no code implementations • 24 Jun 2023 • 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 performance.
no code implementations • 14 Sep 2021 • Amine Bennouna, Bart P. G. Van Parys
We define first a sensible yard stick with which to measure the quality of any data-driven formulation and subsequently seek to find an optimal such formulation.
no code implementations • 8 Feb 2021 • 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.
3 code implementations • 9 Nov 2020 • Shuvomoy Das Gupta, Bartolomeo Stellato, Bart P. G. Van Parys
In this paper, we present the nonconvex exterior-point optimization solver NExOS -- a first-order algorithm tailored to sparse and low-rank optimization problems.
Optimization and Control
1 code implementation • 14 Jul 2020 • Bart P. G. Van Parys, Negin Golrezaei
We propose a novel learning algorithm that we call "DUSA" whose regret matches the information-theoretic regret lower bound up to a constant factor and can handle a wide range of structural information.