Pith. sign in

REVIEW 4 cited by

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.01780 v1 pith:MYYVSUR4 submitted 2020-12-03 cs.LG stat.ML

Neural Contextual Bandits with Deep Representation and Shallow Exploration

Pan Xu , Zheng Wen , Handong Zhao , Quanquan Gu This is my paper
classification cs.LG stat.ML
keywords deepneuralcontextuallastlayerlearningalgorithmapproach
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We study a general class of contextual bandits, where each context-action pair is associated with a raw feature vector, but the reward generating function is unknown. We propose a novel learning algorithm that transforms the raw feature vector using the last hidden layer of a deep ReLU neural network (deep representation learning), and uses an upper confidence bound (UCB) approach to explore in the last linear layer (shallow exploration). We prove that under standard assumptions, our proposed algorithm achieves $\tilde{O}(\sqrt{T})$ finite-time regret, where $T$ is the learning time horizon. Compared with existing neural contextual bandit algorithms, our approach is computationally much more efficient since it only needs to explore in the last layer of the deep neural network.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration

    cs.LG 2025-06 unverdicted novelty 6.0

    Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.

  2. Neural Exploitation and Exploration of Contextual Bandits

    cs.LG 2023-05 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.

  3. Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization

    cs.LG 2026-07 unverdicted novelty 5.0

    Proposes projected quantum kernels with misspecified GP bandit algorithms and regret bounds to trade off expressivity against learnability in quantum kernel optimization.

  4. Variational Proximal Policy Optimization

    stat.ML 2026-06 unverdicted novelty 5.0

    VP2O maps PPO to SVGD in a MoE architecture using functional kernels and expert orthogonalization, claiming +179 ELO on Codeforces and 32% token reduction on AIME for a 33B/4B model.