76 citations · 755 across the 50 of their papers we have counts for
4 papers · 1 filter
PAC-Bayesian Offline Contextual Bandits With Guarantees
Otmane Sakhi, Pierre Alquier, Nicolas Chopin
This paper introduces a new principled approach for off-policy learning in contextual bandits. Unlike previous work, our approach does not derive learning principles from intractab…
Variance-Aware Estimation of Kernel Mean Embedding
Geoffrey Wolfer, Pierre Alquier
An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension…
Optimal quasi-Bayesian reduced rank regression with incomplete response
The Tien Mai, Pierre Alquier
The aim of reduced rank regression is to connect multiple response variables to multiple predictors. This model is very popular, especially in biostatistics where multiple measurem…
Concentration of discrepancy-based approximate Bayesian computation via Rademacher complexity
Sirio Legramanti, Daniele Durante, Pierre Alquier
There has been increasing interest on summary-free solutions for approximate Bayesian computation (ABC) which replace distances among summaries with discrepancies between the empir…