Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPsby Kihyuk Hong, Woojin…
Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Trainingby Xianzhi Du, Tom Gunter, Xiang Kong,…
Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networksby T. Konstantin Rusch, Nathan…
ElastoGen: 4D Generative Elastodynamicsby Yutao Feng, Yintong Shang, Xiang Feng, Lei Lan, Shandian Zhe, Tianjia…
Model-Agnostic Utility-Preserving Biometric Information Anonymizationby Chun-Fu Chen, Bill Moriarty, Shaohan Hu, Sean Moran, Marco Pistoia,…
A classification model based on a population of hypergraphsby Samuel Barton, Adelle Coster, Diane Donovan,…
Direct Preference Optimization With Unobserved Preference Heterogeneityby Keertana Chidambaram, Karthik Vinay Seetharaman, Vasilis SyrgkanisFirst submitted…
4+3 Phases of Compute-Optimal Neural Scaling Lawsby Elliot Paquette, Courtney Paquette, Lechao Xiao, Jeffrey PenningtonFirst…
Distributed Harmonization: Federated Clustered Batch Effect Adjustment and Generalizationby Bao Hoang, Yijiang Pang, Siqi Liang,…
A Survey of Distributed Learning in Cloud, Mobile, and Edge Settingsby Madison Threadgill, Andreas GerstlauerFirst…