conftrace_

asymptotics

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

convergence (2) token (1) almost sure (1) l1 sense (1) overlap (1) adam (1) sgd (1) eigenvalues (1) attention (1) gpt2 (1)

Papers

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD ICML 2025 Consensus Is All You Get: The Role of Attention in Transformers ICML 2025 Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery COLT 2025