activity
20242026
collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2026

Foundations of Reinforcement Learning and Control:Connections and New Perspectives

Claire Vernade, Onno Eberhard, Martha White +4

Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields…

cs.LG2026

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

Kijung Jeon, Michael Muehlebach, Molei Tao

Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generati…

cs.LG2026

Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning

Yike Zhao, Onno Eberhard, Malek Khammassi +2

The family of linear recurrent neural networks has shown strong performance as recurrent memory units in partially observable reinforcement learning. We provide a theoretical justi…

cs.LG2026

Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts

Klaus-Rudolf Kladny, Maximilian Mordig, Bernhard Schölkopf +1

Mixture-of-experts (MoE) models enable scalable transformer architectures by activating only a subset of experts per token. Recent evidence suggests that performance improves with…

cs.LG2026

Commit to the Bit: Reactive Reinforcement Learning Done Right

Onno Eberhard, Claire Vernade, Michael Muehlebach

Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either par…

cs.LG2026

Zeroth-Order Optimization at the Edge of Stability

Minhak Song, Liang Zhang, Bingcong Li +3

Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models,…