robust Optimization IPAM Workshop on Uncertainty Quantification for Multiscale Stochastic Systems and Applications Jan 19, 2016 Henry Lam Industrial & Operations

More information

Generalized quantiles as risk measures

Generalized quantiles as risk measures Generalized quantiles as risk measures F. Bellini 1, B. Klar 2, A. Müller 3, E. Rosazza Gianin 1 1 Dipartimento di Statistica e Metodi Quantitativi, Università di Milano Bicocca 2 Institut für Stochastik,

More information

Robustní monitorování stability v modelu CAPM

Robustní monitorování stability v modelu CAPM Robustní monitorování stability v modelu CAPM Ondřej Chochola, Marie Hušková, Zuzana Prášková (MFF UK) Josef Steinebach (University of Cologne) ROBUST 2012, Němčičky, 10.-14.9. 2012 Contents Introduction

More information

Miloš Kopa. Decision problems with stochastic dominance constraints

Miloš Kopa. Decision problems with stochastic dominance constraints Decision problems with stochastic dominance constraints Motivation Portfolio selection model Mean risk models max λ Λ m(λ r) νr(λ r) or min λ Λ r(λ r) s.t. m(λ r) µ r is a random vector of assets returns

More information

Operations Research Letters. On a time consistency concept in risk averse multistage stochastic programming

Operations Research Letters. On a time consistency concept in risk averse multistage stochastic programming Operations Research Letters 37 2009 143 147 Contents lists available at ScienceDirect Operations Research Letters journal homepage: www.elsevier.com/locate/orl On a time consistency concept in risk averse

More information

The Functional Central Limit Theorem and Testing for Time Varying Parameters

The Functional Central Limit Theorem and Testing for Time Varying Parameters NBER Summer Institute Minicourse What s New in Econometrics: ime Series Lecture : July 4, 008 he Functional Central Limit heorem and esting for ime Varying Parameters Lecture -, July, 008 Outline. FCL.

More information

on t0 t T, how can one compute the value E[g(X(T ))]? The Monte-Carlo method is based on the

on t0 t T, how can one compute the value E[g(X(T ))]? The Monte-Carlo method is based on the SPRING 2008, CSC KTH - Numerical methods for SDEs, Szepessy, Tempone 203 Monte Carlo Euler for SDEs Consider the stochastic differential equation dx(t) = a(t, X(t))dt + b(t, X(t))dW (t) on t0 t T, how

More information

Asymptotic distribution of the sample average value-at-risk

Asymptotic distribution of the sample average value-at-risk Asymptotic distribution of the sample average value-at-risk Stoyan V. Stoyanov Svetlozar T. Rachev September 3, 7 Abstract In this paper, we prove a result for the asymptotic distribution of the sample

More information

Lecture 2. We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales.

Lecture 2. We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales. Lecture 2 1 Martingales We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales. 1.1 Doob s inequality We have the following maximal

More information

ECE276A: Sensing & Estimation in Robotics Lecture 10: Gaussian Mixture and Particle Filtering

ECE276A: Sensing & Estimation in Robotics Lecture 10: Gaussian Mixture and Particle Filtering ECE276A: Sensing & Estimation in Robotics Lecture 10: Gaussian Mixture and Particle Filtering Lecturer: Nikolay Atanasov: natanasov@ucsd.edu Teaching Assistants: Siwei Guo: s9guo@eng.ucsd.edu Anwesan Pal:

More information

1 Glivenko-Cantelli type theorems

1 Glivenko-Cantelli type theorems STA79 Lecture Spring Semester Glivenko-Cantelli type theorems Given i.i.d. observations X,..., X n with unknown distribution function F (t, consider the empirical (sample CDF ˆF n (t = I [Xi t]. n Then

More information

Long-Run Covariability

Long-Run Covariability Long-Run Covariability Ulrich K. Müller and Mark W. Watson Princeton University October 2016 Motivation Study the long-run covariability/relationship between economic variables great ratios, long-run Phillips

More information

Decomposability and time consistency of risk averse multistage programs

Decomposability and time consistency of risk averse multistage programs Decomposability and time consistency of risk averse multistage programs arxiv:1806.01497v1 [math.oc] 5 Jun 2018 A. Shapiro School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta,

More information

Lecture Particle Filters. Magnus Wiktorsson

Lecture Particle Filters. Magnus Wiktorsson Lecture Particle Filters Magnus Wiktorsson Monte Carlo filters The filter recursions could only be solved for HMMs and for linear, Gaussian models. Idea: Approximate any model with a HMM. Replace p(x)

More information