ArXiv TLDR

Lijun Zhang

2 papers · Latest:

Machine Learning

When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds

This paper theoretically explains when and why SignSGD outperforms SGD, showing it reduces complexity by a factor of 'd' under sparse noise.

2605.06615
Machine Learning

Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications

This paper introduces optimal algorithms and lower bounds for distributed online convex optimization with compressed communication, reducing communication costs.

2604.09276

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.