2 papers
cs.LG2024
On the Convergence Analysis of Over-Parameterized Variational Autoencoders: A Neural Tangent Kernel Perspective
Li Wang, Wei Huang
Variational Auto-Encoders (VAEs) have emerged as powerful probabilistic models for generative tasks. However, their convergence properties have not been rigorously proven. The chal…
cs.LG2021
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis
Miao Zhang, Wei Huang, Li Wang
The recently proposed training-free NAS methods abandon the training phase and design various zero-cost proxies as scores to identify excellent architectures, arousing extreme comp…