Pierre Alquier — accepted AI-conference papers

2026

Position: Agentic AI systems should be making Bayes-consistent decisions

Theodore Papamarkou, Pierre Alquier, Matthias Bauer, Wray Buntine, Andrew Davison, Gintare Karolina Dziugaite +24

ICML 2026poster

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for L…

Cited by 0 Source ↗Scholar ↗

2024

Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning

Otmane Sakhi, Imad Aouali, Pierre Alquier, Nicolas Chopin

NeurIPS 2024spotlight

This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies. Motivated by critical applications, we move beyond point est…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

PAC-Bayesian Offline Contextual Bandits With Guarantees

Otmane Sakhi, Pierre Alquier, Nicolas Chopin

ICML 2023poster

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 intractable or loose bounds. We analyse the problem through the PAC-Bayesian lens, interpreting policies as mixtures of decision…

Cited by 19 Source ↗PDF ↗Scholar ↗

2021

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

Thang Doan, Mehdi Abbana Bennani, Bogdan Mazoure, Guillaume Rabusseau, Pierre Alquier

AISTATS 2021poster

Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime. Although major advances have been made in the field, one recurring problem which remains unsolved is that of Catastrophic Forgetting (CF). While the issue has been extensiv…

Cited by 100 Source ↗PDF ↗code ↗Scholar ↗

2021

Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions

Pierre Alquier

ICML 2021spotlight

We tackle the problem of online optimization with a general, possibly unbounded, loss function. It is well known that when the loss is bounded, the exponentially weighted aggregation strategy (EWA) leads to a regret in $\sqrt{T}$ after $T$ steps. In this paper, we study a generalized aggregation str…

Cited by 24 Source ↗PDF ↗Scholar ↗

2017

Regret Bounds for Lifelong Learning

Pierre Alquier, The Tien Mai, Massimiliano Pontil

AISTATS 2017poster

We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the within-task algorithm, thereby transferring i…

Cited by 61 Source ↗PDF ↗Scholar ↗