arXiv cs.LG
Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping
중점 잡음 하의 분산 SGD: 최적 수렴 속도와 그래디언트 클리핑의 역할
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.