16 citations · 17 across the 25 of their papers we have counts for
15 papers · 1 filter
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…
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…
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…
Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts
Klaus-Rudolf Kladny, Maximilian Mordig, Bernhard Schölkopf +1
Sparse Mixture-of-experts (MoE) models enable scalable transformer architectures by activating only a subset of experts per token. Recent evidence suggests that performance improve…
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…
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,…
SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference
Hao Ma, Melis Ilayda Bal, Liang Zhang +4
Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central challenge. While sparse and low-ran…
Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing
Kijung Jeon, Michael Muehlebach, Molei Tao
Sampling from constrained statistical distributions is a fundamental task in various fields including Bayesian statistics, computational chemistry, and statistical physics. This ar…
Zeroth-Order Optimization Finds Flat Minima
Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil +3
Zeroth-order methods are extensively used in machine learning applications where gradients are infeasible or expensive to compute, such as black-box attacks, reinforcement learning…
Partially Observable Reinforcement Learning with Memory Traces
Onno Eberhard, Michael Muehlebach, Claire Vernade
Partially observable environments present a considerable computational challenge in reinforcement learning due to the need to consider long histories. Learning with a finite window…
Quantization-Free Autoregressive Action Transformer
Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach +1
Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. Howe…
The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective
Michael Muehlebach, Zhiyu He, Michael I. Jordan
We study the sample complexity of online reinforcement learning in the general \hzyrev{non-episodic} setting of nonlinear dynamical systems with continuous state and action spaces.…
Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy
Paul Fischer, Hannah Willms, Moritz Schneider +3
Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during…
A Pontryagin Perspective on Reinforcement Learning
Onno Eberhard, Claire Vernade, Michael Muehlebach
Reinforcement learning has traditionally focused on learning state-dependent policies to solve optimal control problems in a closed-loop fashion. In this work, we introduce the par…
Stochastic Online Optimization for Cyber-Physical and Robotic Systems
Hao Ma, Melanie Zeilinger, Michael Muehlebach
We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic syste…