← 研踪 PaperTrailarXiv:2609.32478 · v2
Agnostic Smoothed Online Regression with Adversarial Responses
首次提交 2026-09-26 19:17
版本更新 2026-11-19 19:34
雷达观测 2026-11-20 16:53
摘要
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 , which bounds conditional covariate densities relative to a fixed, unknown base measure. We propose Hedge-Cover, an information-theoretic algorithm that achieves sublinear regret for function classes with bounded pseudo-dimension. The algorithm aggregates a carefully constructed family of experts using Hedge, with a prior that links regret to the number of disagreements between a consistent selector and a target function. We bound this number by exploiting covariate smoothness. This answers an open problem posed in \cite{blanchard2025agnostic} on the minimax optimal adaptive regret of the smoothed online regression problem. We establish a matching lower bound for the class of linear predictors. The main intricacy of the lower bound lies in explicitly constructing a challenging sequential covariate distribution supported on mutually orthogonal hyperplanes. This construction may be of independent technical interest. Finally, we revisit the well-specified setting and quantify the effect of response noise. For conditionally -subGaussian responses, we extend the existing lower bound under realizable responses by showing that the minimax expected regret is for a function class of VC dimension . A corresponding upper bound for ERM matches this dependence on .
作者备注:32 pages, 1 table
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 19:34 · 最新观测版本
Agnostic Smoothed Online Regression with Adversarial Responses
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 , which bounds conditional covariate densities relative to a fixed, unknown base measure. We propose Hedge-Cover, an information-theoretic algorithm that achieves sublinear regret for function classes with bounded pseudo-dimension. The algorithm aggregates a carefully constructed family of experts using Hedge, with a prior that links regret to the number of disagreements between a consistent selector and a target function. We bound this number by exploiting covariate smoothness. This answers an open problem posed in \cite{blanchard2025agnostic} on the minimax optimal adaptive regret of the smoothed online regression problem. We establish a matching lower bound for the class of linear predictors. The main intricacy of the lower bound lies in explicitly constructing a challenging sequential covariate distribution supported on mutually orthogonal hyperplanes. This construction may be of independent technical interest. Finally, we revisit the well-specified setting and quantify the effect of response noise. For conditionally -subGaussian responses, we extend the existing lower bound under realizable responses by showing that the minimax expected regret is for a function class of VC dimension . A corresponding upper bound for ERM matches this dependence on .
查看此版本解读 →查看此版本原文 ↗