arXiv research

Unified method for estimating properties of large domain distributions efficiently.

Paper offers a framework for estimating symmetric properties efficiently.

Estimating properties of discrete distributions is a fundamental problem in statistical learning. We design the first unified, linear-time, competitive, property estimator that for a wide class of properties and for all underlying distributions uses just $2n$ samples to achieve the performance attained by the empirical…

New graph properties inherited by Frechet mean and median.

The study examines property testing and estimation under non-identically distributed samples, finding necessary and sufficient sample complexities.

This paper studies how key tensor properties are inherited in subtensors of tensor train decompositions.

The best-known and most commonly used distribution-property estimation technique uses a plug-in estimator, with empirical frequency replacing the underlying distribution. We present novel linear-time-computable estimators that significantly "amplify" the effective amount of data available. For a large variety of distri…

Develops Active Fourier Auditor to estimate ML model properties without reconstructing them.

Unified plug-in approach for estimating symmetric properties of distributions efficiently.

The paper tests properties of multiple distributions with limited samples.

The paper establishes conditions for optimal sampling configurations on complex manifolds.

We present a novel condition, which we term the net- work nullspace property, which ensures accurate recovery of graph signals representing massive network-structured datasets from few signal values. The network nullspace property couples the cluster structure of the underlying network-structure with the geometry of th…

The performance of a machine learning system is usually evaluated by using i.i.d.\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaining unlabeled samples may be cheaper. Stratified sampling can be beneficial in such settings and can reduce the number of true labels require…

We give a proof of the sublinear tracking property for sample paths of random walks on various groups acting on spaces with hyperbolic-like properties. As an application, we prove sublinear tracking in Teichmueller distance for random walks on mapping class groups, and on Cayley graphs of a large class of finitely gene…

New method speeds up sampling of Markov random fields.

One of the most fundamental concepts in statistics is the concept of sample mean. Properties of the sample mean that are well-defined in Euclidean spaces become unwieldy or even unclear in graph spaces. Open problems related to the sample mean of graphs include: non-existence, non-uniqueness, statistical inconsistency,…

We study three fundamental statistical-learning problems: distribution estimation, property estimation, and property testing. We establish the profile maximum likelihood (PML) estimator as the first unified sample-optimal approach to a wide range of learning tasks. In particular, for every alphabet size $k$ and desired…

Validates conformal prediction for network data under non-uniform sampling.

WeSpeR speeds up non-linear shrinkage for high-dimensional weighted covariance.

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

Proposes a new method for joint sample and feature selection in multi-view data.

Generative neural network designs novel 3D molecules with specified properties.

Optimization algorithms and Monte Carlo sampling algorithms have provided the computational foundations for the rapid growth in applications of statistical machine learning in recent years. There is, however, limited theoretical understanding of the relationships between these two kinds of methodology, and limited unde…

This work investigates the properties of Gaussian-smoothed sliced divergences for comparing distributions.

Improves MCMC performance with adaptive affine transformations.

SGD improves DR by solving two-stage sampling problems.

Develops a two-sample test using projected Wasserstein distance to handle high-dimensional data.

Diffusion models generate new samples with active guidance, but theory is limited.

The paper tackles uniform sampling from databases with duplicates.

Optimal testing of discrete distributions with high probability, achieving sample complexity bounds.

New method relaxes TV distance for two-sample testing without distributional assumptions.

We study finite sample properties of estimators of power-law cross-correlations -- detrended cross-correlation analysis (DCCA), height cross-correlation analysis (HXA) and detrending moving-average cross-correlation analysis (DMCA) -- with a special focus on short-term memory bias as well as power-law coherency. Presen…

When faced with a data set too large to be processed all at once, an obvious solution is to retain only part of it. In practice this takes a wide variety of different forms, and among them "coresets" are especially appealing. A coreset is a (small) weighted sample of the original data that comes with the following guar…

Flexible framework integrates machine learning and DRO for uncertain parameter prediction.

Evaluating generative adversarial networks (GANs) is inherently challenging. In this paper, we revisit several representative sample-based evaluation metrics for GANs, and address the problem of how to evaluate the evaluation metrics. We start with a few necessary conditions for metrics to produce meaningful scores, su…

New metric detects adversarial samples with high accuracy.

Deep learning speeds up material property quantification using stress waves.

Method for conditional sampling with pre-trained normalizing flows.

Topological constraints improve neural network generalization.

While the Matrix Generalized Inverse Gaussian ($\mathcal{MGIG}$) distribution arises naturally in some settings as a distribution over symmetric positive semi-definite matrices, certain key properties of the distribution and effective ways of sampling from the distribution have not been carefully studied. In this paper…

Magnetic manifold HMC improves sampling on constrained manifolds.

New algorithm reduces sample complexity for Top Two method.

Algorithm infers sampling distribution from i.i.d. samples without supervision.

This paper analyzes statistical properties of the Robust Satisficing model.

The paper analyzes error bounds and KL properties for noisy matrix recovery problems.

New algorithm learns LQR with $O(\sqrt{T})$ regret using Langevin dynamics and excitation.

Network sampling is integral to the analysis of social, information, and biological networks. Since many real-world networks are massive in size, continuously evolving, and/or distributed in nature, the network structure is often sampled in order to facilitate study. For these reasons, a more thorough and complete unde…

Algorithm distinguishes light-tailed from non-light-tailed distributions.