pith. sign in

Title resolution pending

With probability at least 1−O (TnL 2)· exp(−Ω(mω2/3L)) over the random initialization, for allt∈ [T ],i∈ [n], θ satisfying∥θ− θ0∥2≤ω with ω≤O (L−9/2[logm]−3), it holds uniformly that (1),|f(xt,i, θ)|≤O (1) · 2019

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

2023 1

verdicts

UNVERDICTED 1

representative citing papers

Neural Exploitation and Exploration of Contextual Bandits

cs.LG · 2023-05-05 · unverdicted · novelty 6.0

EE-Net is a contextual bandit algorithm that pairs an exploitation neural net with a separate exploration neural net and proves an instance-dependent Õ(√T) regret bound while beating linear and neural baselines on real data.

citing papers explorer

Showing 1 of 1 citing paper.

  • Neural Exploitation and Exploration of Contextual Bandits cs.LG · 2023-05-05 · unverdicted · none · ref 13

    EE-Net is a contextual bandit algorithm that pairs an exploitation neural net with a separate exploration neural net and proves an instance-dependent Õ(√T) regret bound while beating linear and neural baselines on real data.