73 citations · 218 across the 15 of their papers we have counts for
19 papers
A stochastic subgradient method with optimal failure exponent
Bart P. G. van Parys
Fix a target accuracy , a gradient-noise level , and a horizon . We wish to design algorithms which minimize the probability of observing a suboptimality gap whi…
Large and Moderate Deviations for Conservative Tail-Index Estimation
Martijn Gösgens, Bart P. G. van Parys, Bert Zwart
To design systems that are protected against events much rarer than the observational record, extreme-value methods are needed to extrapolate distribution tails. Tail-index estimat…
Globalized Adversarial Regret Optimization: Robust Decisions with Uncalibrated Predictions
Jannis Kurtz, Bart P. G. van Parys
Optimization problems routinely depend on uncertain parameters that must be predicted before a decision is made. Classical robust and regret formulations are designed to handle err…
Subgradient Methods for Nonsmooth Convex Functions with Adversarial Errors
Martijn Gösgens, Bart P. G. Van Parys
We consider minimizing nonsmooth convex functions with bounded subgradients. However, instead of directly observing a subgradient at every step , we assume th…
Smoothed -Divergence Distributionally Robust Optimization
Zhenyuan Liu, Bart P. G. Van Parys, Henry Lam
In data-driven optimization, sample average approximation (SAA) is known to suffer from the so-called optimizer's curse that causes an over-optimistic evaluation of the solution pe…
Certified Robust Neural Networks: Generalization and Corruption Resistance
Amine Bennouna, Ryan Lucas, Bart Van Parys
Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibilit…
Mean Robust Optimization
Irina Wang, Cole Becker, Bart Van Parys +1
Robust optimization is a tractable and expressive technique for decision-making under uncertainty, but it can lead to overly conservative decisions when pessimistic assumptions are…
Holistic Robust Data-Driven Decisions
Amine Bennouna, Bart Van Parys, Ryan Lucas
The design of data-driven formulations for machine learning and decision-making with good out-of-sample performance is a key challenge. The observation that good in-sample performa…
Learning and Decision-Making with Data: Optimal Formulations and Phase Transitions
Amine Bennouna, Bart P. G. Van Parys
We study the problem of designing optimal learning and decision-making formulations when only historical data is available. Prior work typically commits to a particular class of da…
Efficient Data-Driven Optimization with Noisy Data
Bart P. G. Van Parys
Classical Kullback-Leibler or entropic distances are known to enjoy certain desirable statistical properties in the context of decision-making with noiseless data. However, in most…
A Pareto Dominance Principle for Data-Driven Optimization
Tobias Sutter, Bart P. G. Van Parys, Daniel Kuhn
We propose a statistically optimal approach to construct data-driven decisions for stochastic optimization problems. Fundamentally, a data-driven decision is simply a function that…
Optimal Learning for Structured Bandits
Bart P. G. Van Parys, Negin Golrezaei
We study structured multi-armed bandits, which is the problem of online decision-making under uncertainty in the presence of structural information. In this problem, the decision-m…
Sparse Regression: Scalable algorithms and empirical performance
Dimitris Bertsimas, Jean Pauphilet, Bart Van Parys
In this paper, we review state-of-the-art methods for feature selection in statistics with an application-oriented eye. Indeed, sparsity is a valuable property and the profusion of…
Bootstrap Robust Prescriptive Analytics
Dimitris Bertsimas, Bart Van Parys
We address the problem of prescribing an optimal decision in a framework where the cost function depends on uncertain problem parameters that need to be learned from data. Earlier…
Sparse Classification: a scalable discrete optimization perspective
Dimitris Bertsimas, Jean Pauphilet, Bart Van Parys
We formulate the sparse classification problem of samples with features as a binary convex optimization problem and propose a cutting-plane algorithm to solve it exactly. F…
Sparse Hierarchical Regression with Polynomials
Dimitris Bertsimas, Bart Van Parys
We present a novel method for exact hierarchical sparse polynomial regression. Our regressor is that degree polynomial which depends on at most inputs, counting at most $\e…
Sparse High-Dimensional Regression: Exact Scalable Algorithms and Phase Transitions
Dimitris Bertsimas, Bart Van Parys
We present a novel binary convex reformulation of the sparse regression problem that constitutes a new duality perspective. We devise a new cutting plane method and provide evidenc…
Multivariate Chebyshev Inequality with Estimated Mean and Variance
Bartolomeo Stellato, Bart Van Parys, Paul J. Goulart
A variant of the well-known Chebyshev inequality for scalar random variables can be formulated in the case where the mean and variance are estimated from samples. In this paper we…
Security Constrained Optimal Power Flow with Distributionally Robust Chance Constraints
Line Roald, Frauke Oldewurtel, Bart Van Parys +1
The growing amount of fluctuating renewable infeeds and market liberalization increases uncertainty in power system operation. To capture the influence of fluctuations in operation…