Pith. sign in

Since T ≳ L(2) T −1X ℓ=1 d2 log(1/δ)4ℓ ≳d2 log(1/δ)4L(2) T , we get the upper bound ofL(2) T as 2L(2) T ≲ s T d2 log(1/δ)

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

1 Pith paper citing it

fields

stat.ML 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Experimental Design for Semiparametric Bandits

stat.ML · 2025-06-16 · conditional · novelty 7.0

A new design and a sharper analysis of orthogonalized regression yield optimal regret, logarithmic regret under gaps, and the first PAC and best-arm identification guarantees for semiparametric bandits.

citing papers explorer

Showing 1 of 1 citing paper.

  • Experimental Design for Semiparametric Bandits stat.ML · 2025-06-16 · conditional · none · ref 9

    A new design and a sharper analysis of orthogonalized regression yield optimal regret, logarithmic regret under gaps, and the first PAC and best-arm identification guarantees for semiparametric bandits.