Scalable Optimization in the Modular Normby Tim Large, Yang Liu, Minyoung Huh, Hyojin Bahng, Phillip…
Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distributionby Johannes…
SimPO: Simple Preference Optimization with a Reference-Free Rewardby Yu Meng, Mengzhou Xia, Danqi ChenFirst submitted…
AnyLoss: Transforming Classification Metrics into Loss Functionsby Doheon Han, Nuno Moniz, Nitesh V ChawlaFirst submitted…
Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Trainingby Tehila Dahan, Kfir Y. LevyFirst submitted to…
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimensionby…
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Modelsby Jingyi Chen, Ju-Seung Byun,…
Heteroscedastic Preferential Bayesian Optimization with Informative Noise Distributionsby Marshal Arijona Sinaga, Julien Martinelli, Vikas Garg,…
Efficiency for Free: Ideal Data Are Transportable Representationsby Peng Sun, Yi Jiang, Tao LinFirst submitted…
A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detectionby Marco Rando, Luca…