Soroosh Shafiee

Soroosh Shafiee

Auto-generated profile, based on publicly available information

Soroosh Shafiee

Operations Research and Information Engineering, Cornell University, Ithaca, New York 14850

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2023 in Mathematics of Operations Research
Verified
Journal Article
Closed access
VNViet Anh Nguyen
Viet Anh Nguyen
SSSoroosh Shafieezadeh-Abadeh
Soroosh Shafieezadeh-Abadeh
DKDaniel Kuhn
Daniel Kuhn
PEPeyman Mohajerin Esfahani
Peyman Mohajerin Esfahani
We introduce a distributionally robust minimium mean square error estimation model with a Wasserstein ambiguity set to recover an unknown signal from a noisy observation. The proposed model can be viewed as a zero-sum game between a statistician choosing an estimator—that is, a measurable function of the observation—and a fictitious adversary choosing a prior—that is, a pair of signal and noise distributions ranging over independent Wasserstein balls—with the goal to minimize and maximize the expected squared estimation error, respectively. We show that, if the Wasserstein balls are centered at normal distributions, then the zero-sum game admits a Nash equilibrium, by which the players’ optimal strategies are given by an affine estimator and a normal prior, respectively. We further prove that this Nash equilibrium can be computed by solving a tractable convex program. Finally, we develop a Frank–Wolfe algorithm that can solve this convex program orders of magnitude faster than state-of-the-art general-purpose solvers. We show that this algorithm enjoys a linear convergence rate and that its direction-finding subproblems can be solved in quasi-closed form. Funding: This research was supported by the Swiss National Science Foundation [Grants BSCGI0_ 157733 and 51NF40_180545], an Early Postdoc.Mobility Fellowship [Grant P2ELP2_195149], and the European Research Council [Grant TRUST-949796].

25 July 2022 in Mathematical Programming
Verified
Journal Article
Open access
PDF file
BTBahar Taşkesen
Bahar Taşkesen
SSSoroosh Shafieezadeh-Abadeh
Soroosh Shafieezadeh-Abadeh
DKDaniel Kuhn
Daniel Kuhn
Semi-discrete optimal transport problems, which evaluate the Wasserstein distance between a discrete and a generic (possibly non-discrete) probability measure, are believed to be computationally hard. Even though such problems are ubiquitous in statistics, machine learning and computer vision, however, this perception has not yet received a theoretical justification. To fill this gap, we prove that computing the Wasserstein distance between a discrete probability measure supported on two points and the Lebesgue measure on the standard hypercube is already $$\#$$# P-hard. This insight prompts us to seekapproximatesolutions for semi-discrete optimal transport problems. We thus perturb the underlying transportation cost with an additive disturbance governed by an ambiguous probability distribution, and we introduce a distributionally robustdualoptimal transport problem whose objective function is smoothed with the most adverse disturbance distributions from within a given ambiguity set. We further show that smoothing the dual objective function is equivalent to regularizing the primal objective function, and we identify several ambiguity sets that give rise to several known and new regularization schemes. As a byproduct, we discover an intimate relation between semi-discrete optimal transport problems and discrete choice models traditionally studied in psychology and economics. To solve the regularized optimal transport problems efficiently, we use a stochastic gradient descent algorithm with imprecise stochastic gradient oracles. A new convergence analysis reveals that this algorithm improves the best known convergence guarantee for semi-discrete optimal transport problems with entropic regularizers.

1 January 2025 in Operations Research
Verified
Journal Article
Closed access
FKFatma Kılınç-Karzan
Fatma Kılınç-Karzan
SKSimge Küçükyavuz
Simge Küçükyavuz
DLDabeen Lee
Dabeen Lee
SSSoroosh Shafieezadeh-Abadeh
Soroosh Shafieezadeh-Abadeh
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 in Mathematical Programming
Verified
Journal Article
Closed access
PDF file
SSSoroosh Shafiee
Soroosh Shafiee
FKFatma Kılınç-Karzan
Fatma Kılınç-Karzan

15 January 2026 in Mathematical Programming
Verified
Journal Article
Closed access
PDF file
LALiviu Aolaritei
Liviu Aolaritei
SSSoroosh Shafiee
Soroosh Shafiee
FDFlorian Dörfler
Florian Dörfler

1 May 2026 in Operations Research
Verified
Journal Article
Closed access
SSSoroosh Shafiee
Soroosh Shafiee
LALiviu Aolaritei
Liviu Aolaritei
FDFlorian Dörfler
Florian Dörfler
DKDaniel Kuhn
Daniel Kuhn
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.