Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning
Yanyi Li, Wendao Wu, Haihan Zhang +6
Tracking changing comparators is a central problem in online learning. For exp-concave losses, previous work established the dependence on the horizon and Eu…
cs.LG2026
PRAC: Principal-Random Subspace for LLM Activation Compression and Memory-Efficient Training
Yanyi Li, Yimu Zhang, Cong Fang
Activations have become the primary memory bottleneck in large-batch LLM training. However, existing compression methods fail to exploit the spectral structure of activations, resu…