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.

168,657 papers · 148 categories

Trend · papers per month

67133200266 · Jun 202019922001200920172026
48 results for Frequentist guarantees

The paper analyzes distributed Bayesian inference and its Frequentist guarantees.

problem Analyzing large decentralized datasets with distributed Bayesian inference.
method Establishes Frequentist properties for distributed (non-)Bayesian inference.
result Distributed Bayesian inference retains parametric efficiency and enhances robustness.

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

problem Connecting Bayesian and frequentist approaches in statistical inference.
method Developed a theoretical framework for M-posteriors, showing asymptotic normality and frequentist consistency.
result M-posteriors are robust and contract around M-estimators under mild conditions.

We present two algorithms for Bayesian optimization in the batch feedback setting, based on Gaussian process upper confidence bound and Thompson sampling approaches, along with frequentist regret guarantees and numerical results.

2019-11-04abs ↗pdf ↗

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

problem Theoretical limitations in Bayesian online learning, especially in the one-pass setting.
method Proposed a new Bayesian online learning algorithm with a warm-start phase for the one-pass regime, establishing convergence rates and valid uncertainty quantification.
result The sequentially updated posterior attains optimal convergence rates and valid uncertainty quantification without diverging mini-batch sample sizes.

A new sequential method estimates Poisson means in streaming data, achieving optimality and efficiency.

problem Estimating Poisson means in a streaming, or online, framework.
method A quasi-Bayesian approach based on Newton's algorithm for a sequential estimate.
result Established frequentist guarantees including consistency and asymptotic optimality.

Frequentist method estimates uncertainty in RNNs without altering architecture.

problem Uncertainty quantification in RNNs for decision-making.
method Jackknife resampling and influence functions to estimate variability.
result The method provides theoretical coverage guarantees on uncertainty intervals.

The paper analyzes uncertainty quantification in sparse Gaussian process regression with a Brownian motion prior.

problem Analyzing uncertainty in sparse Gaussian process regression with a Brownian motion prior.
method Theoretical guarantees and limitations for pointwise credible sets are derived for a rescaled Brownian motion prior with a sparse variational Gaussian process method.
result Theoretical characterization of asymptotic frequentist coverage for credible sets, distinguishing conservative and overconfident cases.

WBCP improves conformal prediction for distribution shifts using weighted Dirichlet posteriors.

problem Handling distribution shifts in conformal prediction.
method Generalizes Bayesian Quadrature Conformal Prediction (BQ-CP) to arbitrary importance-weighted settings.
result WBCP maintains coverage guarantees while providing richer uncertainty information.

New rigorous uncertainty bounds for Gaussian Process regression.

problem Need for frequentist uncertainty bounds in applications like learning-based control.
method Introduce new uncertainty bounds that are rigorous and practically useful.
result New bounds are less conservative and more useful for practical applications.

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

problem Efficiently evaluating many LLMs on a large suite of benchmarks is expensive.
method FAQ uses Bayesian factor models, adaptive sampling, and proactive active inference to select queries.
result FAQ delivers up to 5x effective sample size gains over baselines, matching CI width with fewer queries.

Locally Valid and Discriminative prediction intervals for deep learning models.

problem Efficient and theoretically sound uncertainty quantification for deep learning models.
method Locally Valid and Discriminative prediction intervals (LVD) using kernel regression.
result Locally Valid and Discriminative prediction intervals (LVD) offer better performance and scalability compared to existing methods.

New algorithms reduce regret in reinforcement learning with MNL approximations.

problem Efficient reinforcement learning with MNL function approximation for MDPs.
method Proposed randomized exploration algorithms with frequentist regret guarantees.
result Achieved improved regret bounds for MNL transition models.

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

problem Bayesian neural networks struggle in out-of-distribution (OOD) detection tasks.
method Incorporated out-of-distribution data into Bayesian inference through four different methods.
result OOD-trained Bayesian neural networks are competitive with frequentist baselines.

Safe Bayesian Optimization algorithms are improved to ensure safety in real-world applications.

problem Ensuring safety in Bayesian Optimization algorithms for real-world applications.
method Investigated and improved three safety-related issues of SafeOpt-type algorithms: frequentist uncertainty bounds, RKHS norm assumptions, and discrete search spaces.
result Introduced Real-{eta}-SafeOpt, Lipschitz-only Safe Bayesian Optimization (LoSBO), and Lipschitz-only GP-UCB (LoS-GP-UCB) algorithms that retain safety guarantees and superior performance.

The study provides statistical guarantees for Bayesian variational boosting.

problem Statistical and convergence issues in variational boosting.
method Proposed a novel variational family and a functional Frank-Wolfe optimization algorithm.
result Demonstrated stochastic boundedness and provided convergence rate for boosting iterates.

Bayesian algorithm improves best-arm identification within fixed budget.

problem Maximizing probability of identifying optimal arm within fixed budget.
method Proposes Bayesian elimination algorithm and derives upper bound on misidentification probability.
result Upper bound on misidentification probability reflects prior quality and matches lower bound.

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

problem Designing tests with frequentist false discovery rate control using horseshoe prior.
method Frequentist-assisted horseshoe procedure for high-dimensional normal means testing.
result Consistently achieves robust finite-sample FDR control in various sparse cases.

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

problem Intractable likelihood functions in complex systems make classical statistics ineffective for likelihood-free inference.
method Likelihood-Free Frequentist Inference (LF2I) framework that combines classical statistics and machine learning.
result Valid confidence sets with near finite-sample validity can be constructed for any parameter value.

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

problem Statisticians struggle to understand variational inference from a Frequentist perspective.
method Explains VI, VAEs, and DDMs from a Frequentist viewpoint, starting with EM.
result VI emerges as a scalable solution for intractable E-steps in VAEs and DDMs.

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

problem The frequentist regret of Linear Thompson Sampling (LinTS) is worse than its Bayesian counterpart.
method The paper proves the fundamental nature of the frequentist regret bound for LinTS and proposes a data-driven version of LinTS to achieve minimax optimal frequentist regret.
result The frequentist regret bound for LinTS is O~(ddT)\widetilde{\mathcal{O}}(d\sqrt{dT}), which is the best possible under certain conditions.

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

problem Deriving a frequentist regret bound for Thompson sampling in multi-agent settings with sparse hypergraphs.
method Proposed εε-exploring Multi-Agent Thompson Sampling (εε-MATS) algorithm that combines exploration and exploitation strategies.
result Achieves a worst-case frequentist regret bound sublinear in time horizon and local arm size, optimal up to constants and logarithms for sparse hypergraphs.

The study compares Bayesian and frequentist approaches in deep learning.

problem Comparing Bayesian and frequentist inference in deep learning.
method Conducts a comparative analysis of point and posterior estimators across various settings.
result Amortized point estimators generally outperform posterior inference, though posterior inference remains competitive in some low-dimensional problems.

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

problem Estimating the BLP model with reduced bias and improved performance.
method Phrasing BLP as an automatically differentiable moment function, using CUE for estimation, and incorporating MCMC credible intervals.
result CUE estimation shows lower bias but higher MAE compared to 2S-GMM, with MCMC providing closest empirical coverage.

We address the problem of computing reliable policies in reinforcement learning problems with limited data. In particular, we compute policies that achieve good returns with high confidence when deployed. This objective, known as the \emph{percentile criterion}, can be optimized using Robust MDPs~(RMDPs). RMDPs general…

2019-10-23abs ↗pdf ↗

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

problem Inefficient set prediction in conformal prediction for limited training data.
method Meta-learning approach using cross-validation-based conformal prediction.
result Meta-learning scheme reduces set prediction size and preserves formal guarantees.

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…

2017-05-09abs ↗pdf ↗

DBPA assesses LLM perturbations using frequentist hypothesis testing.

problem Quantifying input perturbation impacts on LLM outputs.
method DBPA reformulates perturbation analysis as frequentist hypothesis testing, using Monte Carlo sampling for empirical null and alternative distributions.
result DBPA provides interpretable p-values and scalar effect sizes for LLM perturbations.

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

problem Thompson Sampling's exploration is insufficient in some contexts.
method Developed Feel-Good Thompson Sampling to address exploration issues.
result Feel-Good Thompson Sampling reduces regret compared to standard Thompson Sampling.

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…

2019-11-01abs ↗pdf ↗

Method estimates shared and study-specific factors for multi-study data.

problem Covariance estimation for multi-study data with shared and study-specific components.
method Spectral decomposition for latent factors, surrogate Bayesian regressions for loadings and variances.
result Strong frequentist guarantees and superior performance in simulations and real data.

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

problem Evaluating variability of posterior estimates in Bayesian models.
method Use of Bayesian Infinitesimal Jackknife approximation and W-kernel.
result Principal space of W is central to frequentist evaluation of Bayesian models.

We propose a family of variational approximations to Bayesian posterior distributions, called αα-VB, with provable statistical guarantees. The standard variational approximation is a special case of αα-VB with α=1α=1. When α(0,1]α\in(0,1], a novel class of variational inequalities are developed for linking the Bayes risk …

2017-10-09abs ↗pdf ↗

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…

2015-06-19abs ↗pdf ↗

Thompson sampling for multi-armed bandit problems is known to enjoy favorable performance in both theory and practice. However, it suffers from a significant limitation computationally, arising from the need for samples from posterior distributions at every iteration. We propose two Markov Chain Monte Carlo (MCMC) meth…

2020-02-23abs ↗pdf ↗

A new kernel-based nonconformity score improves multivariate prediction regions.

problem Tackling the challenge of compressing multivariate residual vectors into scalars while preserving geometric structure.
method Introducing a Multivariate Kernel Score (MKS) that decomposes into an anisotropic MMD, providing finite-sample coverage guarantees and convergence rates.
result The MKS produces prediction regions that explicitly adapt to geometric structure, reducing volume compared to ellipsoidal baselines.

We study a variant of the stochastic multi-armed bandit (MAB) problem in which the rewards are corrupted. In this framework, motivated by privacy preservation in online recommender systems, the goal is to maximize the sum of the (unobserved) rewards, based on the observation of transformation of these rewards through a…

2017-08-16abs ↗pdf ↗