Co-occurring keywords · papers mentioning both
Papers
On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
ICML 2025
Characterizing ResNet’s Universal Approximation Capability
ICML 2024
Optimal approximation of continuous functions by very deep ReLU networks
COLT 2018
Local Minimax Complexity of Stochastic Convex Optimization
NeurIPS 2016