A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilitiesby…
On the Crucial Role of Initialization for Matrix Factorizationby Bingcong Li, Liang Zhang, Aryan Mokhtari,…
Rethinking Positive Pairs in Contrastive Learningby Jiantao Wu, Shentong Mo, Zhenhua Feng, Sara Atito, Josef…
Implicit Regularization for Tubal Tensor Factorizations via Gradient Descentby Santhosh Karnik, Anna Veselovska, Mark Iwen,…
Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Modelby Xinyu Yuan, Yan Qiao, Pei Zhao,…
IPO: Interpretable Prompt Optimization for Vision-Language Modelsby Yingjun Du, Wenfang Sun, Cees G. M. SnoekFirst…
Privacy for Free in the Over-Parameterized Regimeby Simone Bombari, Marco MondelliFirst submitted to arxiv on:…
Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selectionby Addison Kristanto Julistiono, Davoud Ataee Tarzanagh,…
Neuro-Symbolic Traders: Assessing the Wisdom of AI Crowds in Marketsby Namid R. Stillman, Rory BaggottFirst…
A Mirror Descent Perspective of Smoothed Sign Descentby Shuyang Wang, Diego KlabjanFirst submitted to arxiv…