Albert Thomas — accepted AI-conference papers

2025

AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting

Abdelhakim Benechehab, Vasilii Feofanov, Giuseppe Paolo, Albert Thomas, Maurizio Filippone, Balázs Kégl

ICML 2025poster

Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying uncertainty in predictions. This study aims to tackle these crit…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Zero-shot Model-based Reinforcement Learning using Large Language Models

Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat, Oussama Zekri, Albert Thomas, Giuseppe Paolo +3

ICLR 2025poster

The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcement learning, while LLMs have been extensively used in text-based environments, their integration with continuous state s…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

An $\alpha$-No-Regret Algorithm For Graphical Bilinear Bandits

Geovani Rizk, Igor Colin, Albert Thomas, Rida Laraki, Yann Chevaleyre

NeurIPS 2022accept

We propose the first regret-based approach to the \emph{Graphical Bilinear Bandits} problem, where $n$ agents in a graph play a stochastic bilinear bandit game with each of their neighbors. This setting reveals a combinatorial NP-hard problem that prevents the use of any existing regret-based algori…

Cited by 0 Source ↗PDF ↗Scholar ↗

2021

Best Arm Identification in Graphical Bilinear Bandits

Geovani Rizk, Albert Thomas, Igor Colin, Rida Laraki, Yann Chevaleyre

ICML 2021spotlight

We introduce a new graphical bilinear bandit problem where a learner (or a \emph{central entity}) allocates arms to the nodes of a graph and observes for each edge a noisy bilinear reward representing the interaction between the two end nodes. We study the best arm identification problem in which th…

Cited by 7 Source ↗PDF ↗Scholar ↗

2021

Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?

Balázs Kégl, Gabriel Hurtado, Albert Thomas

ICLR 2021poster

We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models using a fixed (random shooting) control agent. We find that on an environment that requires multimodal posterior predictives, mixture density nets outperform all other models by a…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2017

Anomaly Detection in Extreme Regions via Empirical MV-sets on the Sphere

Albert Thomas, Stéphan Clemencon, Alexandre Gramfort, Anne Sabourin

AISTATS 2017poster

Extreme regions in the feature space are of particular concern for anomaly detection: anomalies are likely to be located in the tails, whereas data scarcity in such regions makes it difficult to distinguish between large normal instances and anomalies. This paper presents an unsupervised algorithm f…

Cited by 23 Source ↗PDF ↗Scholar ↗