Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transportby Jaemoo Choi, Jaewoong Choi,…
Implicit Diffusion: Efficient Optimization through Stochastic Samplingby Pierre Marion, Anna Korba, Peter Bartlett, Mathieu Blondel,…
Principled Preferential Bayesian Optimizationby Wenjie Xu, Wenbin Wang, Yuning Jiang, Bratislav Svetozarevic, Colin N. JonesFirst…
Noise Contrastive Alignment of Language Models with Explicit Rewardsby Huayu Chen, Guande He, Lifan Yuan,…
DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learningby Weikang Wan, Ziyu Wang, Yufei…
Universal Neural Functionalsby Allan Zhou, Chelsea Finn, James HarrisonFirst submitted to arxiv on: 7 Feb…
Feature learning as alignment: a structural property of gradient descent in non-linear neural networksby Daniel…
Do Transformer World Models Give Better Policy Gradients?by Michel Ma, Tianwei Ni, Clement Gehring, Pierluca…
Online Learning Approach for Survival Analysisby Camila Fernandez, Pierre Gaillard, Joseph de Vilmarest, Olivier WintenbergerFirst…
FlowPG: Action-constrained Policy Gradient with Normalizing Flowsby Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat KumarFirst submitted…