arXiv research

A new strategy for identifying the best arm in Gaussian bandits with improved exploration.

New oracles improve stochastic optimization with noisy or biased measurements.

This paper analyzes error bounds for biased SMC samplers in conditional sampling.

The paper proposes methods to estimate MCMC quality with couplings, bounding Wasserstein distance.

To improve the efficiency of Monte Carlo estimation, practitioners are turning to biased Markov chain Monte Carlo procedures that trade off asymptotic exactness for computational speed. The reasoning is sound: a reduction in variance due to more rapid sampling can outweigh the bias introduced. However, the inexactness …

The paper develops methods to estimate the high-dimensional efficient frontier without distributional assumptions.

Resampling outperforms reweighting for correcting biased data in machine learning models.

LinUCB algorithm handles adaptive sampling biases for linear bandits.

The paper analyzes the randomized midpoint method for Langevin diffusions, revealing biases and asymptotic properties.

Stochastic EM with biased MCMC improves inference stability.

New method estimates nested expectations with biased and antithetic sampling.

The asymptotic behavior of the stochastic gradient algorithm with a biased gradient estimator is analyzed. Relying on arguments based on the dynamic system theory (chain-recurrence) and the differential geometry (Yomdin theorem and Lojasiewicz inequality), tight bounds on the asymptotic bias of the iterates generated b…

New algorithm improves convergence of Bayesian inference.

High-dimensional inference for sparse spectral precision matrices

Method samples triangulations of manifolds using biased random walks.

This work analyzes IRM and ERM from sample complexity perspective, revealing different behaviors under various distribution shifts.

The paper tackles sampling biases by ensuring minority groups are adequately represented in training data.

Entity resolution (ER) presents unique challenges for evaluation methodology. While crowdsourcing platforms acquire ground truth, sound approaches to sampling must drive labelling efforts. In ER, extreme class imbalance between matching and non-matching records can lead to enormous labelling requirements when seeking s…

Biased sampling and missing data complicates statistical problems ranging from causal inference to reinforcement learning. We often correct for biased sampling of summary statistics with matching methods and importance weighting. In this paper, we study nearest neighbor matching (NNM), which makes estimates of populati…

In many applications, different populations are compared using data that are sampled in a biased manner. Under sampling biases, standard methods that estimate the difference between the population means yield unreliable inferences. Here we develop an inference method that is resilient to sampling biases and is able to …

Improved estimator reduces bias in statistical learning models.

We study high-dimensional Gaussian mixture classification using statistical physics methods.

This paper analyzes SGD with biased gradients for deep learning models.

New method identifies parameters of wider shallow neural networks with biases.

The study addresses biases in evaluating molecular optimization methods and proposes methods to reduce these biases.

This paper presents the nonparametric inference for nonlinear volatility functionals of general multivariate Itô semimartingales, in high-frequency and noisy setting. Pre-averaging and truncation enable simultaneous handling of noise and jumps. Second-order expansion reveals explicit biases and a pathway to bias correc…

Approximate Markov chain Monte Carlo (MCMC) offers the promise of more rapid sampling at the cost of more biased inference. Since standard MCMC diagnostics fail to detect these biases, researchers have developed computable Stein discrepancy measures that provably determine the convergence of a sample to its target dist…

The paper tackles bandit problems with biased offline data by using causal methods.

SA-GFN corrects biases in GFlowNets due to graph symmetries.

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

Asynchronous stochastic approximations (SAs) are an important class of model-free algorithms, tools and techniques that are popular in multi-agent and distributed control scenarios. To counter Bellman's curse of dimensionality, such algorithms are coupled with function approximations. Although the learning/ control pro…

Study reveals biases in gradient descent for GLNs, improving neural network performance.

In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimension, low-sample-size (HDLSS) settings. We show that the hard-margin linear SVM holds a consistency property in which misclassification rates tend to zero as the dimension goes to infinity under certain severe conditions. …

Proposes methods to learn from biased samples, ensuring robust decision rules.

A new biased gradient descent method for conditional stochastic optimization.

We study how the round-off (or discretization) error changes the statistical properties of a Gaussian long memory process. We show that the autocovariance and the spectral density of the discretized process are asymptotically rescaled by a factor smaller than one, and we compute exactly this scaling factor. Consequentl…

Study reveals biases in ImageNet models are not sufficient for generalization.

We study the convergence rate of stochastic optimization of exact (NP-hard) objectives, for which only biased estimates of the gradient are available. We motivate this problem in the context of learning the structure and parameters of Ising models. We first provide a convergence-rate analysis of deterministic errors fo…

The paper analyzes time-dependent streaming data with biased gradient estimates and proposes improved stochastic optimization methods.

Paper proposes a method to use in silico experiments with foundation models to reduce sample size.

Bayesian model explains and improves black-box estimators for class distribution.

A new method for adaptive experiments improves inference.

New method constructs confidence bands for ODE models with unknown regulatory effects.

Theoretical analysis of CNNs' inductive biases and their efficiency in approximating functions.

Strong inductive biases prevent harmless interpolation in overparameterized models.

This study examines biases in flow matching samplers using finite-sample estimation.

We propose a robust inferential procedure for assessing uncertainties of parameter estimation in high-dimensional linear models, where the dimension $p$ can grow exponentially fast with the sample size $n$. Our method combines the de-biasing technique with the composite quantile function to construct an estimator that …

We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or inefficient. Focusing on the latter, we show that a specific class of attacks, Boundary …