220 citations · 724 across the 45 of their papers we have counts for
50 papers
Unifying Distributionally Robust Optimization via Optimal Transport Theory
Jose Blanchet, Daniel Kuhn, Jiajin Li +1
In recent years, two prominent paradigms have shaped distributionally robust optimization (DRO), modeling distributional ambiguity through -divergences and Wasserstein distances…
End-to-End Learning for Stochastic Optimization: A Bayesian Perspective
Yves Rychener, Daniel Kuhn, Tobias Sutter
We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation…
Frequency Regulation with Storage: On Losses and Profits
Dirk Lauinger, François Vuille, Daniel Kuhn
Low-carbon societies will need to store vast amounts of electricity to balance intermittent generation from wind and solar energy, for example, through frequency regulation. Here,…
Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets
Mengmeng Li, Daniel Kuhn, Tobias Sutter
We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets, thereby addressing an open challenge in th…
Distributionally Robust Linear Quadratic Control
Bahar Taşkesen, Dan A. Iancu, Çağıl Koçyiğit +1
Linear-Quadratic-Gaussian (LQG) control is a fundamental control paradigm that is studied in various fields such as engineering, computer science, economics, and neuroscience. It i…
PIQP: A Proximal Interior-Point Quadratic Programming Solver
Roland Schwan, Yuning Jiang, Daniel Kuhn +1
This paper presents PIQP, a high-performance toolkit for solving generic sparse quadratic programs (QP). Combining an infeasible Interior Point Method (IPM) with the Proximal Metho…
Nash Equilibria, Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimization
Soroosh Shafiee, Liviu Aolaritei, Florian Dörfler +1
We study optimal transport-based distributionally robust optimization problems where a fictitious adversary, often envisioned as nature, can choose the distribution of the uncertai…
Distributionally Robust Optimal Allocation with Costly Verification
Halil İbrahim Bayrak, Çağıl Koçyiğit, Daniel Kuhn +1
We consider the mechanism design problem of a principal allocating a single good to one of several agents without monetary transfers. Each agent desires the good and uses it to cre…
Stability Verification of Neural Network Controllers using Mixed-Integer Programming
Roland Schwan, Colin N. Jones, Daniel Kuhn
We propose a framework for the stability verification of Mixed-Integer Linear Programming (MILP) representable control policies. This framework compares a fixed candidate policy, w…
On Approximations of Data-Driven Chance Constrained Programs over Wasserstein Balls
Zhi Chen, Daniel Kuhn, Wolfram Wiesemann
Distributionally robust chance constrained programs minimize a deterministic cost function subject to the satisfaction of one or more safety conditions with high probability, given…
Metrizing Fairness
Yves Rychener, Bahar Taskesen, Daniel Kuhn
We study supervised learning problems that have significant effects on individuals from two demographic groups, and we seek predictors that are fair with respect to a group fairnes…
Discrete Optimal Transport with Independent Marginals is #P-Hard
Bahar Taşkesen, Soroosh Shafieezadeh-Abadeh, Daniel Kuhn +1
We study the computational complexity of the optimal transport problem that evaluates the Wasserstein distance between the distributions of two K-dimensional discrete random vector…
Mean-Covariance Robust Risk Measurement
Viet Anh Nguyen, Soroosh Shafiee, Damir Filipović +1
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-covari…
Distributionally Robust Optimization with Markovian Data
Mengmeng Li, Tobias Sutter, Daniel Kuhn
We study a stochastic program where the probability distribution of the uncertain problem parameters is unknown and only indirectly observed via finitely many correlated samples ge…
Robust Generalization despite Distribution Shift via Minimum Discriminating Information
Tobias Sutter, Andreas Krause, Daniel Kuhn
Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to train…
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
Bahar Taskesen, Man-Chung Yue, Jose Blanchet +2
Least squares estimators, when trained on a few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additi…
A Unified Theory of Robust and Distributionally Robust Optimization via the Primal-Worst-Equals-Dual-Best Principle
Jianzhe Zhen, Daniel Kuhn, Wolfram Wiesemann
Robust and distributionally robust optimization are modeling paradigms for decision-making under uncertainty where the uncertain parameters are only known to reside in an uncertain…
Topological Linear System Identification via Moderate Deviations Theory
Wouter Jongeneel, Tobias Sutter, Daniel Kuhn
Two dynamical systems are topologically equivalent when their phase-portraits can be morphed into each other by a homeomorphic coordinate transformation on the state space. The ind…
Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution
Bahar Taskesen, Soroosh Shafieezadeh-Abadeh, 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 c…
Small errors in random zeroth-order optimization are imaginary
Wouter Jongeneel, Man-Chung Yue, Daniel Kuhn
Most zeroth-order optimization algorithms mimic a first-order algorithm but replace the gradient of the objective function with some gradient estimator that can be computed from a…
A Planner-Trader Decomposition for Multi-Market Hydro Scheduling
Kilian Schindler, Napat Rujeerapaiboon, Daniel Kuhn +1
Peak/off-peak spreads on European electricity forward and spot markets are eroding due to the ongoing nuclear phaseout in Germany and the steady growth in photovoltaic capacity. Th…
Efficient Learning of a Linear Dynamical System with Stability Guarantees
Wouter Jongeneel, Tobias Sutter, Daniel Kuhn
We propose a principled method for projecting an arbitrary square matrix to the non-convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we…
A proof of the Erdős-Faber-Lovász conjecture
Dong Yeap Kang, Tom Kelly, Daniela Kühn +2
The Erdős-Faber-Lovász conjecture (posed in 1972) states that the chromatic index of any linear hypergraph on vertices is at most . In this paper, we prove this conjecture f…
A Statistical Test for Probabilistic Fairness
Bahar Taskesen, Jose Blanchet, Daniel Kuhn +1
Algorithms are now routinely used to make consequential decisions that affect human lives. Examples include college admissions, medical interventions or law enforcement. While algo…