arXiv research

Bayesian UQ matches frequentist UQ for adaptively collected data.

Bayesian inference corrected for bias in high-dimensional models.

OOD-trained Bayesian neural networks perform similarly to frequentist methods in uncertainty quantification.

Bayesian online learning algorithm for one-pass data, achieving frequentist validity and uncertainty quantification.

FAB-PPI uses prior knowledge to improve prediction-powered inference.

Unified taxonomy for ML uncertainty in physics, validated.

A new framework bridges classical and machine learning methods for reliable inference from complex models.

Simplifies inference for simulators with or without tractable likelihoods.

Locally Valid and Discriminative prediction intervals for deep learning models.

FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.

Flexible method for estimating frequencies in large datasets using sketching.

Novel quasi-Bayesian method for IV regression using machine learning models.

This work proposes a model averaging method for SVM that avoids redundant covariates and achieves asymptotic optimality.

Theoretical framework for M-posteriors connects Bayesian and frequentist statistics.

Proposes a new method to control FDR using frequentist-assisted horseshoe for high-dimensional testing.

Two models predict net loan losses using Bayesian and frequentist regression.

We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (possibly with overlap across learners) but each trained classifier can be evaluated on a validation dataset. We propose a new approach to aggre…

This paper bridges statistical and machine learning approaches to variational inference.

The paper addresses frequentist regret of Linear Thompson Sampling in stochastic linear bandits.

New method estimates model uncertainty in regression.

The paper analyzes distributed Bayesian inference and its Frequentist guarantees.

A new algorithm reduces frequentist regret in multi-agent bandit problems with sparse hypergraphs.

The study compares Bayesian and frequentist approaches in deep learning.

The machine learning community adopted the use of null hypothesis significance testing (NHST) in order to ensure the statistical validity of results. Many scientific fields however realized the shortcomings of frequentist reasoning and in the most radical cases even banned its use in publications. We should do the same…

Meta-learning reduces set prediction size in conformal prediction for few-shot calibration.

Automatically differentiable estimation for BLP model reduces bias in demand estimation.

FreB protocol uses AI to infer hidden parameters with valid confidence regions.

A key challenge for modern Bayesian statistics is how to perform scalable inference of posterior distributions. To address this challenge, variational Bayes (VB) methods have emerged as a popular alternative to the classical Markov chain Monte Carlo (MCMC) methods. VB methods tend to be faster while achieving comparabl…

DBPA assesses LLM perturbations using frequentist hypothesis testing.

Improved Thompson Sampling reduces regret in contextual bandits and reinforcement learning.

Scores measure certainty and doubt in classification predictions.

We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfeasible and some form of function approximation is mandatory. In this paper, we introduce an optimistically-initialized variant of the popula…

Frequentist method estimates uncertainty in RNNs without altering architecture.

Study evaluates posterior covariance matrix W for frequentist evaluation of Bayesian estimators.

We have recently proposed a new information-based approach to model selection, the Frequentist Information Criterion (FIC), that reconciles information-based and frequentist inference. The purpose of this current paper is to provide a simple example of the application of this criterion and a demonstration of the natura…

Gaussian Process Regression and Kernel Ridge Regression are popular nonparametric regression approaches. Unfortunately, they suffer from high computational complexity rendering them inapplicable to the modern massive datasets. To that end a number of approximations have been suggested, some of them allowing for a distr…

Gaussian process (GP) regression is a powerful interpolation technique due to its flexibility in capturing non-linearity. In this paper, we provide a general framework for understanding the frequentist coverage of point-wise and simultaneous Bayesian credible sets in GP regression. As an intermediate result, we develop…

A new framework uses matrix flows to unify frequentist and Bayesian approaches for sparse GGMs.

Efficient classifier with uncertainty bounds for safety-critical applications.

This paper develops a new method for online density estimation from noisy data.

Deep ensembles effectively capture epistemic uncertainty through training stochasticity, providing a frequentist perspective.

We introduce a novel uncertainty estimation for classification tasks for Bayesian convolutional neural networks with variational inference. By normalizing the output of a Softplus function in the final layer, we estimate aleatoric and epistemic uncertainty in a coherent manner. The intractable posterior probability dis…

Lecture notes on reinforcement learning using statistical methods.

Unified framework for Bayesian and Frequentist statistics.

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

Bayes optimal algorithm under certain conditions doesn't achieve exponential simple regret.

New method provides valid confidence intervals for spatial associations.

Paper discusses optimal CP for second-order predictions.