A general condition for fast rates in multi-group learning
arXiv:2610.26198v1 Announce Type: new Abstract: In multi-group learning, a single predictor must control its excess risk simultaneously over overlapping groups. Tosh and Hsu (2022) obtained $1/\sqrt{n}$ slow rates via a reduction to online learning with sleeping experts, and $1/n$ rates only under…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv stat.ML
A general condition for fast rates in multi-group learning