3 papers
cs.LG2026
An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension
Guangjian Zhang, Zhengyi Yang, Xiaoyang Wang
We study the squared-loss sample compression question posed by Attias, Hanneke, Kontorovich, and Sadigurschi in their ICML 2024 paper. For every nonempty class $\mathcal{F}\subsete…
cs.LG2026
Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression
Guangjian Zhang
We resolve the threshold part of Question 4 of the COLT 2025 open problem "Data Selection for Regression Tasks" of Hanneke, Moran, Shlimovich and Yehudayoff. We study vector-valued…
cs.LG2026
Exact Risk Ratios for Weighted Data Selection in Linear Regression
Guangjian Zhang
How much data must a fixed learner retain? Hanneke, Moran, Shlimovich and Yehudayoff (COLT 2025) posed this question for linear regression with the minimum-norm empirical risk mini…