2024 "spectral analysis" Papers
4 papers found
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
Behrad Moniri, Donghwan Lee, Hamed Hassani et al.
ICML 2024posterarXiv:2310.07891
Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
Zenan Ling, Longbo Li, Zhanbo Feng et al.
ICML 2024posterarXiv:2402.02697
Recovering the Pre-Fine-Tuning Weights of Generative Models
Eliahu Horwitz, Jonathan Kahana, Yedid Hoshen
ICML 2024posterarXiv:2402.10208
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
Vithursan Thangarasa, Shreyas Saxena, Abhay Gupta et al.
ICML 2024posterarXiv:2303.11525