Pith. sign in

Title resolution pending

Let δ ∈ (0, 1), ρ ≥ 12K T, η = min n ρ 40H ln T ln(H/δ) , p K/PT t=1 ℓ⊤ t x∗ ln(1/δ) o , where H := ln (⌈ln(T )⌉⌈3 ln(T )⌉/δ) · 2025

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

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Data-Dependent Regret Bounds for Constrained MABs

cs.LG · 2025-05-26 · conditional · novelty 7.0

Constrained bandit algorithms whose regret depends on the realized losses, split into a safety term and a bandit-learning term, with a matching lower bound.

citing papers explorer

Showing 1 of 1 citing paper.

  • Data-Dependent Regret Bounds for Constrained MABs cs.LG · 2025-05-26 · conditional · none · ref 4

    Constrained bandit algorithms whose regret depends on the realized losses, split into a safety term and a bandit-learning term, with a matching lower bound.