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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “heteroscedastic linear bandits”

SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Banditsstat.ML

Presents SPEED, an algorithm for optimal policy evaluation in linear bandits with heteroscedastic noise.

problem Optimal data collection for policy evaluation in linear bandits with heteroscedastic reward noise.

method Formulated an optimal design for weighted least squares estimates, derived the optimal sample allocation, introduced SPEED algorithm, and derived regret bounds.

result SPEED leads to policy evaluation with MSE comparable to oracle strategy and significantly lower than random policy execution.

policy evaluation linear bandits heteroscedastic noise optimal design regret analysis

2023-01-29abs ↗pdf ↗

Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Setcs.LG

New algorithm reduces regret in stochastic linear bandits with heteroscedastic noise.

problem Optimizing performance in stochastic linear bandits with varying noise levels.

method Variance-adaptive algorithm VAEE with active exploration strategy.

result Achieves simple regret with a nearly harmonic-mean dependent rate.

bandits heteroscedastic noise simple regret harmonic-mean active exploration

2026-07-26abs ↗pdf ↗

Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Renegingcs.LG

A new model for lifetime maximization with reneging in heterogeneous outcomes.

problem Maximizing lifetime in applications with reneging and heterogeneous satisfaction levels.

method Heteroscedastic linear bandits with reneging, UCB-type policy HR-UCB.

result HR-UCB achieves

\mathcal{O}\big(\sqrt{{T}(\log({T}))^{3}}\big)

regret.

lifetime maximization heteroscedastic linear bandits reneging UCB regret

2018-10-29abs ↗pdf ↗

Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Banditscs.LG

Study on online regression with noise, achieving near-optimal regret bounds.

problem Online generalized linear regression with stochastic noise.

method Sharp analysis of FTRL algorithm for stochastic label noise.

result Achieved near-optimal regret bounds for

O(σ^2 d \log T) + o(\log T)

online learning generalized linear regression stochastic noise FTRL algorithm regret bound

2022-02-28abs ↗pdf ↗

Information Directed Sampling and Bandits with Heteroscedastic Noisestat.ML

In the stochastic bandit problem, the goal is to maximize an unknown function via a sequence of noisy evaluations. Typically, the observation noise is assumed to be independent of the evaluation point and to satisfy a tail bound uniformly on the domain; a restrictive assumption for many applications. In this work, we c…

2018-01-29abs ↗pdf ↗

Information-Directed Exploration for Deep Reinforcement Learningcs.LG

IDS improves exploration in deep reinforcement learning.

problem Efficient exploration in reinforcement learning, especially with heteroscedastic returns.

method Information-Directed Sampling (IDS) for deep Q-learning.

result Significant improvement in Atari game performance over alternative approaches.

reinforcement learning deep Q-learning heteroscedasticity exploration IDS

2018-12-18abs ↗pdf ↗

Online A-Optimal Design and Active Linear Regressionstat.ML

Optimal online sampling strategy for linear regression with varying variances.

problem Designing experiments to estimate a linear model with unknown covariate variances.

method Combining bandit and convex optimization techniques, proposing an active sampling algorithm.

result Achieved an \(\mathcal{O}(T^{-2})\) regret bound in ideal conditions.

online design active sampling heteroscedasticity bandit convex optimization

2019-06-20abs ↗pdf ↗

Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variancecs.LG

Improved GP bandit algorithms for noiseless, varying noise, and RKHS norms.

problem Minimizing regret in Gaussian process bandits with unknown reward functions.

method New upper bound on maximum posterior variance, refined MVR and PE algorithms.

result Optimal regret bounds for noiseless, varying noise, and RKHS norms.

Gaussian process bandit regret maximum posterior variance RKHS

2025-02-10abs ↗pdf ↗

Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiencycs.LG

New algorithm reduces regret for linear bandits with unknown noise variance.

problem Finding optimal actions in linear bandits with varying noise variance.

method Adaptive algorithm with Freedman-type concentration inequality and multi-layer structure.

result Achieves

ilde{O}(d \sqrt{\sum_{k = 1}^K σ_k^2} + d)

regret for linear bandits.

Linear Bandits Adaptive Algorithms Variance-Dependent Regret Freedman-type Inequality Multi-Layer Structure

2023-02-21abs ↗pdf ↗

Bayesian Linear Regression on Deep Representationscs.LG

Bayesian linear regression on neural network representations handles both homoscedastic and heteroscedastic noise.

problem Uncertainty in neural network predictions, especially with heteroscedastic noise.

method Proposes a novel Bayesian linear regression approach to model heteroscedastic noise in neural network representations.

result The method outperforms standard ensembling and other methods in model-based reinforcement learning.

Bayesian linear regression neural networks heteroscedastic noise uncertainty reinforcement learning

2019-12-14abs ↗pdf ↗

Forecasting wind power - Modeling periodic and non-linear effects under conditional heteroscedasticitystat.AP

In this article we present an approach that enables joint wind speed and wind power forecasts for a wind park. We combine a multivariate seasonal time varying threshold autoregressive moving average (TVARMA) model with a power threshold generalized autoregressive conditional heteroscedastic (power-TGARCH) model. The mo…

2016-06-02abs ↗pdf ↗

Quantifying predictive uncertainty of aphasia severity in stroke patients with sparse heteroscedastic Bayesian high-dimensional regressionstat.ME

New method predicts aphasia severity with narrower uncertainty intervals.

problem Predicting aphasia severity in stroke patients using neuroimages.

method Sparse heteroscedastic Bayesian high-dimensional regression with H-PROBE algorithm.

result H-PROBE provides narrower prediction intervals for aphasia severity.

aphasia stroke neuroimages Bayesian regression

2023-09-15abs ↗pdf ↗

Identifying Patient-Specific Root Causes with the Heteroscedastic Noise Modelstat.ML

New model identifies patient-specific disease root causes.

problem Identifying root causes of complex diseases varying between patients.

method Generalized Root Causal Inference (GRCI) algorithm for heteroscedastic noise model.

result GRCI accurately extracts patient-specific root causes.

disease root causes structural equation model heteroscedastic noise Generalized Root Causal Inference patient-specific

2022-05-25abs ↗pdf ↗

A concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noisemath.ST

We prove a new and general concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise. No specific structure is required on the model, except the existence of a suitable function that controls the local suprema of the empirical process. So far, only the case of…

2017-02-16abs ↗pdf ↗

Support estimation in high-dimensional heteroscedastic mean regressionmath.ST

Paper supports robust estimation in regression with heavy-tailed errors.

problem Support estimation in high-dimensional heteroscedastic mean regression.

method Use of Huber loss function and adaptive LASSO penalty for robust estimation.

result Sign-consistency and optimal rates of convergence in

\ell_\infty

norm.

robust regression heteroscedasticity Huber loss adaptive LASSO support estimation

2020-11-03abs ↗pdf ↗

Variance function estimation in high-dimensionsstat.ML

We consider the high-dimensional heteroscedastic regression model, where the mean and the log variance are modeled as a linear combination of input variables. Existing literature on high-dimensional linear regres- sion models has largely ignored non-constant error variances, even though they commonly occur in a variety…

2012-05-21abs ↗pdf ↗

Inference in Bayesian Additive Vector Autoregressive Tree Modelsecon.EM

BAVART model combines VAR and BART for non-linear forecasting.

problem Overly restrictive linearity assumption in VAR models.

method Combining VAR with Bayesian additive regression trees (BART).

result BAVART model yields highly competitive forecasts.

Bayesian VAR BART Non-linear Forecasting

2020-06-29abs ↗pdf ↗

Near Optimal Heteroscedastic Regression with Symbiotic Learningstat.ML

Improved heteroscedastic regression with machine learning techniques.

problem Estimating weights in heteroscedastic linear regression with varying noise.

method Alternating minimization with weighted least squares and pseudogradient descent.

result Achieved a tighter error bound for estimating weights.

heteroscedastic regression machine learning weighted least squares pseudogradient descent phase retrieval

2023-06-25abs ↗pdf ↗

Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithmsstat.ML

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

problem Stochastic contextual linear bandits with unknown context distribution.

method Establishes a reduction framework to convert to linear bandit problems.

result Achieves nearly optimal regret bound of

O(d\sqrt{T\log T})

stochastic contextual bandits linear bandit algorithms context distribution regret bound open problem

2022-11-08abs ↗pdf ↗

Optimal Thresholding Linear Banditstat.ML

Optimal algorithm for identifying best arm in stochastic linear bandits with fixed confidence.

problem Identifying the best arm in stochastic linear bandits with fixed confidence.

method Extending an algorithm designed for Best Arm Identification to the

ε

-Thresholding Bandit Problem (TBP).

result Asymptotically optimal algorithm for TBP.

Thresholding Bandit Stochastic Linear Bandits Best Arm Identification Fixed Confidence

2024-02-11abs ↗pdf ↗

On the Estimation Performance of Generalized Power Method for Heteroscedastic Probabilistic PCAmath.OC

Paper proposes GPM for heteroscedastic PCA estimation.

problem Estimating ground truth from heterogeneous data.

method Generalized power method (GPM) for HQPOC.

result GPM achieves geometrically decreasing distances to ground truth.

PCA heteroscedastic power method estimation sub-Gaussian noise

2023-12-06abs ↗pdf ↗

A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertaintiescs.LG

A new framework for lightweight BNNs learns heteroscedastic uncertainties efficiently.

problem Learning heteroscedastic uncertainties from BNNs for lightweight networks.

method Embedding heteroscedastic variances into BNN parameters and using moment propagation for inference.

result Improves predictive performance for lightweight BNNs without increasing parameter count.

Bayesian Neural Networks Heteroscedastic Uncertainties Lightweight Networks Variational Inference Moment Propagation

2024-02-22abs ↗pdf ↗

Per-sample Prediction Intervals for Extreme Learning Machinescs.LG

This paper proposes a fast method for estimating input-dependent prediction intervals in Extreme Learning Machines.

problem Estimating reliable prediction intervals for Extreme Learning Machines with heteroscedastic outputs.

method A separate Extreme Learning Machine model estimates input-dependent prediction intervals using a weighted Jackknife method to correct for model uncertainty.

result The proposed method is fast, robust to heteroscedastic outputs, and handles large datasets and insufficient training data.

Extreme Learning Machines Prediction Intervals Heteroscedastic Outputs Jackknife Method Variance Estimation

2019-12-19abs ↗pdf ↗

ALPCAHUS: Subspace Clustering for Heteroscedastic Datastat.ML

ALPCAHUS clusters data from multiple subspaces with varying noise.

problem Heteroscedastic data with varying noise levels.

method Develops a heteroscedastic PCA method for subspace clustering.

result Improves subspace clustering by accounting for sample-wise noise variances.

subspace clustering heteroscedastic data PCA noise variance data quality

2025-05-25abs ↗pdf ↗

Approximation Theory Based Methods for RKHS Banditscs.LG

New algorithms tackle RKHS bandits with reduced complexity and improved performance.

problem Adversarial and stochastic RKHS bandit problems with high computational complexity.

method Combining approximation theory with misspecified linear bandit methods.

result First general algorithm for adversarial RKHS bandit problem.

approximation theory RKHS bandits misspecified linear bandit stochastic bandits adversarial bandits

2020-10-23abs ↗pdf ↗

Faithful Heteroscedastic Regression with Neural Networkscs.LG

Improved heteroscedastic regression using neural networks with provably accurate mean estimates and calibrated variance.

problem Optimizing neural network parameters for heteroscedastic regression leads to suboptimal mean and variance estimates.

method Two simple modifications to optimization to retain accuracy of mean-only models and offer best-in-class variance calibration.

result Mean estimates from the proposed method are provably as accurate as those from a homoscedastic model.

heteroscedastic regression neural networks mean estimation variance calibration optimization

2022-12-18abs ↗pdf ↗

Locally Differentially Private (Contextual) Bandits Learningcs.LG

Paper tackles LDP bandits learning with improved results and sub-linear regret.

problem Contextual bandits learning with LDP privacy constraints.

method Simple black-box reduction frameworks for context-free bandits, extended to GLB.

result First result for BCO with multi-point feedback under LDP, sub-linear regret for GLB.

Locally Differential Privacy Bandits Learning Contextual Bandits Privacy Guarantees Sub-linear Regret

2020-06-01abs ↗pdf ↗

Robust Stochastic Linear Contextual Bandits Under Adversarial Attacksstat.ML

First robust bandit algorithm for contextual bandits with sub-linear regret.

problem Vulnerability of linear contextual bandit algorithms to adversarial attacks.

method Proposes a robust bandit algorithm for stochastic linear contextual bandits under fully adaptive and omniscient attacks.

result Sub-linear regret under various attacks without requiring attack information.

robust bandits contextual bandits adversarial attacks sub-linear regret recommender systems

2021-06-05abs ↗pdf ↗

Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Banditscs.LG

New algorithms improve linear bandit performance with low computation.

problem Optimizing reward in linear stochastic bandits.

method Reward-biased maximum likelihood method modified for linear and generalized linear bandits.

result New policies achieve order-optimality and competitive empirical performance.

bandits maximum likelihood linear stochastic optimization

2020-10-08abs ↗pdf ↗

Adversarial Combinatorial Bandits with General Non-linear Reward Functionsstat.ML

Study non-linear combinatorial bandits with polynomial rewards, finding significant differences from linear cases.

problem Adversarial combinatorial bandits with general non-linear reward functions.

method Extending existing work on adversarial linear combinatorial bandits, analyzing minimax optimal regret for polynomial and non-polynomial reward functions.

result Minimax optimal regret bounds for adversarial combinatorial bandits with general non-linear reward functions.

Adversarial Bandits Non-Linear Reward Polynomial Reward Regret Analysis Combinatorial Optimization

2021-01-05abs ↗pdf ↗

Massively Scaling Heteroscedastic Classifierscs.LG

HET-XL improves heteroscedastic classifiers for large-scale image classification.

problem Scaling heteroscedastic classifiers to handle large numbers of classes and tuning the temperature hyperparameter.

method HET-XL, a heteroscedastic classifier with independent parameter count from the number of classes, learns the temperature hyperparameter directly from training data.

result HET-XL requires 14X fewer additional parameters and performs better than baseline heteroscedastic classifiers on large image classification datasets.

heteroscedastic classifiers temperature hyperparameter large-scale image classification 0-shot learning multimodal contrastive learning

2023-01-30abs ↗pdf ↗

Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductionscs.LG

Unified approach for non-stationary linear bandits with dynamic regret.

problem Non-stationary linear bandits with round-specific feasible actions and drifting reward models.

method Unified misspecification-reduction viewpoint, restarting algorithms with misspecification-dependent regret guarantees.

result Optimal \(T^{2/3}P_T^{1/3}\) dynamic-regret dependence for both linear bandits and contextual linear bandits.

non-stationary bandits dynamic regret misspecification reduction restart algorithms linear bandits

2026-07-03abs ↗pdf ↗

Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Banditsstat.ML

Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.

problem Theoretical justification for Bayesian bandit algorithms with approximate inference in stochastic linear bandits.

method Proposed a theoretical framework to analyze approximate inference impact and conducted frequentist regret analysis on LinTS and LinBUCB.

result LinTS and LinBUCB preserve their original regret upper bounds with larger constant terms in approximate inference settings.

Bayesian bandit stochastic linear bandits approximate inference regret analysis Thompson Sampling

2024-06-20abs ↗pdf ↗

Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matchingcs.LG

New method prevents forgetting in neural-linear bandits for high-dimensional data.

problem Catastrophic forgetting in neural-linear bandits with high-dimensional features.

method Limited memory neural-linear bandit with likelihood matching.

result Resilient to catastrophic forgetting and superior performance.

bandit learning neural networks catastrophic forgetting likelihood matching high-dimensional data

2019-01-24abs ↗pdf ↗

Estimating value at risk: LSTM vs. GARCHq-fin.RM

Paper compares LSTM and GARCH for estimating value-at-risk.

problem Estimating value-at-risk on time series with heteroscedastic dynamics.

method Uses LSTM neural networks to estimate value-at-risk compared to GARCH benchmarks.

result LSTM outperforms GARCH on real market data in terms of exception rate and mean quantile score.

value-at-risk LSTM GARCH heteroscedasticity time series

2022-07-21abs ↗pdf ↗

Linear Bandits with Feature Feedbackcs.LG

New algorithm for linear bandits learns from feature feedback, reducing regret.

problem Linear bandit problem with feature feedback.

method Developed new theory and algorithms for linear bandits with feature feedback.

result Achieves regret scaling like

k\sqrt{T}

, improving over traditional linear bandits.

linear bandits feature feedback regret algorithm stochastic rewards

2019-03-09abs ↗pdf ↗

Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisationstat.ML

Paper proposes a new Bayesian optimisation method to handle aleatoric uncertainty.

problem Representing and minimizing aleatoric noise in Bayesian optimisation.

method Heteroscedastic Gaussian process (GP) surrogate model with AEI and ANPEI acquisition functions.

result Improved performance on toy problems and real-world datasets compared to homoscedastic methods.

Bayesian optimisation aleatoric uncertainty heteroscedasticity GP surrogate augmented expected improvement

2019-10-17abs ↗pdf ↗

No-Regret Gaussian Process Optimization of Time-Varying Functionsstat.ML

No-regret optimization for time-varying functions using uncertainty injection.

problem Optimizing time-varying functions with no-regret in bandit feedback.

method W-SparQ-GP-UCB, incorporating uncertainty injection and additional queries.

result Achieves no-regret with a vanishing number of additional queries per iteration.

Gaussian Process Time-varying functions No-regret Bandit feedback Uncertainty injection

2025-11-29abs ↗pdf ↗

Residual Bootstrap Exploration for Stochastic Linear Banditstat.ML

A new algorithm improves stochastic linear bandit performance using residual bootstrap.

problem Improving performance in stochastic linear bandit problems.

method Residual bootstrap exploration to estimate mean reward and pull the arm with the highest estimate.

result Proposed algorithm exttt{LinReBoot} achieves high-probability sub-linear regret under mild conditions.

stochastic linear bandit residual bootstrap online learning sub-linear regret optimism

2022-02-23abs ↗pdf ↗

Variational Heteroscedastic Volatility Modelq-fin.ST

VHVM models financial time series with varying volatility.

problem Modeling heteroscedastic behavior in multivariate financial time series.

method Variational autoencoder and recurrent neural network for capturing relationships and temporal dynamics.

result VHVM outperforms GARCH and SV models on FX datasets.

financial time series heteroscedasticity volatility modeling deep learning variational autoencoder

2022-04-11abs ↗pdf ↗

Gamification of Pure Exploration for Linear Banditsstat.ML

Optimizes pure exploration in linear bandits with a new algorithm.

problem Best-arm identification in linear stochastic bandits.

method Developed the first asymptotically optimal algorithm for fixed-confidence pure exploration in linear bandits.

result Avoids the pitfall of a simple but difficult instance and bypasses the need to solve an optimal design problem.

gamification pure exploration linear bandits asymptotically optimal experimental design

2020-07-02abs ↗pdf ↗

A Perturbation Approach to Unconstrained Linear Banditscs.LG

New approach reduces unconstrained linear bandits to simpler optimization problems.

problem Unconstrained linear bandits problem.

method Perturbation-based approach combined with comparator-adaptive OLO algorithms.

result First high-probability guarantees for both static and dynamic regret in unconstrained linear bandits.

Bandit Linear Optimization Unconstrained Linear Bandits Perturbation Approach Online Linear Optimization Comparator-Adaptive Algorithms

2026-03-30abs ↗pdf ↗

On the Optimal Regret of Locally Private Linear Contextual Banditstat.ML

This paper achieves optimal regret bounds for locally private linear contextual bandit.

problem Designing locally private linear contextual bandit algorithms with optimal regret bounds.

method New algorithmic and analytical ideas, including mean absolute deviation analysis and layered principal component regression.

result Achieves an

ilde O(\sqrt{T})

regret upper bound for locally private linear contextual bandit.

locally private linear contextual bandit regret bounds mean absolute deviation principal component regression

2024-04-15abs ↗pdf ↗

Best Arm Identification in Generalized Linear Banditscs.LG

New algorithm for identifying best drug arm in generalized linear bandits.

problem Identifying the best drug arm in drug design with minimal trials.

method Proposes an algorithm for best-arm identification in generalized linear bandits, providing theoretical guarantees and simulations.

result First algorithm for best-arm identification in generalized linear bandits with theoretical guarantees.

drug design best arm identification generalized linear bandits minimize trials

2019-05-20abs ↗pdf ↗

HeMPPCAT: Mixtures of Probabilistic Principal Component Analysers for Data with Heteroscedastic Noisestat.ME

HeMPPCAT improves PCA for data with varying noise.

problem PCA's suboptimal performance on data with heterogeneous noise.

method HeMPPCAT uses a GEM algorithm to estimate factors, means, and noise variances.

result Improved factor estimates and clustering accuracy compared to MPPCA.

PCA heteroscedastic noise GEM algorithm factor estimation clustering

2023-01-21abs ↗pdf ↗

Performance of the empirical median for location estimation in heteroscedastic settingsmath.ST

Empirical median performs well in estimating location with varying scales.

problem Estimating location with varying scales in data.

method Analysis of empirical median as an estimator.

result Matching upper and lower bounds on estimation error.

empirical median location estimation heteroscedasticity estimation error robustness

2025-01-28abs ↗pdf ↗

Pricing with Contextual Elasticity and Heteroscedastic Valuationcs.LG

Study online pricing with contextual elasticity and heteroscedastic valuation.

problem Online contextual dynamic pricing with customer decision based on features and price.

method Introduced a novel approach to modeling customer demand with feature-based price elasticity and heteroscedastic noise. Proposed an efficient algorithm called Pricing with Perturbation (PwP).

result Proved an

O(\sqrt{dT\log T})

regret bound for the algorithm, matching a lower bound of

Ω(\sqrt{dT})

dynamic pricing contextual elasticity heteroscedastic valuation regret minimization algorithm

2023-12-26abs ↗pdf ↗

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regressioncs.LG

New method estimates covariance in deep heteroscedastic regression without labels.

problem Estimating covariance in deep heteroscedastic models is challenging due to sample-dependent covariance and lack of ground truth.

method Proposes a self-supervised approach using KL Divergence and 2-Wasserstein distance for covariance estimation and a neighborhood-based heuristic for pseudo labels.

result Demonstrates effective pseudo labels and a computationally cheaper yet accurate deep heteroscedastic regression.

covariance estimation deep heteroscedastic regression self-supervised learning 2-Wasserstein distance KL Divergence

2025-02-14abs ↗pdf ↗