arXiv research

Triangular flows ensure statistical consistency and fast rates in generative modeling.

Stable and consistent model alignment for language models without assuming human preference models.

MIC consistently estimates dependence in large datasets.

Bandit algorithms struggle with consistent performance and robustness.

Novel Orlicz regrets consistently bound environmental variable statistics.

We analyze a family of methods for statistical causal inference from sample under the so-called Additive Noise Model. While most work on the subject has concentrated on establishing the soundness of the Additive Noise Model, the statistical consistency of the resulting inference methods has received little attention. W…

Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.

Unified framework for certifying LLM reliability without extra supervision.

The paper proves statistical consistency and fairness guarantees for a plug-in algorithm.

Estimates dimension of subsets from random samples, proving consistency.

Quick Shift is a popular mode-seeking and clustering algorithm. We present finite sample statistical consistency guarantees for Quick Shift on mode and cluster recovery under mild distributional assumptions. We then apply our results to construct a consistent modal regression algorithm.

Paper addresses statistical inference for GANs and minimax problems.

Paper introduces a neural network for consistent estimation of optimal transport maps.

Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.

Support vector machines (SVMs) are special kernel based methods and belong to the most successful learning methods since more than a decade. SVMs can informally be described as a kind of regularized M-estimators for functions and have demonstrated their usefulness in many complicated real-life problems. During the last…

New theorem for generalized group sparsity improves consistency and convergence rates.

This paper studies statistical estimation in optional regression models.

In the knowledge that the ex-post performance of Markowitz efficient portfolios is inferior to that implied ex-ante, we make two contributions to the portfolio selection literature. Firstly, we propose a methodology to identify the region of risk-expected return space where ex-post performance matches ex-ante estimates…

Subbagging estimation for big data reduces memory usage while maintaining statistical consistency.

This work explains how large neural networks generalize well despite overparameterization.

The massive amount of available data potentially used to discover patters in machine learning is a challenge for kernel based algorithms with respect to runtime and storage capacities. Local approaches might help to relieve these issues. From a statistical point of view local approaches allow additionally to deal with …

Paper provides statistical guarantees for GNNs in link prediction.

Symbolic grounding in causal dynamics achieves near-infinite temporal consistency.

We formalize AURC and develop estimators for SC systems.

Researchers analyze the relationship between ML cost functions and the C-index in survival analysis.

We study the problem of nonparametric dependence detection. Many existing methods may suffer severe power loss due to non-uniform consistency, which we illustrate with a paradox. To avoid such power loss, we approach the nonparametric test of independence through the new framework of binary expansion statistics (BEStat…

Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature approximation, have been proposed to alleviate the problem. However, the statistic…

Paper analyzes consistency of Bayesian and machine learning methods for hierarchical parameter estimation.

Statistical machine learning plays an important role in modern statistics and computer science. One main goal of statistical machine learning is to provide universally consistent algorithms, i.e., the estimator converges in probability or in some stronger sense to the Bayes risk or to the Bayes decision function. Kerne…

Framework generates precise synthetic populations for scalable modeling.

In scientific inference problems, the underlying statistical modeling assumptions have a crucial impact on the end results. There exist, however, only a few automatic means for validating these fundamental modelling assumptions. The contribution in this paper is a general criterion to evaluate the consistency of a set …

Paper introduces new regression methods for consistent estimation of biophysical parameters.

Jackknife variance estimation validated for generalized U-statistics.

Community detection is a fundamental statistical problem in network data analysis. Many algorithms have been proposed to tackle this problem. Most of these algorithms are not guaranteed to achieve the statistical optimality of the problem, while procedures that achieve information theoretic limits for general parameter…

New theory explains consistency of kernel methods with non-i.i.d. data.

Single-step samplers generate high-quality samples efficiently.

This manuscript studies statistical properties of linear classifiers obtained through minimization of an unregularized convex risk over a finite sample. Although the results are explicitly finite-dimensional, inputs may be passed through feature maps; in this way, in addition to treating the consistency of logistic reg…

New approach for distributed learning of Gaussian mixtures.

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…

Modified relative universality for unbiasedness and consistency in dimension reduction.

In stochastic decision problems, one often wants to estimate the underlying probability measure statistically, and then to use this estimate as a basis for decisions. We shall consider how the uncertainty in this estimation can be explicitly and consistently incorporated in the valuation of decisions, using the theory …

Graph-based semi-supervised learning is one of the most popular methods in machine learning. Some of its theoretical properties such as bounds for the generalization error and the convergence of the graph Laplacian regularizer have been studied in computer science and statistics literatures. However, a fundamental stat…

Study improves statistical inference for CATEs using Lasso and DML.

A new family of nonparametric statistics, the r-statistics, is introduced. It consists of counting the number of records of the cumulative sum of the sample. The single-sample r-statistic is almost as powerful as Student's t-statistic for Gaussian and uniformly distributed variables, and more powerful than the sign and…

We lay theoretical foundations for new database release mechanisms that allow third-parties to construct consistent estimators of population statistics, while ensuring that the privacy of each individual contributing to the database is protected. The proposed framework rests on two main ideas. First, releasing (an esti…

Improved estimation of higher order integrals using shrinkage techniques.

SC improves robustness in model comparison for misspecified models.

Label aggregation makes learning robust to noisy labels.