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.

168,695 papers · 148 categories

Trend · papers per month

3469103137 · May 202619922001200920172026
48 results for finite-sample regret

New framework calibrates decision robustness using inverse conformal risk control.

problem Inadequate robustness levels in decision-making due to ad hoc choices.
method Constructs valid estimators to trace miscoverage-regret Pareto frontier.
result Provides distribution-free, finite-sample guarantees on robustness levels.

The paper optimizes regret using covariance between costs and decisions.

problem Optimizing expected regret in decision-making problems.
method Developed derivative theory of covariance regret functional, derived Gâteaux derivative, and extended to constrained optimization.
result Gradient of covariance regret is the cost covariance matrix, with implications for portfolio optimization.

The paper tackles batch policy learning in Markov Decision Processes, focusing on average reward maximization.

problem Maximizing long-term average reward in Markov Decision Processes with batch learning.
method Doubly robust estimator for average reward, optimization algorithm for optimal policy, finite-sample regret guarantee.
result The proposed method achieves semiparametric efficiency and provides a finite-sample regret guarantee.

The paper provides bounds on estimation error in a distributed online learning setting.

problem Estimating an unknown parameter in a distributed and online manner with finite sample guarantees.
method Proposes a distributed online estimation algorithm that improves accuracy through communication, providing non-asymptotic bounds on estimation error.
result Demonstrates a trade-off between estimation error and communication costs, and determines a stopping time for communication based on desired accuracy.

The paper tackles personalized policy learning from diverse data sources in a federated setting.

problem Learning personalized decision policies from observational bandit feedback across multiple heterogeneous data sources.
method Introduces a novel regret analysis for distinguishing global and local regret, and presents a federated policy learning algorithm using local policies trained with doubly robust offline policy evaluation strategies.
result Establishes finite-sample upper bounds on global and local regret, characterizing them by source heterogeneity and distribution shift.

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.

CRIMED optimizes regret in bandits with unbounded stochastic corruption.

problem Minimizing regret in bandits with arbitrary unbounded corruptions.
method Introduces CRIMED, an asymptotically-optimal algorithm for Gaussian distributions with known variance.
result Achieves exact lower bound on regret for Gaussian distributions with high corruption probability.

Enhanced HH-consistency bounds derived under relaxed conditions.

problem Quantifying the relationship between zero-one estimation error and surrogate loss estimation error.
method Relaxing the condition on the surrogate loss conditional regret and presenting a general framework for establishing enhanced HH-consistency bounds.
result Derivation of more favorable HH-consistency bounds in various scenarios.

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, which thus lead to over-exploration. In this paper, we propose a n…

2019-06-12abs ↗pdf ↗

The paper introduces new measures to quantify variability in decision tree models due to observational multiplicity.

problem The variability in decision tree models due to observational multiplicity.
method Introduces leaf regret and structural regret to decompose observational multiplicity.
result Structural regret is the primary driver of observational multiplicity, accounting for over 15 times the variability of leaf regret in some datasets.

Paper achieves logarithmic regret for online Kalman filter learning.

problem Predicting observations from an unknown, partially observed linear system with stochastic noise.
method Online least-squares algorithm exploiting the approximate linearity of Kalman filter predictions.
result Achieves regret of order poly(log(N)) with high probability.

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in many applications where rewards are binary. However, most theoretical analyses …

2017-02-28abs ↗pdf ↗

A new test improves statistical inference in bandit algorithms without sacrificing adaptiveness.

problem Challenges in statistical inference for adaptive randomised experiments in bandits.
method An allocation probability test for Thompson Sampling without trading-off regret or requiring large sample sizes.
result Improves statistical inference in small samples, showing advantages in mental health experiments.

This study develops a dynamic inverse optimization framework to recover hidden, time-varying preferences from observed allocation trajectories.

problem The gap between classical optimization theory and real-world practice, especially in the presence of drift and shocks.
method Dynamic inverse optimization framework using a drift-aware estimator grounded in convex analysis and online learning theory.
result Sharp static and dynamic regret bounds for the framework, demonstrating its responsiveness to gradual drift and sudden shocks.

Efficient algorithm predicts unknown linear systems with long-term memory.

problem Predicting unknown and partially observed linear dynamical systems with long-term memory.
method Bounding the generalized Kolmogorov width of the Kalman filter model using spectral methods and conducting tight convex relaxation.
result Competes with Kalman filter in hindsight with only logarithmic regret.

The paper tackles Nash-regret minimization in congestion games with bandit feedback.

problem Minimizing Nash-regret in congestion games with bandit feedback.
method Proposes centralized and decentralized algorithms for congestion games with bandit feedback, and a centralized algorithm for Markov congestion games.
result Sample complexity depends polynomially on the number of players and facilities, not the size of the action set.

STEEL tackles batch RL with singularity, improving policy optimization.

problem Existing RL methods assume absolutely continuous data, but STEEL handles non-overlapping regions.
method Proposes STEEL algorithm using maximum mean discrepancy and distributionally robust optimization.
result First finite-sample regret guarantee for batch RL with singularity.

Adapting policy learning for data collected from evolving systems.

problem Challenges in learning optimal policies from adaptively collected data.
method Proposes an algorithm based on generalized augmented inverse propensity weighted (AIPW) estimators to control worst-case estimation variance.
result Achieves minimax rate optimal regret guarantees even with diminishing exploration.

New findings show ETO outperforms IEO in well-specified models with sufficient data.

problem Comparing estimate-then-optimize (ETO) and integrated-estimation-optimization (IEO) methods in stochastic optimization.
method Analyzes the performance of ETO and IEO in well-specified and misspecified models using stochastic dominance.
result Simple ETO outperforms IEO asymptotically in well-specified models with sufficient data.

New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.

problem Challenges in online reinforcement learning for non-episodic, finite-horizon MDPs.
method Introduces a K-step lookahead Q-function with a time-varying threshold for selecting actions.
result Achieves minimax optimal constant regret for K=1 and O(max((K1),CK1)SATlog(T))\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)}) regret for K ≥ 2.

One-step Bellman alignment improves online RL by reducing task mismatch.

problem Online RL struggles with task similarity defined by rewards or transitions.
method One-step Bellman alignment and re-weighted targeting (RWT) to correct task mismatch.
result Regret bounds show task shift complexity, not target MDP, affects performance.

Study of repeated games with unobserved agent rewards using MAB framework.

problem Designing policies for principals in repeated principal-agent games with unobservable agent rewards.
method Developed a policy achieving low regret (square-root regret up to a log factor) for perfect-knowledge agents.
result Constructed an estimator for agent's expected reward and designed a policy achieving low regret.

New meta-reinforcement learning method improves performance in finite-horizon MDPs.

problem Improving meta-reinforcement learning in finite-horizon MDPs with shared optimal action-value functions.
method Proposes MTSRL and MTSRL+ algorithms with learned priors and covariance, coupled with prior-alignment technique for meta-regret guarantees.
result Achieves meta-regret guarantees with learned priors and covariance, outperforming prior-independent RL and bandit-only meta-baselines.

New algorithms improve efficiency in learning from personalized rewards.

problem Learning from personalized rewards in recommendation systems.
method Developed provably efficient algorithms with sublinear regret for context-dependent feedback.
result Introduced a Lipschitz reward estimator that improves generalization performance.

This paper improves binary classification methods beyond accuracy, especially in imbalanced datasets.

problem Binary classification performance metrics often fail to reflect real-world consequences, especially in imbalanced datasets.
method Derives a generalized Bayes-optimal classifier from accuracy to any performance metric, removing assumptions and providing finite-sample statistical guarantees.
result Optimal classification performance depends on class imbalance properties, providing new insights and guarantees.

Study on newsvendor problem with censored data, showing how much information is lost.

problem Minimizing costs in a newsvendor problem with limited historical demand data.
method Distributionally robust optimization framework, evaluating policies based on worst-case regret.
result Characterization of information loss due to demand censoring and development of a robust algorithm.

Synthetic data augmentation can improve imbalanced classification metrics.

problem Improving imbalanced classification metrics
method Developing a framework for analyzing the effects of synthetic data augmentation on score-based classification
result Augmentation can improve AUROC, AUPRC, balanced accuracy, and F1 score

The paper extends Hoeffding's inequality for Markov chains using a generalized concentrability condition.

problem Applying Hoeffding's inequality to non-ergodic Markov chains.
method Integrates generalized concentrability condition via IPM to extend traditional hypotheses.
result Demonstrates utility in machine learning applications such as empirical risk minimization and bandits.

This paper analyzes momentum Q-learning with finite-sample guarantees.

problem Improving Q-learning performance with momentum schemes.
method Proposes MomentumQ algorithm integrating Nesterov and Polyak's momentum schemes, analyzes convergence for function approximations.
result Establishes finite-sample convergence rates for MomentumQ, demonstrating better performance than vanilla Q-learning.

Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.

problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.

Paper tackles RL with continuous actions and unmeasured confounders.

problem Offline policy learning with continuous actions and unmeasured confounders.
method Developed a novel identification result and a minimax estimator for nonparametric policy value estimation.
result Introduced a policy-gradient-based algorithm to identify the optimal policy.

Propose an XMSE-aware mixed estimator for EB that interpolates between ML and EB shrinkage.

problem Kernel-based EB estimation may be worse than ML when the kernel is poorly aligned with the true parameter.
method An XMSE-aware mixed estimator that interpolates between ML and EB shrinkage.
result Fixed-weight XMSE is a scalar quadratic, yielding a closed-form oracle mixing weight that is no worse than both ML and the base EB estimator at the XMSE scale.

New findings show modern neural networks have finite sample complexity in o-minimal structures.

problem Understanding the learnability of modern neural networks in a broad context.
method Analyzing feedforward neural networks definable in o-minimal structures.
result Modern neural networks, including MLPs, CNNs, GNNs, and transformers, have finite sample complexity in the agnostic PAC setting.

New methods for estimating causal effects with limited overlap, using Stable Probability Weighting.

problem Estimating causal effects with limited overlap in multivalued treatments.
method Stable Probability Weighting (SPW) and Finite-Sample Stable Probability Weighting (FPW) methods.
result SPW and FPW provide practical solutions for estimating and inferring causal effects with limited overlap.