Soroosh Shafiee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Soroosh Shafiee has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Kuhn
Risk Analytics and Optimization Chair, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
4 shared publications - Fatma Kılınç-Karzan
Tepper School of Business, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
4 shared publications - Florian Dörfler
ETH Zurich, Zurich, Switzerland
3 shared publications - Bahar Taşkesen
Risk Analytics and Optimization Chair EPFL
2 shared publications - Dabeen Lee
Department of Industrial and Systems Engineering KAIST 34141 Daejeon Republic of Korea
2 shared publications - Simge Küçükyavuz
Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, Illinois 60208
2 shared publications
Latest Publications
- 1 May 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 74 (3) , 1689-1709
Nash Equilibria, Regularization, and Computation in Optimal Transport-Based Distributionally Robust Optimization
Nature Doesn’t Play Dice, It Plays to Win Decision making under uncertainty can be brittle, often failing when real-world data deviates from training assumptions. This study frames this problem as a game between a decision maker and an adversary, nature, who strategically corrupts the data distribution to create a worst case scenario with the cost of these changes defined by optimal transport theory. The authors establish conditions under which a stable outcome, a Nash equilibrium, exists and provide efficient methods to compute it. A key insight is that nature’s optimal strategy corresponds to generating remarkably deceptive adversarial examples; in an image classification task, this strategy can transform an image of an “8” into a convincing “3.” This work provides a powerful framework for developing more reliable models by understanding and countering worst case data perturbations.
- 1 May 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 74 (3) , 1689-1709
Nash Equilibria, Regularization, and Computation in Optimal Transport-Based Distributionally Robust Optimization
Nature Doesn’t Play Dice, It Plays to Win Decision making under uncertainty can be brittle, often failing when real-world data deviates from training assumptions. This study frames this problem as a game between a decision maker and an adversary, nature, who strategically corrupts the data distribution to create a worst case scenario with the cost of these changes defined by optimal transport theory. The authors establish conditions under which a stable outcome, a Nash equilibrium, exists and provide efficient methods to compute it. A key insight is that nature’s optimal strategy corresponds to generating remarkably deceptive adversarial examples; in an image classification task, this strategy can transform an image of an “8” into a convincing “3.” This work provides a powerful framework for developing more reliable models by understanding and countering worst case data perturbations.
- Open Access
Wasserstein Distributionally Robust Online Learning
We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm is well understood in the offline setting through Wasserstein Distributionally Robust Optimization (DRO), its online extension poses significant challenges in both convergence and computation. In this paper, we address these challenges. First, we formulate the problem as an online saddle-point stochastic game between a decision maker and an adversary selecting worst-case distributions, and propose a general framework that converges to a robust Nash equilibrium coinciding with the solution of the corresponding offline Wasserstein DRO problem. Second, we address the main computational bottleneck, which is the repeated solution of worst-case expectation problems. For the important class of piecewise concave loss functions, we propose a tailored algorithm that exploits problem geometry to achieve substantial speedups over state-of-the-art solvers such as Gurobi. The key insight is a novel connection between the worst-case expectation problem, an inherently infinite-dimensional optimization problem, and a classical and tractable budget allocation problem, which is of independent interest.
Open AccessWasserstein Distributionally Robust Online Learning
We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm is well understood in the offline setting through Wasserstein Distributionally Robust Optimization (DRO), its online extension poses significant challenges in both convergence and computation. In this paper, we address these challenges. First, we formulate the problem as an online saddle-point stochastic game between a decision maker and an adversary selecting worst-case distributions, and propose a general framework that converges to a robust Nash equilibrium coinciding with the solution of the corresponding offline Wasserstein DRO problem. Second, we address the main computational bottleneck, which is the repeated solution of worst-case expectation problems. For the important class of piecewise concave loss functions, we propose a tailored algorithm that exploits problem geometry to achieve substantial speedups over state-of-the-art solvers such as Gurobi. The key insight is a novel connection between the worst-case expectation problem, an inherently infinite-dimensional optimization problem, and a classical and tractable budget allocation problem, which is of independent interest.
- 1 January 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 73 (1) , 251-269
Technical Note—Conic Mixed-Binary Sets: Convex Hull Characterizations and Applications
A Unifying Framework for the Convexification of Mixed-Integer Conic Binary Sets The paper “Conic Mixed-Binary Sets: Convex Hull Characterizations and Applications,” by Fatma Kilinc-Karzan, Simge Kucukyavuz, Dabeen Lee, and Soroosh Shafieezadeh-Abadeh, develops a unifying framework for convexifying mixed-integer conic binary sets. Many applications in machine-learning and operations research give rise to integer programming models with nonlinear structures and binary variables. The paper develops general methods for generating strong valid inequalities that take into account multiple conic constraints at the same time. The authors demonstrate that their framework applies to conic quadratic programming with binary variables, fractional programming, best subset selection, distributionally robust optimization, and sparse approximation of positive semidefinite matrices.
- 1 January 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Operations Research
- Vol. 73 (1) , 251-269
Technical Note—Conic Mixed-Binary Sets: Convex Hull Characterizations and Applications
A Unifying Framework for the Convexification of Mixed-Integer Conic Binary Sets The paper “Conic Mixed-Binary Sets: Convex Hull Characterizations and Applications,” by Fatma Kilinc-Karzan, Simge Kucukyavuz, Dabeen Lee, and Soroosh Shafieezadeh-Abadeh, develops a unifying framework for convexifying mixed-integer conic binary sets. Many applications in machine-learning and operations research give rise to integer programming models with nonlinear structures and binary variables. The paper develops general methods for generating strong valid inequalities that take into account multiple conic constraints at the same time. The authors demonstrate that their framework applies to conic quadratic programming with binary variables, fractional programming, best subset selection, distributionally robust optimization, and sparse approximation of positive semidefinite matrices.
- 20 January 2024
- Published by Springer Nature in Mathematical Programming
- Vol. 208 (1-2) , 533-579
Constrained optimization of rank-one functions with indicator variables
- 20 January 2024
- Published by Springer Nature in Mathematical Programming
- Vol. 208 (1-2) , 533-579
Constrained optimization of rank-one functions with indicator variables
- Open Access
Conic Mixed-Binary Sets: Convex Hull Characterizations and Applications
We consider a general conic mixed-binary set where each homogeneous conic constraint $j$ involves an affine function of independent continuous variables and an epigraph variable associated with a nonnegative function, $f_j$, of common binary variables. Sets of this form naturally arise as substructures in a number of applications including mean-risk optimization, chance-constrained problems, portfolio optimization, lot-sizing and scheduling, fractional programming, variants of the best subset selection problem, a class of sparse semidefinite programs, and distributionally robust chance-constrained programs. We give a convex hull description of this set that relies on simultaneous characterization of the epigraphs of $f_j$'s, which is easy to do when all functions $f_j$'s are submodular. Our result unifies and generalizes an existing result in two important directions. First, it considers \emph{multiple general convex cone} constraints instead of a single second-order cone type constraint. Second, it takes \emph{arbitrary nonnegative functions} instead of a specific submodular function obtained from the square root of an affine function. We close by demonstrating the applicability of our results in the context of a number of problem classes.Open AccessConic Mixed-Binary Sets: Convex Hull Characterizations and Applications
We consider a general conic mixed-binary set where each homogeneous conic constraint $j$ involves an affine function of independent continuous variables and an epigraph variable associated with a nonnegative function, $f_j$, of common binary variables. Sets of this form naturally arise as substructures in a number of applications including mean-risk optimization, chance-constrained problems, portfolio optimization, lot-sizing and scheduling, fractional programming, variants of the best subset selection problem, a class of sparse semidefinite programs, and distributionally robust chance-constrained programs. We give a convex hull description of this set that relies on simultaneous characterization of the epigraphs of $f_j$'s, which is easy to do when all functions $f_j$'s are submodular. Our result unifies and generalizes an existing result in two important directions. First, it considers \emph{multiple general convex cone} constraints instead of a single second-order cone type constraint. Second, it takes \emph{arbitrary nonnegative functions} instead of a specific submodular function obtained from the square root of an affine function. We close by demonstrating the applicability of our results in the context of a number of problem classes. - Open Access
Mean-Covariance Robust Risk Measurement
We introduce a universal framework for mean-covariance robust risk measurement and portfolio optimization. We model uncertainty in terms of the Gelbrich distance on the mean-covariance space, along with prior structural information about the population distribution. Our approach is related to the theory of optimal transport and exhibits superior statistical and computational properties than existing models. We find that, for a large class of risk measures, mean-covariance robust portfolio optimization boils down to the Markowitz model, subject to a regularization term given in closed form. This includes the finance standards, value-at-risk and conditional value-at-risk, and can be solved highly efficiently.
Open AccessMean-Covariance Robust Risk Measurement
We introduce a universal framework for mean-covariance robust risk measurement and portfolio optimization. We model uncertainty in terms of the Gelbrich distance on the mean-covariance space, along with prior structural information about the population distribution. Our approach is related to the theory of optimal transport and exhibits superior statistical and computational properties than existing models. We find that, for a large class of risk measures, mean-covariance robust portfolio optimization boils down to the Markowitz model, subject to a regularization term given in closed form. This includes the finance standards, value-at-risk and conditional value-at-risk, and can be solved highly efficiently.
- Open Access
Constrained Optimization of Rank-One Functions with Indicator Variables
Optimization problems involving minimization of a rank-one convex function over constraints modeling restrictions on the support of the decision variables emerge in various machine learning applications. These problems are often modeled with indicator variables for identifying the support of the continuous variables. In this paper we investigate compact extended formulations for such problems through perspective reformulation techniques. In contrast to the majority of previous work that relies on support function arguments and disjunctive programming techniques to provide convex hull results, we propose a constructive approach that exploits a hidden conic structure induced by perspective functions. To this end, we first establish a convex hull result for a general conic mixed-binary set in which each conic constraint involves a linear function of independent continuous variables and a set of binary variables. We then demonstrate that extended representations of sets associated with epigraphs of rank-one convex functions over constraints modeling indicator relations naturally admit such a conic representation. This enables us to systematically give perspective formulations for the convex hull descriptions of these sets with nonlinear separable or non-separable objective functions, sign constraints on continuous variables, and combinatorial constraints on indicator variables. We illustrate the efficacy of our results on sparse nonnegative logistic regression problems.
Open AccessConstrained Optimization of Rank-One Functions with Indicator Variables
Optimization problems involving minimization of a rank-one convex function over constraints modeling restrictions on the support of the decision variables emerge in various machine learning applications. These problems are often modeled with indicator variables for identifying the support of the continuous variables. In this paper we investigate compact extended formulations for such problems through perspective reformulation techniques. In contrast to the majority of previous work that relies on support function arguments and disjunctive programming techniques to provide convex hull results, we propose a constructive approach that exploits a hidden conic structure induced by perspective functions. To this end, we first establish a convex hull result for a general conic mixed-binary set in which each conic constraint involves a linear function of independent continuous variables and a set of binary variables. We then demonstrate that extended representations of sets associated with epigraphs of rank-one convex functions over constraints modeling indicator relations naturally admit such a conic representation. This enables us to systematically give perspective formulations for the convex hull descriptions of these sets with nonlinear separable or non-separable objective functions, sign constraints on continuous variables, and combinatorial constraints on indicator variables. We illustrate the efficacy of our results on sparse nonnegative logistic regression problems.
- Open Access
Wasserstein Distributionally Robust Estimation in High Dimensions: Performance Analysis and Optimal Hyperparameter Tuning
Wasserstein distributionally robust optimization has recently emerged as a powerful framework for robust estimation, enjoying good out-of-sample performance guarantees, well-understood regularization effects, and computationally tractable reformulations. In such framework, the estimator is obtained by minimizing the worst-case expected loss over all probability distributions which are close, in a Wasserstein sense, to the empirical distribution. In this paper, we propose a Wasserstein distributionally robust estimation framework to estimate an unknown parameter from noisy linear measurements, and we focus on the task of analyzing the squared error performance of such estimators. Our study is carried out in the modern high-dimensional proportional regime, where both the ambient dimension and the number of samples go to infinity at a proportional rate which encodes the under/over-parametrization of the problem. Under an isotropic Gaussian features assumption, we show that the squared error can be recovered as the solution of a convex-concave optimization problem which, surprinsingly, involves at most four scalar variables. Importantly, the precise quantification of the squared error allows to accurately and efficiently compare different ambiguity radii and to understand the effect of the under/over-parametrization on the estimation error. We conclude the paper with a list of exciting research directions enabled by our results.
Open AccessWasserstein Distributionally Robust Estimation in High Dimensions: Performance Analysis and Optimal Hyperparameter Tuning
Wasserstein distributionally robust optimization has recently emerged as a powerful framework for robust estimation, enjoying good out-of-sample performance guarantees, well-understood regularization effects, and computationally tractable reformulations. In such framework, the estimator is obtained by minimizing the worst-case expected loss over all probability distributions which are close, in a Wasserstein sense, to the empirical distribution. In this paper, we propose a Wasserstein distributionally robust estimation framework to estimate an unknown parameter from noisy linear measurements, and we focus on the task of analyzing the squared error performance of such estimators. Our study is carried out in the modern high-dimensional proportional regime, where both the ambient dimension and the number of samples go to infinity at a proportional rate which encodes the under/over-parametrization of the problem. Under an isotropic Gaussian features assumption, we show that the squared error can be recovered as the solution of a convex-concave optimization problem which, surprinsingly, involves at most four scalar variables. Importantly, the precise quantification of the squared error allows to accurately and efficiently compare different ambiguity radii and to understand the effect of the under/over-parametrization on the estimation error. We conclude the paper with a list of exciting research directions enabled by our results.
- Open Access
Outlier-Robust Wasserstein DRO
Distributionally robust optimization (DRO) is an effective approach for data-driven decision-making in the presence of uncertainty. Geometric uncertainty due to sampling or localized perturbations of data points is captured by Wasserstein DRO (WDRO), which seeks to learn a model that performs uniformly well over a Wasserstein ball centered around the observed data distribution. However, WDRO fails to account for non-geometric perturbations such as adversarial outliers, which can greatly distort the Wasserstein distance measurement and impede the learned model. We address this gap by proposing a novel outlier-robust WDRO framework for decision-making under both geometric (Wasserstein) perturbations and non-geometric (total variation (TV)) contamination that allows an $\varepsilon$-fraction of data to be arbitrarily corrupted. We design an uncertainty set using a certain robust Wasserstein ball that accounts for both perturbation types and derive minimax optimal excess risk bounds for this procedure that explicitly capture the Wasserstein and TV risks. We prove a strong duality result that enables tractable convex reformulations and efficient computation of our outlier-robust WDRO problem. When the loss function depends only on low-dimensional features of the data, we eliminate certain dimension dependencies from the risk bounds that are unavoidable in the general setting. Finally, we present experiments validating our theory on standard regression and classification tasks.
Open AccessOutlier-Robust Wasserstein DRO
Distributionally robust optimization (DRO) is an effective approach for data-driven decision-making in the presence of uncertainty. Geometric uncertainty due to sampling or localized perturbations of data points is captured by Wasserstein DRO (WDRO), which seeks to learn a model that performs uniformly well over a Wasserstein ball centered around the observed data distribution. However, WDRO fails to account for non-geometric perturbations such as adversarial outliers, which can greatly distort the Wasserstein distance measurement and impede the learned model. We address this gap by proposing a novel outlier-robust WDRO framework for decision-making under both geometric (Wasserstein) perturbations and non-geometric (total variation (TV)) contamination that allows an $\varepsilon$-fraction of data to be arbitrarily corrupted. We design an uncertainty set using a certain robust Wasserstein ball that accounts for both perturbation types and derive minimax optimal excess risk bounds for this procedure that explicitly capture the Wasserstein and TV risks. We prove a strong duality result that enables tractable convex reformulations and efficient computation of our outlier-robust WDRO problem. When the loss function depends only on low-dimensional features of the data, we eliminate certain dimension dependencies from the risk bounds that are unavoidable in the general setting. Finally, we present experiments validating our theory on standard regression and classification tasks.