Superhedging and distributionally robust optimization with neural networks
|
|
- Jessica Craig
- 5 years ago
- Views:
Transcription
1 Superhedging and distributionally robust optimization with neural networks Stephan Eckstein joint work with Michael Kupper and Mathias Pohl Robust Techniques in Quantitative Finance University of Oxford Stephan Eckstein Neural Network Hedging September 5, / 1
2 Robust optimization problems Setup: Set of probability measures Q on R d Continuous and bounded function f : R d R. Objective: Solve (P) := sup ν Q f dν Different choices of Q lead to Constrained optimal transport (see e.g. Ekren and Soner (018), includes martingale optimal transport) Distributionally robust optimization (see e.g. Esfahani and Kuhn (015), Blanchet and Murthy (016), Bartl et al. (017), Ob lój and Wiesel (018)) Mixtures of the above (Gao and Kleywegt (017)) Stephan Eckstein Neural Network Hedging September 5, 018 / 1
3 Robust optimization problems Setup: Set of probability measures Q on R d Continuous and bounded function f : R d R. Objective: Solve (P) := sup ν Q f dν Different choices of Q lead to Constrained optimal transport (see e.g. Ekren and Soner (018), includes martingale optimal transport) Distributionally robust optimization (see e.g. Esfahani and Kuhn (015), Blanchet and Murthy (016), Bartl et al. (017), Ob lój and Wiesel (018)) Mixtures of the above (Gao and Kleywegt (017)) Stephan Eckstein Neural Network Hedging September 5, 018 / 1
4 Robust optimization problems Setup: Set of probability measures Q on R d Continuous and bounded function f : R d R. Objective: Solve (P) := sup ν Q f dν Different choices of Q lead to Constrained optimal transport (see e.g. Ekren and Soner (018), includes martingale optimal transport) Distributionally robust optimization (see e.g. Esfahani and Kuhn (015), Blanchet and Murthy (016), Bartl et al. (017), Ob lój and Wiesel (018)) Mixtures of the above (Gao and Kleywegt (017)) Stephan Eckstein Neural Network Hedging September 5, 018 / 1
5 Robust optimization problems Setup: Set of probability measures Q on R d Continuous and bounded function f : R d R. Objective: Solve (P) := sup ν Q f dν Different choices of Q lead to Constrained optimal transport (see e.g. Ekren and Soner (018), includes martingale optimal transport) Distributionally robust optimization (see e.g. Esfahani and Kuhn (015), Blanchet and Murthy (016), Bartl et al. (017), Ob lój and Wiesel (018)) Mixtures of the above (Gao and Kleywegt (017)) Stephan Eckstein Neural Network Hedging September 5, 018 / 1
6 Example: Martingale optimal transport (MOT) Stock S t for times t = 1, has known marginals µ 1, µ P(R). Q = { ν P(R ) : ν 1 = µ 1, ν = µ, if (S 1, S ) ν, then E[S S 1 ] = S 1 } The function f can model an exotic option, e.g. f (s 1, s ) = (s Ks 1 ) are all potential martingale couplings ? Stephan Eckstein Neural Network Hedging September 5, / 1
7 Numerical approach: Discretization Idea: Reduce problem (P) to a finite dimensional problem (P n ) by going over to a discrete space. In the prior example for instance: Approximate marginals Replace Q by µ 1 µ n 1 = n α i δ xi, µ µ n = i=1 n β i δ yi i=1 Q n = {ν P(R ) : ν 1 = µ n 1, ν = µ n, if (S 1, S ) ν, then E[S S 1 ] = S 1 } Solve (P n ) = inf ν Qn f dν instead of (P). Stephan Eckstein Neural Network Hedging September 5, / 1
8 Numerical approach: Discretization In the prior example for instance: n Measures in n only put mass on intersections of grid n Stephan Eckstein Neural Network Hedging September 5, / 1
9 Numerical approach: Discretization Discretization of (P), as well as solving the discrete versions of (P) are studied and applied successfully in a lot of works: MOT: Alfonsi et al. (017), Guo and Ob lój (018) OT: See e.g. Peyre and Cuturi (018) Distributionally robust optimization: Esfahani and Kuhn (015) Difficulty: Discretization scales badly with dimension. In the prior example, (P n ) has n parameters. In a MOT problem with T time steps, and K dimensional assets, (P n ) has n T K parameters! Stephan Eckstein Neural Network Hedging September 5, / 1
10 Numerical approach: Discretization Discretization of (P), as well as solving the discrete versions of (P) are studied and applied successfully in a lot of works: MOT: Alfonsi et al. (017), Guo and Ob lój (018) OT: See e.g. Peyre and Cuturi (018) Distributionally robust optimization: Esfahani and Kuhn (015) Difficulty: Discretization scales badly with dimension. In the prior example, (P n ) has n parameters. In a MOT problem with T time steps, and K dimensional assets, (P n ) has n T K parameters! Stephan Eckstein Neural Network Hedging September 5, / 1
11 Alternative: Parametrization Idea: Work with {ν λ : λ Λ} Q where Λ is a finite-dimensional parameter space that one can scale independently of dimension. Problem: No expressive sets {ν λ : λ Λ} available that are also numerically feasible to work with. Stephan Eckstein Neural Network Hedging September 5, / 1
12 Using the dual formulation We consider problems (P) = sup ν Q fdν which allow for a dual formulation of the form (D) = inf ϕ(h) h H: h f where H C(R d ) and ϕ : H R is a linear functional. Example: For the MOT problem from before H = {h(x, y) = h 1 (x) + h (y) + h 3 (x) (y x) : h i C b (R)} ϕ(h) = R h 1dµ 1 + R h dµ Parametrizing H is simpler than parametrizing Q! (See also Henry-Labordère (013)) Stephan Eckstein Neural Network Hedging September 5, / 1
13 Using the dual formulation We consider problems (P) = sup ν Q fdν which allow for a dual formulation of the form (D) = inf ϕ(h) h H: h f where H C(R d ) and ϕ : H R is a linear functional. Example: For the MOT problem from before H = {h(x, y) = h 1 (x) + h (y) + h 3 (x) (y x) : h i C b (R)} ϕ(h) = R h 1dµ 1 + R h dµ Parametrizing H is simpler than parametrizing Q! (See also Henry-Labordère (013)) Stephan Eckstein Neural Network Hedging September 5, / 1
14 Why use neural networks? (Feed-forward) neural networks are parametrized functions that build on concatenation of several layers of simple functions. R k x A l σ A }{{ l 1... σ A } 0 (x) }{{} (l 1). layer 1. layer where A i are affine transformations and σ : R R is a non-linear activation function that is applied element-wise. Neural networks can approximate a lot of functions with a high, but numerically feasible amount of parameters. Successful in practice, even though theoretical understanding of numerical schemes is lacking. Stephan Eckstein Neural Network Hedging September 5, / 1
15 Solution approach using neural networks (D) = inf h H: h f ϕ(h) Step 1: We replace H by a set of neural network functions H m. Thereby, trading strategies are then restricted to feed-forward neural networks. Resulting finite-dimensional problem (D m ) = inf h H m : h f ϕ(h) Problem: Constraint h f prevents application of numerical schemes based on gradient-descent. Stephan Eckstein Neural Network Hedging September 5, / 1
16 Solution approach using neural networks (D m ) = inf h H m : h f ϕ(h) Step : Penalize the inequality constraint h f. (Dθ m ) = inf ϕ(h) + max{f h, 0}dθ h H m If θ gives positive mass of every open ball, then (D m θ ) = (Dm ). Implementation problem: The mapping x max{0, x} has no useful gradients. Stephan Eckstein Neural Network Hedging September 5, / 1
17 Solution approach using neural networks (Dθ m ) = inf ϕ(h) + h H m max{f h, 0}dθ Step 3: Approximate x max{x, 0} by a sequence of differentiable nondecreasing convex functions (β γ ) γ>0, e.g. β γ = γ max{0, x}. (Dθ,γ m ) = inf ϕ(h) + β γ (f h)dθ h H m Stephan Eckstein Neural Network Hedging September 5, / 1
18 Solution approach: Overview Label Statement Description (D) inf h H: h f ϕ(h) initial problem (D m ) inf h H m : h f (D m θ ) inf h H m ϕ(h) + (Dθ,γ m ) inf ϕ(h) + h H m ϕ(h) finite dimensional version of (D) (f h) + dθ dominated version of (D m ) β γ (f h) dθ penalized version of (D m θ ) Table: Summary of problems occurring in the approach. Stephan Eckstein Neural Network Hedging September 5, / 1
19 Solution approach: Theoretical results Under mild assumptions on H, H m and θ it holds (D m ) (D) for m (1) (D m θ,γ ) (Dm ) for γ () Related results To (1): E.g. Bühler et al. (018), To (): E.g. Cominetti and San Martín (1994), Cuturi (013), many others related to Sinkhorn distance, Bregman projection and Schrödinger problem. Stephan Eckstein Neural Network Hedging September 5, / 1
20 Solution approach: Theoretical results Under mild assumptions on H, H m and θ it holds (D m ) (D) for m (1) (D m θ,γ ) (Dm ) for γ () Related results To (1): E.g. Bühler et al. (018), To (): E.g. Cominetti and San Martín (1994), Cuturi (013), many others related to Sinkhorn distance, Bregman projection and Schrödinger problem. Stephan Eckstein Neural Network Hedging September 5, / 1
21 Numerics: MOT example MOT as in introduction f (s1, s) = (s s1) + Marginals µ 1, µ : Some mixtures of normals Parameter Optimizer Superhedging price Subhedging price (inf over Q instead) Neural network NN with 4 layers & hidden dimension 64, θ = µ 1 µ, β γ (x) = 1000 max{0, x} Approximate dual optimizer ĥ Discretization n = 600 (Relaxed martingale constraint: ε = 10 6 ) Approximate coupling ˆν Stephan Eckstein Neural Network Hedging September 5, / 1
22 MOT: Dual optimizer Superhedging Stephan Eckstein Neural Network Hedging September 5, / 1
23 MOT: Dual optimizer Subhedging Stephan Eckstein Neural Network Hedging September 5, / 1
24 Back to the primal Goal: Use the neural network solution of the dual to obtain a (near) optimal measure of the primal! The problem (D θ,γ ) = inf ϕ(h) + h H has a primal formulation (P θ,γ ) = sup ν Q fdν β γ (f h)dθ β γ ( ) dν dθ dθ and if (D θ,γ ) has an optimizer ĥ, one can often show that ˆν given by is an optimizer of (P θ,γ ). d ˆν dθ = β γ(f ĥ) Stephan Eckstein Neural Network Hedging September 5, / 1
25 Back to the primal Goal: Use the neural network solution of the dual to obtain a (near) optimal measure of the primal! The problem (D θ,γ ) = inf ϕ(h) + h H has a primal formulation (P θ,γ ) = sup ν Q fdν β γ (f h)dθ β γ ( ) dν dθ dθ and if (D θ,γ ) has an optimizer ĥ, one can often show that ˆν given by is an optimizer of (P θ,γ ). d ˆν dθ = β γ(f ĥ) Stephan Eckstein Neural Network Hedging September 5, / 1
26 Back to the primal Goal: Use the neural network solution of the dual to obtain a (near) optimal measure of the primal! The problem (D θ,γ ) = inf ϕ(h) + h H has a primal formulation (P θ,γ ) = sup ν Q fdν β γ (f h)dθ β γ ( ) dν dθ dθ and if (D θ,γ ) has an optimizer ĥ, one can often show that ˆν given by is an optimizer of (P θ,γ ). d ˆν dθ = β γ(f ĥ) Stephan Eckstein Neural Network Hedging September 5, / 1
27 MOT: Primal optimizer Approximately optimal coupling: Superhedging Stephan Eckstein Neural Network Hedging September 5, / 1
28 MOT: Primal optimizer Approximately optimal coupling: Subhedging Stephan Eckstein Neural Network Hedging September 5, / 1
29 MOT: Primal optimizer Approximately optimal coupling: Subhedging Stephan Eckstein Neural Network Hedging September 5, / 1
30 Risk aggregation (DNB Case Study - Aas and Puccetti (014)) Bank is exposed to 6 types of risks X 1,..., X 6 with known marginal exposures. An expert opinion µ P(R 6 ) about the joint distribution of (X 1,..., X 6 ) is given. Goal: Calculate bounds on under constraints that AVaR α ( 6 i=1 X i (X 1,..., X 6 ) have marginals µ 1,..., µ 6 Joint distribution ν (X 1,..., X 6 ) is in a Wasserstein ball around µ of a given radius ρ: W p ( µ, ν) ρ ) Stephan Eckstein Neural Network Hedging September 5, / 1
31 Risk aggregation (DNB Case Study - Aas and Puccetti (014)) Bank is exposed to 6 types of risks X 1,..., X 6 with known marginal exposures. An expert opinion µ P(R 6 ) about the joint distribution of (X 1,..., X 6 ) is given. Goal: Calculate bounds on under constraints that AVaR α ( 6 i=1 X i (X 1,..., X 6 ) have marginals µ 1,..., µ 6 Joint distribution ν (X 1,..., X 6 ) is in a Wasserstein ball around µ of a given radius ρ: W p ( µ, ν) ρ ) Stephan Eckstein Neural Network Hedging September 5, / 1
32 Bank risk aggregation (DNB Case Study) Using only marginal information: Average Value at Risk for = 0.95 Reference model 4165 (Best Case) (Worst Case) Stephan Eckstein Neural Network Hedging September 5, / 1
33 Bank risk aggregation (DNB Case Study) Worst case around reference model: Average Value at Risk for = 0.95 Reference model 4165 (Best Case) ( = 1/6) ( = 1) (Worst Case) Worst case over Wasserstein ball around of radius Stephan Eckstein Neural Network Hedging September 5, / 1
34 Thank you
35 References Aas, Kjersti and Puccetti, Giovanni Bounds on total economic capital: the DNB case study Springer, 17(4): , 014. Alfonsi, Aurélien and Corbetta, Jacopo and Jourdain, Benjamin Sampling of probability measures in the convex order and approximation of Martingale Optimal Transport problems arxiv preprint arxiv: , 017. Bartl, Daniel and Drapeau, Samuel and Tangpi, Ludovic Computational aspects of robust optimized certainty equivalents arxiv preprint arxiv: , 017. Blanchet, Jose and Murthy, Karthyek RA Quantifying distributional model risk via optimal transport arxiv preprint arxiv: , 016. H. Buehler, L. Gonon, J. Teichmann, and B. Wood. Deep hedging. arxiv preprint arxiv: , 018.
36 R. Cominetti and J. San Martín. Asymptotic analysis of the exponential penalty trajectory in linear programming. Mathematical Programming, 67(1-3): , M. Cuturi. Sinkhorn distances: Lightspeed computation of optimal transport. In Advances in neural information processing systems, pages 9 300, 013. Eckstein, Stephan and Kupper, Michael Computation of optimal transport and related hedging problems via penalization and neural networks. arxiv preprint arxiv: , 018. I. Ekren and H. M. Soner. Constrained optimal transport. Archive for Rational Mechanics and Analysis, pages 1 37, 017. Esfahani, Peyman Mohajerin and Kuhn, Daniel Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations Mathematical Programming, pages 1 5, 017.
37 R. Gao and A. Kleywegt Data-Driven Robust Optimization with Known Marginal Distributions Working paper, 017 Henry-Labordère, Pierre Automated option pricing: Numerical methods International Journal of Theoretical and Applied Finance, 013. Guo, Gaoyue and Obloj, Jan Computational Methods for Martingale Optimal Transport problems arxiv preprint arxiv: , 017. Obloj, Jan and Wiesel, Johannes Statistical estimation of superhedging prices arxiv preprint arxiv: , 018. Peyré, Gabriel and Cuturi, Marco Computational optimal transport arxiv preprint arxiv: , 018.
arxiv: v1 [math.oc] 23 Feb 2018
Computation of optimal transport and related hedging problems via penalization and neural networks arxiv:1802.08539v1 [math.oc] 23 Feb 2018 Stephan Eckstein Michael Kupper February 26, 2018 Abstract This
More informationOptimal Transport in Risk Analysis
Optimal Transport in Risk Analysis Jose Blanchet (based on work with Y. Kang and K. Murthy) Stanford University (Management Science and Engineering), and Columbia University (Department of Statistics and
More informationOptimal Transport Methods in Operations Research and Statistics
Optimal Transport Methods in Operations Research and Statistics Jose Blanchet (based on work with F. He, Y. Kang, K. Murthy, F. Zhang). Stanford University (Management Science and Engineering), and Columbia
More informationAdditional information and pricing-hedging duality in robust framework
Additional information and pricing-hedging duality in robust framework Anna Aksamit based on joint work with Zhaoxu Hou and Jan Ob lój London - Paris Bachelier Workshop on Mathematical Finance Paris, September
More informationCanonical Supermartingale Couplings
Canonical Supermartingale Couplings Marcel Nutz Columbia University (with Mathias Beiglböck, Florian Stebegg and Nizar Touzi) June 2016 Marcel Nutz (Columbia) Canonical Supermartingale Couplings 1 / 34
More informationRobust pricing hedging duality for American options in discrete time financial markets
Robust pricing hedging duality for American options in discrete time financial markets Anna Aksamit The University of Sydney based on joint work with Shuoqing Deng, Jan Ob lój and Xiaolu Tan Robust Techniques
More informationDistributionally Robust Stochastic Optimization with Wasserstein Distance
Distributionally Robust Stochastic Optimization with Wasserstein Distance Rui Gao DOS Seminar, Oct 2016 Joint work with Anton Kleywegt School of Industrial and Systems Engineering Georgia Tech What is
More informationQuantifying 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 informationRisk Aggregation with Dependence Uncertainty
Introduction Extreme Scenarios Asymptotic Behavior Challenges Risk Aggregation with Dependence Uncertainty Department of Statistics and Actuarial Science University of Waterloo, Canada Seminar at ETH Zurich
More informationBounding Wrong-Way Risk in CVA Calculation
Bounding Wrong-Way Risk in CVA Calculation Paul Glasserman, Linan Yang May 2015 Abstract A credit valuation adjustment (CVA) is an adjustment applied to the value of a derivative contract or a portfolio
More informationDuality formulas for robust pricing and hedging in discrete time
Duality formulas for robust pricing and hedging in discrete time Patrick Cheridito Michael Kupper Ludovic Tangpi February 2016 Abstract In this paper we derive robust super- and subhedging dualities for
More informationMinimal Supersolutions of Backward Stochastic Differential Equations and Robust Hedging
Minimal Supersolutions of Backward Stochastic Differential Equations and Robust Hedging SAMUEL DRAPEAU Humboldt-Universität zu Berlin BSDEs, Numerics and Finance Oxford July 2, 2012 joint work with GREGOR
More informationFRIAS Workshop on Robust Optimization and Control (ROC 2014)
University of Freiburg FRIAS Workshop on Robust Optimization and Control (ROC 2014) August 20, 2014, 9:30-16:30 FRIAS Workshop on Robust Optimization and Control (ROC 2014) 3 Contents I Welcome....................................
More informationDistirbutional robustness, regularizing variance, and adversaries
Distirbutional robustness, regularizing variance, and adversaries John Duchi Based on joint work with Hongseok Namkoong and Aman Sinha Stanford University November 2017 Motivation We do not want machine-learned
More informationGenerative Models and Optimal Transport
Generative Models and Optimal Transport Marco Cuturi Joint work / work in progress with G. Peyré, A. Genevay (ENS), F. Bach (INRIA), G. Montavon, K-R Müller (TU Berlin) Statistics 0.1 : Density Fitting
More informationConvex Optimization in Computer Vision:
Convex Optimization in Computer Vision: Segmentation and Multiview 3D Reconstruction Yiyong Feng and Daniel P. Palomar The Hong Kong University of Science and Technology (HKUST) ELEC 5470 - Convex Optimization
More informationTHE stochastic and dynamic environments of many practical
A Convex Optimization Approach to Distributionally Robust Markov Decision Processes with Wasserstein Distance Insoon Yang, Member, IEEE Abstract In this paper, we consider the problem of constructing control
More informationData-Driven Distributionally Robust Chance-Constrained Optimization with Wasserstein Metric
Data-Driven Distributionally Robust Chance-Constrained Optimization with asserstein Metric Ran Ji Department of System Engineering and Operations Research, George Mason University, rji2@gmu.edu; Miguel
More informationDistributionally Robust Convex Optimization
Submitted to Operations Research manuscript OPRE-2013-02-060 Authors are encouraged to submit new papers to INFORMS journals by means of a style file template, which includes the journal title. However,
More informationRobust Hypothesis Testing Using Wasserstein Uncertainty Sets
Robust Hypothesis Testing Using Wasserstein Uncertainty Sets Rui Gao School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 3332 rgao32@gatech.edu Yao Xie School of Industrial
More informationShiqian Ma, MAT-258A: Numerical Optimization 1. Chapter 4. Subgradient
Shiqian Ma, MAT-258A: Numerical Optimization 1 Chapter 4 Subgradient Shiqian Ma, MAT-258A: Numerical Optimization 2 4.1. Subgradients definition subgradient calculus duality and optimality conditions Shiqian
More informationComputational aspects of robust optimized certainty equivalents and option pricing
Computational aspects of robust optimized certainty equivalents and option pricing Daniel Bartl a,1, Samuel Drapeau b,2,, Ludovic Tangpi c,3, April 17, 2018 arxiv:1706.10186v2 [q-fin.rm] 16 Apr 2018 ABSTRACT
More informationCS-E4830 Kernel Methods in Machine Learning
CS-E4830 Kernel Methods in Machine Learning Lecture 3: Convex optimization and duality Juho Rousu 27. September, 2017 Juho Rousu 27. September, 2017 1 / 45 Convex optimization Convex optimisation This
More informationA Note on Robust Representations of Law-Invariant Quasiconvex Functions
A Note on Robust Representations of Law-Invariant Quasiconvex Functions Samuel Drapeau Michael Kupper Ranja Reda October 6, 21 We give robust representations of law-invariant monotone quasiconvex functions.
More informationDistributionally Robust Convex Optimization
Distributionally Robust Convex Optimization Wolfram Wiesemann 1, Daniel Kuhn 1, and Melvyn Sim 2 1 Department of Computing, Imperial College London, United Kingdom 2 Department of Decision Sciences, National
More informationSubgradient. Acknowledgement: this slides is based on Prof. Lieven Vandenberghes lecture notes. definition. subgradient calculus
1/41 Subgradient Acknowledgement: this slides is based on Prof. Lieven Vandenberghes lecture notes definition subgradient calculus duality and optimality conditions directional derivative Basic inequality
More informationShort-time expansions for close-to-the-money options under a Lévy jump model with stochastic volatility
Short-time expansions for close-to-the-money options under a Lévy jump model with stochastic volatility José Enrique Figueroa-López 1 1 Department of Statistics Purdue University Statistics, Jump Processes,
More informationOn Distributionally Robust Chance Constrained Program with Wasserstein Distance
On Distributionally Robust Chance Constrained Program with Wasserstein Distance Weijun Xie 1 1 Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA 4061 June 15, 018 Abstract
More informationLearning Methods for Online Prediction Problems. Peter Bartlett Statistics and EECS UC Berkeley
Learning Methods for Online Prediction Problems Peter Bartlett Statistics and EECS UC Berkeley Course Synopsis A finite comparison class: A = {1,..., m}. 1. Prediction with expert advice. 2. With perfect
More informationConstrained Optimization and Lagrangian Duality
CIS 520: Machine Learning Oct 02, 2017 Constrained Optimization and Lagrangian Duality Lecturer: Shivani Agarwal Disclaimer: These notes are designed to be a supplement to the lecture. They may or may
More informationRearrangement Algorithm and Maximum Entropy
University of Illinois at Chicago Joint with Carole Bernard Vrije Universiteit Brussel and Steven Vanduffel Vrije Universiteit Brussel R/Finance, May 19-20, 2017 Introduction An important problem in Finance:
More informationarxiv: 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 informationSharp bounds on the VaR for sums of dependent risks
Paul Embrechts Sharp bounds on the VaR for sums of dependent risks joint work with Giovanni Puccetti (university of Firenze, Italy) and Ludger Rüschendorf (university of Freiburg, Germany) Mathematical
More informationarxiv: v1 [stat.ml] 27 May 2018
Robust Hypothesis Testing Using Wasserstein Uncertainty Sets arxiv:1805.10611v1 stat.ml] 27 May 2018 Rui Gao School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332
More informationSEPARABILITY AND COMPLETENESS FOR THE WASSERSTEIN DISTANCE
SEPARABILITY AND COMPLETENESS FOR THE WASSERSTEIN DISTANCE FRANÇOIS BOLLEY Abstract. In this note we prove in an elementary way that the Wasserstein distances, which play a basic role in optimal transportation
More informationLagrange duality. The Lagrangian. We consider an optimization program of the form
Lagrange duality Another way to arrive at the KKT conditions, and one which gives us some insight on solving constrained optimization problems, is through the Lagrange dual. The dual is a maximization
More informationOptimization 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 informationSet-Valued Risk Measures and Bellman s Principle
Set-Valued Risk Measures and Bellman s Principle Zach Feinstein Electrical and Systems Engineering, Washington University in St. Louis Joint work with Birgit Rudloff (Vienna University of Economics and
More informationTime Series Models for Measuring Market Risk
Time Series Models for Measuring Market Risk José Miguel Hernández Lobato Universidad Autónoma de Madrid, Computer Science Department June 28, 2007 1/ 32 Outline 1 Introduction 2 Competitive and collaborative
More informationOptimal Skorokhod embedding under finitely-many marginal constraints
Optimal Skorokhod embedding under finitely-many marginal constraints Gaoyue Guo Xiaolu Tan Nizar Touzi June 10, 2015 Abstract The Skorokhod embedding problem aims to represent a given probability measure
More informationWorst-Case Expected Shortfall with Univariate and Bivariate. Marginals
Worst-Case Expected Shortfall with Univariate and Bivariate Marginals Anulekha Dhara Bikramjit Das Karthik Natarajan Abstract Worst-case bounds on the expected shortfall risk given only limited information
More informationReformulation 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 informationTightness and duality of martingale transport on the Skorokhod space
Tightness and duality of martingale transport on the Skorokhod space Gaoyue Guo Xiaolu Tan Nizar Touzi July 4, 2015 Abstract The martingale optimal transport aims to optimally transfer a probability measure
More informationTime inconsistency of optimal policies of distributionally robust inventory models
Time inconsistency of optimal policies of distributionally robust inventory models Alexander Shapiro Linwei Xin Abstract In this paper, we investigate optimal policies of distributionally robust (risk
More informationDistributionally Robust Groupwise Regularization Estimator
Proceedings of Machine Learning Research 77:97 112, 2017 ACML 2017 Distributionally Robust Groupwise Regularization Estimator Jose Blanchet jose.blanchet@columbia.edu Yang Kang yang.kang@columbia.edu 1255
More informationRisk Measures in non-dominated Models
Purpose: Study Risk Measures taking into account the model uncertainty in mathematical finance. Plan 1 Non-dominated Models Model Uncertainty Fundamental topological Properties 2 Risk Measures on L p (c)
More informationDistributed Optimization via Alternating Direction Method of Multipliers
Distributed Optimization via Alternating Direction Method of Multipliers Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato Stanford University ITMANET, Stanford, January 2011 Outline precursors dual decomposition
More informationVaR bounds in models with partial dependence information on subgroups
VaR bounds in models with partial dependence information on subgroups L. Rüschendorf J. Witting February 23, 2017 Abstract We derive improved estimates for the model risk of risk portfolios when additional
More informationThe dynamics of Schrödinger bridges
Stochastic processes and statistical machine learning February, 15, 2018 Plan of the talk The Schrödinger problem and relations with Monge-Kantorovich problem Newton s law for entropic interpolation The
More informationRandom Convex Approximations of Ambiguous Chance Constrained Programs
Random Convex Approximations of Ambiguous Chance Constrained Programs Shih-Hao Tseng Eilyan Bitar Ao Tang Abstract We investigate an approach to the approximation of ambiguous chance constrained programs
More informationDuality formulas for robust pricing and hedging in discrete time
Duality formulas for robust pricing and hedging in discrete time Patrick Cheridito Michael Kupper Ludovic Tangpi arxiv:1602.06177v5 [q-fin.mf] 13 Sep 2017 September 2017 Abstract In this paper we derive
More informationComputational Methods for Martingale Optimal Transport problems
Computational Methods for Martingale Optimal Transport problems Gaoyue Guo and Jan Obłój Mathematical Institute, University of Oxford AWB, ROQ, Oxford OX2 6GG, UK arxiv:1710.07911v1 [math.pr] 22 Oct 2017
More informationOn the monotonicity principle of optimal Skorokhod embedding problem
On the monotonicity principle of optimal Skorokhod embedding problem Gaoyue Guo Xiaolu Tan Nizar Touzi June 10, 2015 Abstract This is a continuation of our accompanying paper [18]. We provide an alternative
More informationDuality. Lagrange dual problem weak and strong duality optimality conditions perturbation and sensitivity analysis generalized inequalities
Duality Lagrange dual problem weak and strong duality optimality conditions perturbation and sensitivity analysis generalized inequalities Lagrangian Consider the optimization problem in standard form
More informationGeneralized 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 informationPenalized Barycenters in the Wasserstein space
Penalized Barycenters in the Wasserstein space Elsa Cazelles, joint work with Jérémie Bigot & Nicolas Papadakis Université de Bordeaux & CNRS Journées IOP - Du 5 au 8 Juillet 2017 Bordeaux Elsa Cazelles
More informationA Brief Review on Convex Optimization
A Brief Review on Convex Optimization 1 Convex set S R n is convex if x,y S, λ,µ 0, λ+µ = 1 λx+µy S geometrically: x,y S line segment through x,y S examples (one convex, two nonconvex sets): A Brief Review
More informationStationary states for the aggregation equation with power law attractive-repulsive potentials
Stationary states for the aggregation equation with power law attractive-repulsive potentials Daniel Balagué Joint work with J.A. Carrillo, T. Laurent and G. Raoul Universitat Autònoma de Barcelona BIRS
More informationSample of Ph.D. Advisory Exam For MathFinance
Sample of Ph.D. Advisory Exam For MathFinance Students who wish to enter the Ph.D. program of Mathematics of Finance are required to take the advisory exam. This exam consists of three major parts. The
More informationDistributionally Robust Stochastic Optimization with Dependence Structure
Distributionally Robust Stochastic Optimization with Dependence Structure Rui Gao Anton J. Kleywegt the date of receipt and acceptance should be inserted later Abstract Distributionally robust stochastic
More informationDistributionally Robust Discrete Optimization with Entropic Value-at-Risk
Distributionally Robust Discrete Optimization with Entropic Value-at-Risk Daniel Zhuoyu Long Department of SEEM, The Chinese University of Hong Kong, zylong@se.cuhk.edu.hk Jin Qi NUS Business School, National
More informationArtificial Intelligence
Artificial Intelligence Explainable AI Marc Toussaint University of Stuttgart Winter 2018/19 Explainable AI General Concept of Explaination Data, Objective, Method, & Input Counterfactuals & Pearl Fitting
More informationOptimal Transport: A Crash Course
Optimal Transport: A Crash Course Soheil Kolouri and Gustavo K. Rohde HRL Laboratories, University of Virginia Introduction What is Optimal Transport? The optimal transport problem seeks the most efficient
More informationSupport Vector Machines: Maximum Margin Classifiers
Support Vector Machines: Maximum Margin Classifiers Machine Learning and Pattern Recognition: September 16, 2008 Piotr Mirowski Based on slides by Sumit Chopra and Fu-Jie Huang 1 Outline What is behind
More informationStructural and Multidisciplinary Optimization. P. Duysinx and P. Tossings
Structural and Multidisciplinary Optimization P. Duysinx and P. Tossings 2018-2019 CONTACTS Pierre Duysinx Institut de Mécanique et du Génie Civil (B52/3) Phone number: 04/366.91.94 Email: P.Duysinx@uliege.be
More informationExplicit Bounds for the Distribution Function of the Sum of Dependent Normally Distributed Random Variables
Explicit Bounds for the Distribution Function of the Sum of Dependent Normally Distributed Random Variables Walter Schneider July 26, 20 Abstract In this paper an analytic expression is given for the bounds
More informationOptimal mass transport as a distance measure between images
Optimal mass transport as a distance measure between images Axel Ringh 1 1 Department of Mathematics, KTH Royal Institute of Technology, Stockholm, Sweden. 21 st of June 2018 INRIA, Sophia-Antipolis, France
More information5. Duality. Lagrangian
5. Duality Convex Optimization Boyd & Vandenberghe Lagrange dual problem weak and strong duality geometric interpretation optimality conditions perturbation and sensitivity analysis examples generalized
More informationConvex Optimization M2
Convex Optimization M2 Lecture 3 A. d Aspremont. Convex Optimization M2. 1/49 Duality A. d Aspremont. Convex Optimization M2. 2/49 DMs DM par email: dm.daspremont@gmail.com A. d Aspremont. Convex Optimization
More informationOWL to the rescue of LASSO
OWL to the rescue of LASSO IISc IBM day 2018 Joint Work R. Sankaran and Francis Bach AISTATS 17 Chiranjib Bhattacharyya Professor, Department of Computer Science and Automation Indian Institute of Science,
More informationThomas Knispel Leibniz Universität Hannover
Optimal long term investment under model ambiguity Optimal long term investment under model ambiguity homas Knispel Leibniz Universität Hannover knispel@stochastik.uni-hannover.de AnStAp0 Vienna, July
More informationNewton Method with Adaptive Step-Size for Under-Determined Systems of Equations
Newton Method with Adaptive Step-Size for Under-Determined Systems of Equations Boris T. Polyak Andrey A. Tremba V.A. Trapeznikov Institute of Control Sciences RAS, Moscow, Russia Profsoyuznaya, 65, 117997
More informationSolving Dual Problems
Lecture 20 Solving Dual Problems We consider a constrained problem where, in addition to the constraint set X, there are also inequality and linear equality constraints. Specifically the minimization problem
More informationMath 273a: Optimization Convex Conjugacy
Math 273a: Optimization Convex Conjugacy Instructor: Wotao Yin Department of Mathematics, UCLA Fall 2015 online discussions on piazza.com Convex conjugate (the Legendre transform) Let f be a closed proper
More informationUnderstanding GANs: Back to the basics
Understanding GANs: Back to the basics David Tse Stanford University Princeton University May 15, 2018 Joint work with Soheil Feizi, Farzan Farnia, Tony Ginart, Changho Suh and Fei Xia. GANs at NIPS 2017
More informationPrimal-dual Subgradient Method for Convex Problems with Functional Constraints
Primal-dual Subgradient Method for Convex Problems with Functional Constraints Yurii Nesterov, CORE/INMA (UCL) Workshop on embedded optimization EMBOPT2014 September 9, 2014 (Lucca) Yu. Nesterov Primal-dual
More informationConditional and Dynamic Preferences
Conditional and Dynamic Preferences How can we Understand Risk in a Dynamic Setting? Samuel Drapeau Joint work with Hans Föllmer Humboldt University Berlin Jena - March 17th 2009 Samuel Drapeau Joint work
More informationDistributionally robust optimization techniques in batch bayesian optimisation
Distributionally robust optimization techniques in batch bayesian optimisation Nikitas Rontsis June 13, 2016 1 Introduction This report is concerned with performing batch bayesian optimization of an unknown
More informationSensitivity analysis of the expected utility maximization problem with respect to model perturbations
Sensitivity analysis of the expected utility maximization problem with respect to model perturbations Mihai Sîrbu, The University of Texas at Austin based on joint work with Oleksii Mostovyi University
More informationMartingale optimal transport with Monge s cost function
Martingale optimal transport with Monge s cost function Martin Klimmek, joint work with David Hobson (Warwick) klimmek@maths.ox.ac.uk Crete July, 2013 ca. 1780 c(x, y) = x y No splitting, transport along
More informationRandom G -Expectations
Random G -Expectations Marcel Nutz ETH Zurich New advances in Backward SDEs for nancial engineering applications Tamerza, Tunisia, 28.10.2010 Marcel Nutz (ETH) Random G-Expectations 1 / 17 Outline 1 Random
More informationLecture 8 Plus properties, merit functions and gap functions. September 28, 2008
Lecture 8 Plus properties, merit functions and gap functions September 28, 2008 Outline Plus-properties and F-uniqueness Equation reformulations of VI/CPs Merit functions Gap merit functions FP-I book:
More informationLarge deviations for random projections of l p balls
1/32 Large deviations for random projections of l p balls Nina Gantert CRM, september 5, 2016 Goal: Understanding random projections of high-dimensional convex sets. 2/32 2/32 Outline Goal: Understanding
More informationEE613 Machine Learning for Engineers. Kernel methods Support Vector Machines. jean-marc odobez 2015
EE613 Machine Learning for Engineers Kernel methods Support Vector Machines jean-marc odobez 2015 overview Kernel methods introductions and main elements defining kernels Kernelization of k-nn, K-Means,
More informationIteration-complexity of first-order penalty methods for convex programming
Iteration-complexity of first-order penalty methods for convex programming Guanghui Lan Renato D.C. Monteiro July 24, 2008 Abstract This paper considers a special but broad class of convex programing CP)
More informationNeighboring feasible trajectories in infinite dimension
Neighboring feasible trajectories in infinite dimension Marco Mazzola Université Pierre et Marie Curie (Paris 6) H. Frankowska and E. M. Marchini Control of State Constrained Dynamical Systems Padova,
More informationORIGINS OF STOCHASTIC PROGRAMMING
ORIGINS OF STOCHASTIC PROGRAMMING Early 1950 s: in applications of Linear Programming unknown values of coefficients: demands, technological coefficients, yields, etc. QUOTATION Dantzig, Interfaces 20,1990
More informationg(x,y) = c. For instance (see Figure 1 on the right), consider the optimization problem maximize subject to
1 of 11 11/29/2010 10:39 AM From Wikipedia, the free encyclopedia In mathematical optimization, the method of Lagrange multipliers (named after Joseph Louis Lagrange) provides a strategy for finding the
More informationU Logo Use Guidelines
Information Theory Lecture 3: Applications to Machine Learning U Logo Use Guidelines Mark Reid logo is a contemporary n of our heritage. presents our name, d and our motto: arn the nature of things. authenticity
More informationNumerical Optimal Transport and Applications
Numerical Optimal Transport and Applications Gabriel Peyré Joint works with: Jean-David Benamou, Guillaume Carlier, Marco Cuturi, Luca Nenna, Justin Solomon www.numerical-tours.com Histograms in Imaging
More informationLecture 6: Conic Optimization September 8
IE 598: Big Data Optimization Fall 2016 Lecture 6: Conic Optimization September 8 Lecturer: Niao He Scriber: Juan Xu Overview In this lecture, we finish up our previous discussion on optimality conditions
More informationSupport vector machines
Support vector machines Guillaume Obozinski Ecole des Ponts - ParisTech SOCN course 2014 SVM, kernel methods and multiclass 1/23 Outline 1 Constrained optimization, Lagrangian duality and KKT 2 Support
More informationRobust minimum encoding ball and Support vector data description (SVDD)
Robust minimum encoding ball and Support vector data description (SVDD) Stéphane Canu stephane.canu@litislab.eu. Meriem El Azamin, Carole Lartizien & Gaëlle Loosli INRIA, Septembre 2014 September 24, 2014
More informationOptimization 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 informationICS-E4030 Kernel Methods in Machine Learning
ICS-E4030 Kernel Methods in Machine Learning Lecture 3: Convex optimization and duality Juho Rousu 28. September, 2016 Juho Rousu 28. September, 2016 1 / 38 Convex optimization Convex optimisation This
More informationConvergence of generalized entropy minimizers in sequences of convex problems
Proceedings IEEE ISIT 206, Barcelona, Spain, 2609 263 Convergence of generalized entropy minimizers in sequences of convex problems Imre Csiszár A Rényi Institute of Mathematics Hungarian Academy of Sciences
More informationLecture 8. Strong Duality Results. September 22, 2008
Strong Duality Results September 22, 2008 Outline Lecture 8 Slater Condition and its Variations Convex Objective with Linear Inequality Constraints Quadratic Objective over Quadratic Constraints Representation
More informationarxiv: v3 [stat.ml] 4 Aug 2017
SEMI-SUPERVISED LEARNING BASED ON DISTRIBUTIONALLY ROBUST OPTIMIZATION JOSE BLANCHET AND YANG KANG arxiv:1702.08848v3 stat.ml] 4 Aug 2017 Abstract. We propose a novel method for semi-supervised learning
More informationPortfolio 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 informationAccelerated Dual Gradient-Based Methods for Total Variation Image Denoising/Deblurring Problems (and other Inverse Problems)
Accelerated Dual Gradient-Based Methods for Total Variation Image Denoising/Deblurring Problems (and other Inverse Problems) Donghwan Kim and Jeffrey A. Fessler EECS Department, University of Michigan
More information