On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

12 results for “exp4.p”

Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithmscs.LG

New algorithms improve exploration in unbounded reward settings.

problem Challenges in exploration with unbounded rewards in reinforcement learning.

method Proposed EXP4.P and EXP4-RL algorithms for unbounded reward settings.

result EXP4.P achieves global optimality in linear cases with one competent expert.

reinforcement learning exploration EXP-based algorithms unbounded rewards regret bounds

2020-09-20abs ↗pdf ↗

Fighting Contextual Bandits with Stochastic Smoothingstat.ML

We introduce a new stochastic smoothing perspective to study adversarial contextual bandit problems. We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation distributions that lead to strong regret bounds. Using the idea of smoothness, we provide an…

2018-10-11abs ↗pdf ↗

Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advicecs.LG

Improved regret bounds for bandits with fixed expert advice using information theory.

problem Optimizing regret in bandit problems with fixed expert distributions.

method Information-theoretic analysis and KL-divergence measures.

result First regret bounds for EXP4 that can get arbitrarily close to zero under certain conditions.

bandits regret expert advice information theory KL-divergence

2023-03-14abs ↗pdf ↗

Cache Replacement as a MAB with Delayed Feedback and Decaying Costscs.LG

New algorithm improves cache management with delayed feedback and decaying costs.

problem Improving cache replacement policies with delayed and decaying costs feedback.

method Proposed EXP4-DFDC adaptive reinforcement learning algorithm.

result Expected regret is a vanishing quantity as a function of time.

cache replacement multi-armed bandit reinforcement learning delayed feedback decaying costs

2020-09-23abs ↗pdf ↗

Information Capacity Regret Bounds for Bandits with Mediator Feedbackcs.LG

New algorithm bounds regret in mediator feedback bandit problems.

problem Mediator feedback bandit game with policy sets.

method Adopting EXP4 algorithm, new regret bounds based on policy set capacity.

result Nearly-matching lower bounds for policy set families.

bandits mediator feedback policy set capacity regret bounds EXP4 algorithm

2024-02-15abs ↗pdf ↗

Nonstochastic Bandits with Infinitely Many Expertscs.LG

Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.

problem Maximizing reward by choosing actions sequentially from a set of experts.

method Proposed a variant of Exp4.P for infinitely many experts and a meta-algorithm.

result Proved high-probability upper bound of

ilde{\mathcal{O}} \big( i^*K + \sqrt{KT} \big)

on regret.

nonstochastic bandits infinitely many experts meta-algorithm regret bound exp4.p

2021-02-09abs ↗pdf ↗

Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stabilitystat.ML

A new algorithm reduces inference error in adaptive contextual bandits.

problem Challenges in statistical inference for adaptive contextual bandits.

method Proposes a regularized EXP4 algorithm that satisfies the Lai-Wei stability condition.

result Valid Wald-type confidence intervals for linear functionals can be achieved without the price of adaptivity.

contextual bandits stability regression confidence intervals EXP4 algorithm

2025-12-23abs ↗pdf ↗

An Optimal Algorithm for Linear Banditscs.LG

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…

2011-10-19abs ↗pdf ↗

Improved Sleeping Bandits with Stochastic Actions Sets and Adversarial Rewardscs.LG

New algorithm reduces sleeping bandits' regret to O(sqrt(T)).

problem Improving sleeping bandits with stochastic actions and adversarial rewards.

method Inspired by EXP3, new algorithm with

O(\sqrt{T})

regret.

result Achieves

O(\sqrt{T})

regret, improving over existing

O(T^{2/3})

sleeping bandits EXP3 regret minimization stochastic actions adversarial rewards

2020-04-14abs ↗pdf ↗

Bandits with Abstention under Expert Advicecs.LG

Improves reward bounds for prediction with expert advice using abstention.

problem Prediction with expert advice under bandit feedback with abstention.

method CBA algorithm exploiting abstention to improve reward bounds.

result Achieved significant improvement in reward bounds for general confidence-rated predictors.

prediction with expert advice bandit feedback abstention reward bounds confidence-rated predictors

2024-02-22abs ↗pdf ↗

Efficient Contextual Bandits in Non-stationary Worldscs.LG

Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit algorithms for non-stationary environments by equipping existing methods for i.i.d. …

2017-08-05abs ↗pdf ↗

Near-optimal Per-Action Regret Bounds for Sleeping Banditscs.LG

Near-optimal per-action regret bounds for sleeping bandits are derived.

problem Optimizing performance in sleeping bandits where arms and losses are chosen by an adversary.

method Directly minimizing per-action regret using generalized versions of EXP3, EXP3-IX, and FTRL with Tsallis entropy.

result Near-optimal bounds of order

O(\sqrt{TA\ln{K}})

and

O(\sqrt{T\sqrt{AK}})

are obtained.

sleeping bandits regret bounds EXP3 EXP3-IX FTRL

2024-03-02abs ↗pdf ↗