Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery

no code implementations • 24 Feb 2024 • Yassir Jedra, William Réveillard, Stefan Stojanovic, Alexandre Proutiere

For policy evaluation and best policy identification, we show that our algorithms are nearly minimax optimal.

Multi-Armed Bandits

Tight bounds for maximum $\ell_1$-margin classifiers

no code implementations • 7 Dec 2022 • Stefan Stojanovic, Konstantin Donhauser, Fanny Yang

In particular, for the noiseless setting, we prove tight upper and lower bounds for the prediction error that match existing rates of order $\frac{\|w^*\|_1^{2/3}}{n^{1/3}}$ for general ground truths.

Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias

1 code implementation • 7 Mar 2022 • Konstantin Donhauser, Nicolo Ruggeri, Stefan Stojanovic, Fanny Yang

Good generalization performance on high-dimensional data crucially hinges on a simple structure of the ground truth and a corresponding strong inductive bias of the estimator.

Inductive Bias valid