Research
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.

168,742 papers · 148 categories

Trend · papers per month

117234350467 · Jun 202019922001200920172026
48 results for empirical regret

Improved analysis of UCRL2 with empirical Bernstein inequality reduces exploration-exploitation regret.

problem Exploration-exploitation in communicating Markov Decision Processes.
method Analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B).
result Regret bound of O~(DΓSAT)\widetilde{O}(\sqrt{DΓS A T}) for UCRL2B.

Most bandit algorithm designs are purely theoretical. Therefore, they have strong regret guarantees, but also are often too conservative in practice. In this work, we pioneer the idea of algorithm design by minimizing the empirical Bayes regret, the average regret over problem instances sampled from a known distributio…

2019-04-04abs ↗pdf ↗

IDS improves sparse linear bandits by balancing information and regret.

problem Sparse linear bandits in high-dimensional decision-making.
method Information-directed sampling (IDS) with Bayesian regret bounds and empirical Bayesian sparse posterior sampling.
result IDS nearly matches existing lower bounds and significantly reduces regret.

This guide simplifies high-probability regret bounds in empirical risk minimization.

problem High-probability regret bounds in empirical risk minimization.
method Modular presentation, three-step recipe, localized Rademacher complexity, local maximal inequalities, metric-entropy integrals.
result Recover familiar rates for various function classes and derive regret bounds for nuisance components.

New insights into empirical Bayes and compound decision problems with improved regret bounds.

problem Estimating means of normally or Poisson distributed vectors under squared loss.
method Combines Bayesian and frequentist approaches using data-driven estimators.
result Optimal regret bounds for Poisson and normal mean models, resolving conjectures.

We propose minimum regret search (MRS), a novel acquisition function for Bayesian optimization. MRS bears similarities with information-theoretic approaches such as entropy search (ES). However, while ES aims in each query at maximizing the information gain with respect to the global maximum, MRS aims at minimizing the…

2016-02-02abs ↗pdf ↗

New algorithm reduces online learning regret in uninformed Markov games.

problem Achieving no external regret in uninformed Markov games is impossible.
method Empirical Nash-value regret, parameter-free algorithm, adaptive restart.
result Achieves O(min{K+(CK)1/3,LK})O(\min \{\sqrt{K} + (CK)^{1/3},\sqrt{LK}\}) regret bound.

New algorithm reduces online logistic regression regret without exponential constant.

problem Improper learning in online logistic regression with logarithmic regret.
method Regularized empirical risk minimization with surrogate losses.
result Regret scaling as O(B log(Bn)) with low computational complexity.

LinMED is a new linear bandit algorithm with near-optimal regret bound.

problem Optimizing decision-making in linear bandit problems with sub-Gaussian distributions.
method LinMED is a randomized linear bandit algorithm with closed-form arm sampling probabilities.
result LinMED achieves a near-optimal regret bound of dnd\sqrt{n} up to logarithmic factors.

This paper analyzes data-driven Newsvendor problems and finds a wide range of possible regrets.

problem Guessing the number drawn from an unknown distribution with asymmetric costs.
method Unified analysis using the notion of clustered distributions and new lower bounds.
result The entire spectrum of achievable regrets from 1/n1/\sqrt{n} to 1/n1/n is possible.

Optimal algorithm for minimizing regret in heavy-tailed bandits.

problem Minimizing regret in stochastic multi-armed bandits with heavy-tailed distributions.
method Proposes an optimal algorithm under the assumption of uniformly bounded moments of order (1+ε).
result Matches the lower bound exactly in the first-order term and provides a finite-time bound on its regret.

We study the regret of optimal strategies for online convex optimization games. Using von Neumann's minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical minimization algorithm in a stochastic process setting: it is equal to the maximum, over jo…

2009-03-30abs ↗pdf ↗

This paper analyzes how randomizing rewards in MBRL can improve performance without being overly optimistic.

problem The gap between theoretical worst-case regret analysis and empirical performance in MBRL.
method Reward randomization in model-based reinforcement learning (MBRL) with kernelized linear regulator (KNR) model.
result Reward randomization guarantees partial optimism and near-optimal worst-case regret.

New algorithm reduces best-in-class regret in contextual bandits.

problem Compete with the best policy in a class without model restrictions.
method Proposes an algorithm that updates policies by minimizing a pessimistic objective, including a clipped inverse-propensity estimate and variance penalty.
result Achieves fast best-in-class regret rates, including polylogarithmic rates in the parametric case.

Proposes a general method to derive regret bounds for multi-armed bandit algorithms.

problem Deriving regret bounds for randomized multi-armed bandit algorithms.
method Checking sufficient conditions on sampling probabilities and distributions.
result Proves logarithmic regret bounds for various bandit algorithms and new models.

MOL-TS uses Thompson Sampling for multi-objective linear bandits with Pareto guarantees.

problem Optimizing multiple conflicting objectives in linear contextual bandits.
method Proposes MOL-TS, a Thompson Sampling algorithm with Pareto regret guarantees.
result Achieves a worst-case Pareto regret bound of O~(d3/2T)\widetilde{O}(d^{3/2}\sqrt{T}).

We study the KK-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic…

2015-06-08abs ↗pdf ↗

We develop a novel family of algorithms for the online learning setting with regret against any data sequence bounded by the empirical Rademacher complexity of that sequence. To develop a general theory of when this type of adaptive regret bound is achievable we establish a connection to the theory of decoupling inequa…

2017-04-13abs ↗pdf ↗

We investigate the use of bootstrapping in the bandit setting. We first show that the commonly used non-parametric bootstrapping (NPB) procedure can be provably inefficient and establish a near-linear lower bound on the regret incurred by it under the bandit model with Bernoulli rewards. We show that NPB with an approp…

2018-05-24abs ↗pdf ↗

Efficient algorithms for contextual bandits with smooth regret in continuous action spaces.

problem Efficient learning in large or continuous action spaces.
method Smooth regret notion and efficient algorithms for general function approximation.
result Statistically and computationally efficient algorithms for contextual bandits with smooth regret.

A robust bandit algorithm uses Dirichlet sampling to minimize regret under various distributional assumptions.

problem Robustness of bandit algorithms to model misspecification.
method Dirichlet Sampling (DS) algorithm based on pairwise comparisons and re-sampling of arm observations.
result Different DS variants achieve optimal regret guarantees for bounded distributions and logarithmic regret for semi-bounded distributions.

TVBO optimizes time-varying functions with asymptotically vanishing regret.

problem Understanding the asymptotic performance of TVBO for time-varying black-box functions.
method Provided upper and lower bounds for cumulative regret of TVBO algorithms.
result TVBO algorithms can achieve asymptotically vanishing regret under certain conditions.

Adaptive designs achieve strong Neyman regret guarantees for ATE estimation.

problem Estimating unbiased average treatment effect in sequential experiments.
method Proposed adaptive designs with O~(logT)\widetilde{O}(\log T) Neyman regret under boundedness assumptions and O~(T)\widetilde{O}(\sqrt{T}) multigroup Neyman regret in covariate-based settings.
result Adaptive designs outperform non-adaptive designs in terms of Neyman regret, especially in covariate-based settings.

The paper minimizes Borda regret in dueling bandits models.

problem Minimizing Borda regret in dueling bandits models.
method Proposes explore-then-commit and EXP3-type algorithms for stochastic and adversarial settings respectively.
result Achieves nearly matching regret upper bounds of O(d2/3T2/3)O(d^{2/3} T^{2/3}) for both settings.

Improved algorithms for stochastic linear bandits using tighter confidence sequences.

problem Stochastic linear bandits with improved worst-case regret guarantees.
method Novel tail bound for adaptive martingale mixtures to construct tighter confidence sequences.
result Linear bandit algorithm achieves competitive worst-case regret.

New meta-learning framework for minimizing simple regret in bandits.

problem Minimizing simple regret in a sequence of bandit tasks with unknown distributions.
method Developed Bayesian and frequentist meta-learning algorithms for bandits, analyzing their meta simple regret.
result Bayesian algorithm achieves ildeO(m/n) ilde{O}(m / \sqrt{n}) meta simple regret, frequentist algorithm ildeO(mn+m/n) ilde{O}(\sqrt{m} n + m/ \sqrt{n}).

A new exploration strategy for contextual bandits reduces regret and is computationally efficient.

problem Improving exploration in contextual bandits to reduce regret.
method Feature perturbation, injecting randomness directly into feature inputs.
result Achieves ildeO(dT) ilde{\mathcal{O}}(d\sqrt{T}) worst-case regret bound, surpassing existing methods.

New algorithm reduces multi-agent bandit regret by sharing data.

problem Designing efficient collaboration between multi-agent linear bandits.
method Bandit Adaptive Sample Sharing (BASS) algorithm, without assumptions on bandit parameters structure.
result Validated through theoretical analysis and empirical evaluations, BASS outperforms current state-of-the-art.

Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.

problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.

Improved neural active learning algorithms reduce regret and improve performance.

problem Improving performance and reducing regret in neural active learning for non-parametric streaming data.
method Introducing two new regret metrics and leveraging NNs for both exploitation and exploration. The algorithm uses tailored query decision-makers and full feedback.
result Achieved an instance-dependent regret upper bound improving by a multiplicative factor of O(logT)O(\log T) and removing the curse of dimensionality.

This paper improves online learning algorithms for LP problems, achieving better regret bounds.

problem Achieving optimal regret bounds in online linear programming.
method Develops a new framework for first-order online learning algorithms under certain error bound conditions.
result First-order learning algorithms achieve o(T)o(\sqrt{T}) regret in continuous support and O(logT)\mathcal{O}(\log T) regret in finite support, improving over O(T)\mathcal{O}(\sqrt{T}).

We show how to reduce the process of predicting general order statistics (and the median in particular) to solving classification. The accompanying theoretical statement shows that the regret of the classifier bounds the regret of the quantile regression under a quantile loss. We also test this reduction empirically ag…

2012-06-27abs ↗pdf ↗

A new metric, Weighted Regret, unifies FDR and power evaluation in online multiple testing.

problem The asymmetric costs of false positives and false negatives in automated pipelines.
method Introducing Weighted Regret and Decoupled-OMT (DOMT) to unify FDR and power evaluation.
result DOMT achieves an order-optimal sublinear mitigation of threshold depletion in bursty environments.

Paper shows how online betting algorithms' regret can be used to create tight confidence sequences.

problem Estimating the expectation of random variables from samples and creating time-uniform confidence sequences.
method Converts the regret guarantee of universal portfolio algorithms into time-uniform concentration inequalities and confidence sequences.
result Numerically obtained confidence sequences are never vacuous and satisfy the law of iterated logarithm.

Improved exploration in factored average-reward MDPs reduces regret.

problem Minimizing regret in unknown Factored Markov Decision Processes (FMDPs).
method DBN-UCRL strategy, inspired by UCRL2, uses Bernstein-type confidence sets for individual elements of the transition function.
result Achieves a regret bound with a leading term strictly improving over existing bounds.

Learning reward functions can lead to poor policy performance despite low error.

problem Low error in learned reward functions does not guarantee low regret in policy performance.
method Mathematical analysis of reward learning and policy optimization.
result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.

Paper analyzes GP-EI for Bayesian optimization with no regret and provides guidance on choosing incumbents.

problem Analyzing cumulative regret of GP-EI with different incumbents in noisy Bayesian optimization.
method Analyzes GP-EI with three incumbents (BPMI, BSPMI, BOI) in both SE and Matérn kernels, proving no-regret for BPMI and BSPMI.
result GP-EI with BPMI and BSPMI is a no-regret algorithm for both SE and Matérn kernels, providing theoretical guidance for choosing incumbents.