Pith. sign in

REVIEW 7 cited by

Neural Thompson Sampling

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 2010.00827 v2 pith:GI2GAZWD submitted 2020-10-02 cs.LG stat.ML

Weitong Zhang , Dongruo Zhou , Lihong Li , Quanquan Gu This is my paper · ORCID
classification cs.LGstat.ML
keywords neuralalgorithmalgorithmsbanditsamplingthompsoncontextualnetwork
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achieve a cumulative regret of $\mathcal{O}(T^{1/2})$, which matches the regret of other contextual bandit algorithms in terms of total round number $T$. Experimental comparisons with other benchmark bandit algorithms on various data sets corroborate our theory.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest

    cs.IR 2026-07 conditional novelty 6.0 of 10

    A full-funnel exploration and debiasing system deployed at Pinterest is reported to increase fresh-content impressions by ~350% and lift user-engagement and content-provider metrics.

  2. SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity

    cs.LG 2026-02 accept novelty 6.0 of 10

    Across 66 DRL-for-cybersecurity papers, the authors identify 11 recurring methodological pitfalls—averaging 5.8 per paper—and demonstrate their impact in four environments.

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

    cs.LG 2025-06 unverdicted novelty 6.0 of 10

    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.

  4. Contextual Bandit Optimization with Pre-Trained Neural Networks

    cs.LG 2025-01 conditional novelty 6.0 of 10

    E2TC achieves Õ((KT)^{4/5}) regret for stochastic contextual bandits with pre-trained neural representations and locally convex risk, without requiring extremely wide networks.

  5. From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation

    cs.LG 2026-08 conditional novelty 5.0 of 10

    A causal targeting system that optimizes treatment effects under global constraints and uses bandit exploration beat the incumbent prediction-based stack by a statistically significant 7.20% on LinkedIn Feed marketing...

  6. Neural Contextual Bandits Under Delayed Feedback Constraints

    cs.LG 2025-04 conditional novelty 5.0 of 10

    Under sub-exponential reward delays, Delayed NeuralUCB achieves regret O(d~√T logT + d~^{3/2}D+ log^{3/2}T), with D+ depending on the expected delay.

  7. Epinet for Content Cold Start

    cs.IR 2024-11 conditional novelty 5.0 of 10

    An epinet-based Thompson sampling module improved cold-start video recommendations in a live Facebook Reels A/B test, but the experiment does not isolate the uncertainty mechanism.

Pith tools