← Search

Flore Sentenac

5 accepted papers

2024

Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits

NeurIPS 2024poster

We prove that single-parameter natural exponential families with subexponential tails are self-concordant with polynomial-sized parameters. For subgaussian natural exponential families we establish an exact characterization of the growth rate of the self-concordance parameter. Applying these finding…

Cited by 1SourcePDFScholar
2023

On Preemption and Learning in Stochastic Scheduling

ICML 2023poster

We study single-machine scheduling of jobs, each belonging to a job type that determines its duration distribution. We start by analyzing the scenario where the type characteristics are known and then move to two learning scenarios where the types are unknown: non-preemptive problems, where each sta…

2021

Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm

NeurIPS 2021poster

Motivated by sequential budgeted allocation problems, we investigate online matching problems where connections between vertices are not i.i.d., but they have fixed degree distributions -- the so-called configuration model. We estimate the competitive ratio of the simplest algorithm, GREEDY, by app…

Cited by 6SourcePDFScholar
2021

Pure Exploration and Regret Minimization in Matching Bandits

ICML 2021spotlight

Finding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentially. We prove that it is possible to leverage a rank-1 assumption on the adjacency matrix to reduce the sample complexit…

Cited by 11SourcePDFScholar