Pith. sign in

Optimal PAC bounds without uniform convergence

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

ACCEPT 1

representative citing papers

Optimistic Rates for Multiclass PAC Learning

cs.LG · 2026-08-11 · accept · novelty 8.0

For multiclass PAC learning, the optimal excess risk at any fixed oracle error L* equals the square root of L* times the Natarajan dimension over n, plus the realizable DS-dimension rate, with matching upper and lower bounds.

citing papers explorer

Showing 1 of 1 citing paper.

  • Optimistic Rates for Multiclass PAC Learning cs.LG · 2026-08-11 · accept · partial · ref 1

    For multiclass PAC learning, the optimal excess risk at any fixed oracle error L* equals the square root of L* times the Natarajan dimension over n, plus the realizable DS-dimension rate, with matching upper and lower bounds.