3 papers
stat.ML2026
Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach
Sebastian Reboul, Hélène Halconruy
We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding.…
cs.LG2026
Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training
Hamza Cherkaoui, Hélène Halconruy, Antonio Ocello
Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distribut…
stat.ML2026
When to Transfer: Adaptive Source Selection for Positive Transfer in Linear Models
Hamza Cherkaoui, Hélène Halconruy, Yohan Petetin
In many business settings, task-specific labeled data are scarce or costly to obtain, limiting supervised learning on a target task. A classical response is transfer learning (TL).…