Agnostic Smoothed Online Regression with Adversarial Responses
arXiv:2609.32478v1 Announce Type: new Abstract: We study smoothed online prediction with bounded adversarial responses. This widely studied framework bridges i.i.d. sampling and adversarial covariate selection through a smoothness parameter $\textsf{C}_{\textsf{cov}}$, which bounds conditional cova…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-29 04:00 · arXiv stat.ML
Agnostic Smoothed Online Regression with Adversarial Responses