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

36 results for “Lower-confidence-bound”

Post-Selection Confidence Bounds for Prediction Performancestat.ML

Proposes a method to compute valid lower confidence bounds for multiple models selected based on their performance.

problem Model selection and evaluation in machine learning.

method Interprets model selection as a simultaneous inference problem, uses bootstrap tilting and maxT-type multiplicity correction.

result Yields valid lower confidence bounds that are at least as good as standard approaches and reliably reach nominal coverage probability.

machine learning model selection prediction performance confidence bounds bootstrap

2022-10-24abs ↗pdf ↗

Building Bridges: Viewing Active Learning from the Multi-Armed Bandit Lenscs.LG

In this paper we propose a multi-armed bandit inspired, pool based active learning algorithm for the problem of binary classification. By carefully constructing an analogy between active learning and multi-armed bandits, we utilize ideas such as lower confidence bounds, and self-concordant regularization from the multi…

2013-09-26abs ↗pdf ↗

Learning in Prophet Inequalities with Noisy Observationsstat.ML

Study noisy rewards in online decision-making with unknown distributions.

problem Learning optimal decisions in online settings with noisy and unknown reward distributions.

method Proposes algorithms integrating learning and decision-making via LCB thresholding.

result Achieves competitive ratios of 1 - 1/e and 1/2 in various settings.

Prophet inequalities Online decision-making Noisy observations Optimal stopping Lower-confidence-bound

2026-04-02abs ↗pdf ↗

Dynamic Assortment Selection and Pricing with Censored Preference Feedbackstat.ML

Study optimizes dynamic product selection and pricing using censored preference feedback.

problem Maximizing revenue from dynamic assortment and pricing decisions.

method Proposes a censored multinomial logit model and LCB pricing strategy combined with UCB or TS product selection.

result Achieves optimal regret bounds for dynamic pricing and selection.

dynamic assortment pricing censored multinomial logit Lower Confidence Bound Upper Confidence Bound

2025-04-03abs ↗pdf ↗

On Thompson Sampling and Bilateral Uncertainty in Additive Bayesian Optimizationstat.ML

Thompson Sampling with bilateral uncertainty improves performance in Bayesian Optimization.

problem Twin difficulties of modeling and searching complex functions in high dimensions.

method Exploiting conditional independence, Thompson Sampling respecting bilateral uncertainty (BU).

result Thompson Sampling with BU is more effective than the additive approximation in small budgets.

Thompson Sampling Bayesian Optimization Additive Lower Confidence Bound Bilateral Uncertainty Conditional Independence

2025-10-13abs ↗pdf ↗

Robust Bayesian Target Value Optimizationcs.LG

Optimizes target value in stochastic black box functions.

problem Finding input to minimize expected squared error to target value.

method Derives acquisition functions for expected improvement, probability of improvement, and lower confidence bound, assuming Gaussian aleatoric effects.

result Acquisition functions can outperform classical Bayesian optimization under certain conditions.

Bayesian optimization target value optimization stochastic black box expected improvement lower confidence bound

2023-01-11abs ↗pdf ↗

Online Decision Making with Generative Action Setscs.LG

New algorithm optimizes online decision-making with dynamically generated actions.

problem Balancing action generation costs with optimal decision-making in online learning.

method Doubly-optimistic algorithm using LCB for action selection and UCB for action generation.

result Achieves optimal regret bound of

O(T^{\frac{d}{d+2}}d^{\frac{d}{d+2}} + d\sqrt{T\log T})

online learning generative AI doubly-optimistic action generation regret bound

2025-09-30abs ↗pdf ↗

The Efficacy of Pessimism in Asynchronous Q-Learningcs.LG

The paper improves Q-learning by incorporating pessimism for better sample efficiency.

problem Improving sample efficiency in asynchronous Q-learning with non-i.i.d. data.

method Developed an algorithmic framework that incorporates the principle of pessimism into asynchronous Q-learning, penalizing infrequently-visited state-action pairs based on suitable lower confidence bounds (LCBs).

result Achieved near-optimal sample complexity, providing theoretical support for the use of pessimism in non-i.i.d. data.

Q-learning Asynchronous Pessimism Lower Confidence Bounds Sample Efficiency

2022-03-14abs ↗pdf ↗

Multiarmed Bandits Problem Under the Mean-Variance Settingmath.OC

This paper extends the MAB problem to consider risk-reward tradeoffs.

problem Maximizing reward while accounting for risk in multi-armed bandit problems.

method Introduced the Risk Aware Lower Confidence Bound (RALCB) algorithm to solve the mean-variance MAB problem.

result The RALCB algorithm performs better than the algorithm in Sani et al. (2012) in both independent and dependent scenarios.

multiarmed bandits mean-variance risk-aware lower confidence bound sub-Gaussian arms

2022-12-18abs ↗pdf ↗

Are Stochastic Multi-objective Bandits Harder than Single-objective Bandits?cs.LG

New method shows multi-objective bandits are not harder than single-objective ones.

problem Comparing multi-objective bandits to single-objective ones.

method Upper and lower confidence-bound estimators for every arm-objective pair, using top-two races and uncertainty-greedy rule.

result Achieves Pareto regret of \(O( icefrac{\log T}{g^\dagger})\), matching lower bound of \(Ω( icefrac{\log T}{g^\dagger})\).

multi-objective bandits pareto regret upper and lower confidence-bound top-two races uncertainty-greedy rule

2026-04-08abs ↗pdf ↗

Rate-Optimal Online Convex Optimization in Adaptive Linear Controlcs.LG

Optimal control in changing systems without strong convexity assumptions.

problem Adversarial changes in convex costs for unknown linear systems.

method Non-convex lower confidence bounds and computationally-efficient regret minimization.

result Achieves

\smash{\sqrt{T}}

-regret rate, optimal compared to best stabilizing controller.

online convex optimization adaptive control linear dynamical systems regret minimization non-convex bounds

2022-06-03abs ↗pdf ↗

Pessimism for Offline Linear Contextual Bandits using

\ell_p

Confidence Setscs.LG

New method optimizes offline linear bandits using different confidence sets.

problem Optimizing offline learning for linear contextual bandits.

method Introduces a family of pessimistic learning rules based on

\ell_p

confidence sets.

result The

\hatπ_\infty

rule achieves minimax performance and strictly dominates other predictors.

offline learning linear contextual bandits pessimism confidence sets minimax

2022-05-21abs ↗pdf ↗

Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequalitycs.LG

New algorithm learns policies without uniform overlap assumption.

problem Learning optimal policies from non-uniformly collected data.

method Pessimistic Policy Learning (PPL) using lower confidence bounds.

result Efficient policy learning for adaptively collected data.

policy learning offline learning non-uniform overlap empirical Bernstein's inequality behavior policies

2022-12-19abs ↗pdf ↗

Bayesian Regret Minimization in Offline Banditscs.LG

New algorithm minimizes Bayesian regret in offline linear bandits.

problem Minimizing Bayesian regret in offline linear bandits.

method Proposes a new algorithm that directly minimizes upper bounds on Bayesian regret using conic optimization.

result Upper bounds are tight and guarantee superior performance compared to LCB.

Bayesian regret offline bandits conic optimization monetary risk measures

2023-06-02abs ↗pdf ↗

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimismcs.LG

A new offline RL framework unifies imitation learning and vanilla offline RL.

problem Learning from expert datasets without active data collection.

method A new offline RL framework that interpolates between imitation learning and vanilla offline RL, using a weak concentrability coefficient and a lower confidence bound algorithm.

result LCB algorithm achieves a faster rate of

1/N

for nearly-expert datasets, and is adaptively optimal for the entire data composition range.

offline reinforcement learning imitation learning vanilla offline RL concentrability coefficient lower confidence bound

2021-03-22abs ↗pdf ↗

Joint Pricing and Resource Allocation: An Optimal Online-Learning Approachcs.LG

Optimal online learning for joint pricing and resource allocation.

problem Maximizing net profit in dynamic pricing and resource allocation with stochastic demand.

method Developed an efficient algorithm using a Lower-Confidence Bound (LCB) meta-strategy over multiple OCO agents.

result Achieved

ilde{O}(\sqrt{Tmn})

regret, optimal with respect to time horizon

T

online learning dynamic pricing resource allocation stochastic demand meta-strategy

2025-01-29abs ↗pdf ↗

Sequential Test for the Lowest Mean: From Thompson to Murphy Samplingstat.ML

Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning task as the problem of sequentially testing how the minimum mean among a finite set of distributions compares to a given threshold. We deve…

2018-06-04abs ↗pdf ↗

Distributionally Robust Logistic Regressionmath.OC

This paper proposes a distributionally robust approach to logistic regression. We use the Wasserstein distance to construct a ball in the space of probability distributions centered at the uniform distribution on the training samples. If the radius of this ball is chosen judiciously, we can guarantee that it contains t…

2015-09-30abs ↗pdf ↗

Estimation of Predictive Performance in High-Dimensional Data Settings using Learning Curvesstat.ME

Learn2Evaluate uses learning curves to estimate high-dimensional prediction performance.

problem Estimating test performance in high-dimensional data settings is challenging.

method Learn2Evaluate uses learning curves to estimate test performance at the total sample size.

result Learn2Evaluate provides a lower confidence bound for performance estimation.

learning curves high-dimensional data performance estimation predictive modeling bias correction

2022-06-08abs ↗pdf ↗

Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibriumcs.LG

Algorithm finds Nash equilibria in complex games with function approximation.

problem Learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation.

method Online learning algorithm using upper and lower confidence bounds derived from optimism in the face of uncertainty.

result Achieves

O(\sqrt{T})

regret with polynomial complexity, under mild assumptions.

Markov Games Nash Equilibrium Function Approximation Reproducing Kernel Hilbert Space Online Learning

2022-08-10abs ↗pdf ↗

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexitycs.LG

Pessimistic Q-learning improves sample efficiency in offline reinforcement learning.

problem Insufficient coverage and sample scarcity in offline reinforcement learning datasets.

method Pessimistic Q-learning algorithm for offline reinforcement learning, focusing on variance reduction.

result Near-optimal sample complexity achieved with the proposed algorithm.

offline reinforcement learning pessimism Q-learning sample efficiency Markov decision processes

2022-02-28abs ↗pdf ↗

Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluationcs.AI

For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current methods for exact high confidence off-policy evaluation that use importance sampl…

2016-06-20abs ↗pdf ↗

Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communicationcs.LG

Algorithm optimizes multi-player learning with noisy rewards without direct communication.

problem Cooperative multi-player learning with noisy rewards and no communication.

method Upper and lower confidence bounds algorithm for optimal action selection.

result Achieves logarithmic

O(\frac{\log T}{Δ_{\bm{a}}})

and

O(\sqrt{T\log T})

regret.

multiplayer learning bandits noisy rewards asymmetry regret minimization

2023-11-10abs ↗pdf ↗

Model-Based Reinforcement Learning for Offline Zero-Sum Markov Gamescs.LG

Pessimistic model-based algorithm finds Nash equilibria in zero-sum Markov games from offline data.

problem Learning Nash equilibria in two-player zero-sum Markov games from limited data.

method Pessimistic model-based algorithm with Bernstein-style lower confidence bounds (VI-LCB-Game).

result Proves sample complexity no larger than

\frac{C_{\mathsf{clipped}}^\star S(A+B)}{(1-γ)^3 \varepsilon^2}

, achieving minimax optimality.

reinforcement learning Markov games Nash equilibrium model-based offline data

2022-06-08abs ↗pdf ↗

Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancementcs.LG

In data-limited settings, stochastic policies can outperform deterministic ones in bandit problems.

problem Making reliable decisions with limited data in bandit problems.

method Designing TRUST, an algorithm that uses localization laws and relative pessimism.

result TRUST achieves comparable sample complexity to LCB on minimax problems but is significantly lower on few-sample problems.

bandits stochastic policies reinforcement learning data-starved trust region

2024-02-24abs ↗pdf ↗

Provable Self-Play Algorithms for Competitive Reinforcement Learningcs.LG

Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. However, the majority of exisiting theory in reinforcement learning only applies to the setting wher…

2020-02-10abs ↗pdf ↗

Online Auction Design Using Distribution-Free Uncertainty Quantification with Applications to E-Commercecs.GT

COAD maximizes online auction revenue by quantifying uncertainty without known distributions.

problem Designing incentive-compatible mechanisms for online auctions with unknown bidder values and uncertain future participants.

method COAD uses distribution-free uncertainty quantification techniques and integrates machine learning methods to predict bidder values while ensuring revenue guarantees.

result COAD maximizes revenue in online auctions through bidder-specific reserve prices based on lower confidence bounds of valuations.

online auctions incentive compatibility uncertainty quantification machine learning reserve prices

2024-05-11abs ↗pdf ↗

Enhancing Signal Proportion Estimation Through Leveraging Arbitrary Covariance Structuresmath.ST

Paper improves signal proportion estimation by accounting for variable dependence.

problem Traditional estimators assume independence, limiting applicability in real-world scenarios.

method Integrates arbitrary covariance dependence information using principal factor approximation.

result Method outperforms state-of-the-art estimators in accuracy and detection of weaker signals.

signal proportion covariance dependence sparsity principal factor estimation accuracy

2025-07-16abs ↗pdf ↗

Robust Offline Reinforcement Learning for Non-Markovian Decision Processescs.LG

Paper tackles robust offline RL for non-Markovian processes, improving efficiency and applicability.

problem Learning robust policies for non-Markovian decision processes with limited offline data.

method Proposes a novel algorithm with dataset distillation and LCB design for robust values, derived new dual forms, and introduces concentrability coefficients.

result Proves polynomial sample efficiency for finding ε-optimal robust policies.

Offline Reinforcement Learning Non-Markovian Processes Robustness Low-Rank Structure Concentrability Coefficients

2024-11-12abs ↗pdf ↗

Global Optimization of Gaussian processesmath.OC

New method for global optimization of Gaussian processes reduces computational time.

problem Nonconvex optimization problems with Gaussian processes trained on few data points.

method Reduced-space formulation with branch-and-bound solver and McCormick relaxations.

result Significantly reduced computational time compared to state-of-the-art methods.

Gaussian processes global optimization Bayesian optimization branch-and-bound McCormick relaxations

2020-05-21abs ↗pdf ↗

Learning cardiac activation maps from 12-lead ECG with multi-fidelity Bayesian optimization on manifoldseess.SP

Method identifies cardiac ectopic activity sites from 12-lead ECG.

problem Locate dangerous ectopic activation sites in the heart.

method Bayesian optimization on cardiac model and ECG data.

result Method converges to minimum after 11.7-3.5 iterations.

cardiac activation Bayesian optimization ectopic activity ECG global optimization

2022-03-11abs ↗pdf ↗

Satisficing Regret Minimization in Bandits: Constant Rate and Light-Tailed Distributionstat.ML

New algorithm SELECT minimizes satisficing regret in bandits.

problem Minimizing regret in bandit optimization with satisficing arms.

method SELECT algorithm for satisficing regret minimization.

result SELECT achieves constant expected satisficing regret.

bandit optimization satisficing regret SELECT algorithm realizable case non-realizable case

2024-06-10abs ↗pdf ↗

Data Driven Block Replacement Schedulingcs.LG

Develops algorithms to optimize machine replacement schedules using operational data.

problem Optimizing machine replacement intervals when the lifetime distribution is unknown.

method Formulates as a stochastic multi-armed bandit problem and proposes Hoeffding- and Bernstein-based algorithms.

result Achieves optimal or near-optimal replacement intervals with minimal regret.

block replacement machine maintenance stochastic bandits operational data regret minimization

2026-07-16abs ↗pdf ↗

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learningcs.LG

New RL algorithm reduces sample complexity for optimal learning.

problem Achieving optimal learning with minimal samples in RL.

method Early-settled variance reduction method with Q-learning sequences.

result Near-optimal regret achieved with sample size

SA\,\mathrm{poly}(H)

Reinforcement Learning Model-Free Regret Minimization Sample Complexity Early-Settled Variance Reduction

2021-10-09abs ↗pdf ↗

Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworkscs.LG

SVH-PSL uses Stein Variational Gradient Descent and Hypernetworks to improve Pareto set learning for expensive MOO.

problem Fragmented surrogate models and pseudo-local optima in expensive multi-objective optimization problems.

method SVH-PSL integrates Stein Variational Gradient Descent (SVGD) with Hypernetworks to address fragmentation and pseudo-local optima.

result SVH-PSL significantly improves the quality of the learned Pareto set, offering a promising solution for expensive MOO.

Stein Variational Gradient Descent Hypernetworks Pareto set learning Expensive multi-objective optimization Fragmented surrogate models

2024-12-23abs ↗pdf ↗

Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibriumcs.LG

Efficient reinforcement learning for simultaneous-move zero-sum games using optimistic value iteration.

problem Learning optimal strategies in simultaneous-move zero-sum Markov games with function approximation.

method Developed an optimistic variant of least-squares minimax value iteration algorithm for offline and online settings.

result Achieved an upper bound of

ilde O(\sqrt{d^3 H^3 T})

on duality gap and regret.

reinforcement learning Markov games simultaneous moves optimism value iteration

2020-02-17abs ↗pdf ↗