1 code implementation • NeurIPS 2023 • Po-An Wang, Ruo-Chun Tzeng, Alexandre Proutiere
In particular, we present \sred (Continuous Rejects), a truly adaptive algorithm that can reject arms in {\it any} round based on the observed empirical gaps between the rewards of various arms.
no code implementations • 23 Aug 2023 • Po-An Wang, Kaito Ariu, Alexandre Proutiere
For the problem with two arms, also known as the A/B testing problem, we prove that there is no algorithm that (i) performs as well as the algorithm sampling each arm equally (referred to as the {\it uniform sampling} algorithm) in all instances, and that (ii) strictly outperforms uniform sampling on at least one instance.
no code implementations • 16 Feb 2022 • Ruo-Chun Tzeng, Po-An Wang, Florian Adriaens, Aristides Gionis, Chi-Jen Lu
We present a novel analysis of the randomized SVD algorithm of \citet{halko2011finding} and derive tight bounds in many cases of interest.
no code implementations • NeurIPS 2021 • Po-An Wang, Ruo-Chun Tzeng, Alexandre Proutiere
For this problem, instance-specific lower bounds on the expected sample complexity reveal the optimal proportions of arm draws an Oracle algorithm would apply.
no code implementations • 28 Sep 2019 • Alexandre Proutiere, Po-An Wang
We present DPE (Decentralized Parsimonious Exploration), a decentralized algorithm that achieves the same regret as that obtained by an optimal centralized algorithm.
no code implementations • ICML 2017 • Po-An Wang, Chi-Jen Lu
Tensor decomposition is an important problem with many applications across several disciplines, and a popular approach for this problem is the tensor power method.