Pith. sign in

REVIEW 3 cited by

Bandits with Mean Bounds

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 2002.08405 v5 pith:5QMPF4KW submitted 2020-02-19 cs.LG stat.ML

Nihal Sharma , Soumya Basu , Karthikeyan Shanmugam , Sanjay Shakkottai This is my paper · ORCID
classification cs.LGstat.ML
keywords boundsarmsestimatesmeanalgorithmalgorithmsexplorationglue
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study a variant of the bandit problem where side information in the form of bounds on the mean of each arm is provided. We prove that these translate to tighter estimates of subgaussian factors and develop novel algorithms that exploit these estimates. In the linear setting, we present the Restricted-set OFUL (R-OFUL) algorithm that additionally uses the geometric properties of the problem to (potentially) restrict the set of arms being played and reduce exploration rates for suboptimal arms. In the stochastic case, we propose the non-optimistic Global Under-Explore (GLUE) algorithm which employs the inferred subgaussian estimates to adapt the rate of exploration for the arms. We analyze the regret of R-OFUL and GLUE, showing that our regret upper bounds are never worse than that of the standard OFUL and UCB algorithms respectively. Further, we also consider a practically motivated setting of learning from confounded logs where mean bounds appear naturally.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Decentralized Relaxed Smooth Optimization with Gradient Descent Methods

    math.OC 2025-08 unverdicted novelty 6.0 of 10

    A decentralized gradient descent method with adaptive clipping is claimed to reach best-known convergence rates for convex and nonconvex problems under (L0,L1)-smoothness without knowing the constants.

  2. Using causal abstractions to accelerate decision-making in complex bandit problems

    cs.LG 2025-09 conditional novelty 5.0 of 10

    AT-UCB uses a cheap abstracted causal model to filter out suboptimal actions before running UCB on the expensive base model, with a regret bound that improves when the abstraction is accurate.

  3. Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine

    stat.ML 2025-05 conditional novelty 4.0 of 10

    DWTS debiases and selects features from observational data, then warm-starts Thompson sampling with those estimates, achieving lower cumulative regret than LinTS in simulations.

Pith tools