Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate
arXiv:2610.13442v1 Announce Type: new Abstract: Compression schemes provide a general framework for deriving data-dependent risk bounds for learning algorithms. For learning rules based on preferent compression, existing results upper-bound the risk in terms of a sample-dependent complexity $\bolds…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv stat.ML
Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate