Work

Parameter-Free Interval-Dynamic Regret under Heavy-Tailed Noise

Year: 2026
Type: preprint
Abstract: We study online convex optimization with one unbiased stochastic subgradient per round and an unknown finite conditional $p$th noise moment, $1
Language: English
Open Access status: green
OpenAlex ID: W7220388789
Cites: 3
Cited by:
Related to: 10