English
Related papers

Related papers: A Separation in Heavy-Tailed Sampling: Gaussian vs…

200 papers

A large body of work in the statistics and computer science communities dating back to Huber (Huber, 1960) has led to statistically and computationally efficient outlier-robust estimators. Two particular outlier models have received…

Statistics Theory · Mathematics 2024-11-26 Yeshwanth Cherapanamjeri , Daniel Lee

We study a scalable alternative to robust gradient descent (RGD) techniques that can be used when the gradients can be heavy-tailed, though this will be unknown to the learner. The core technique is simple: instead of trying to robustly…

Machine Learning · Statistics 2020-12-16 Matthew J. Holland

We present an algorithm for simulating a distribution using prefix conditional samples (Adar, Fischer and Levi, 2024), as well as ``prefix-compatible'' conditional models such as the interval model (Cannone, Ron and Servedio, 2015) and the…

Data Structures and Algorithms · Computer Science 2026-04-21 Tomer Adar

Finite sample properties of random covariance-type matrices have been the subject of much research. In this paper we focus on the "lower tail" of such a matrix, and prove that it is subgaussian under a simple fourth moment assumption on the…

Probability · Mathematics 2013-12-11 Roberto Imbuzeiro Oliveira

Bayesian hierarchical models have been demonstrated to provide efficient algorithms for finding sparse solutions to ill-posed inverse problems. The models comprise typically a conditionally Gaussian prior model for the unknown, augmented by…

Numerical Analysis · Mathematics 2023-03-31 Daniela Calvetti , Erkki Somersalo

Understanding the complexity of sampling from a strongly log-concave and log-smooth distribution $\pi$ on $\mathbb{R}^d$ to high accuracy is a fundamental problem, both from a practical and theoretical standpoint. In practice, high-accuracy…

Statistics Theory · Mathematics 2023-02-22 Jason M. Altschuler , Sinho Chewi

Gaussian boson sampling (GBS) is a promising protocol for demonstrating quantum computational advantage. One of the key steps for proving classical hardness of GBS is the so-called ``hiding conjecture'', which asserts that one can ``hide''…

Quantum Physics · Physics 2025-09-03 Laura Shou , Sarah H. Miller , Victor Galitski

We revisit the sample and computational complexity of completing a rank-1 tensor in $\otimes_{i=1}^{N} \mathbb{R}^{d}$, given a uniformly sampled subset of its entries. We present a characterization of the problem (i.e. nonzero entries)…

Data Structures and Algorithms · Computer Science 2024-08-21 Alejandro Gomez-Leos , Oscar López

This paper proposes a new robust smooth-threshold estimating equation to select important variables and automatically estimate parameters for high dimensional longitudinal data. A novel working correlation matrix is proposed to capture…

Methodology · Statistics 2021-11-30 Liya Fu , Jiaqi Li , You-Gan Wang

We initiate the study of stochastic optimization with oblivious noise, broadly generalizing the standard heavy-tailed noise setup. In our setting, in addition to random observation noise, the stochastic gradient may be subject to…

Data Structures and Algorithms · Computer Science 2024-08-06 Ilias Diakonikolas , Sushrut Karmalkar , Jongho Park , Christos Tzamos

In this paper we analyze the necessary number of samples to estimate the gradient of any multidimensional smooth (possibly non-convex) function in a zero-order stochastic oracle model. In this model, an estimator has access to noisy values…

Machine Learning · Computer Science 2021-07-07 Abdulrahman Alabdulkareem , Jean Honorio

The paper suggests a simple method of deriving minimax lower bounds to the accuracy of statistical inference on heavy tails. A well-known result by Hall and Welsh (Ann. Statist. 12 (1984) 1079-1084) states that if $\hat{\alpha}_n$ is an…

Statistics Theory · Mathematics 2014-03-14 S. Y. Novak

Uniform sampling is a highly efficient method for data summarization. However, its effectiveness in producing coresets for clustering problems is not yet well understood, primarily because it generally does not yield a strong coreset, which…

Data Structures and Algorithms · Computer Science 2026-02-19 Amir Carmel , Robert Krauthgamer

We provide sample complexity upper bounds for agnostically learning multivariate Gaussians under the constraint of approximate differential privacy. These are the first finite sample upper bounds for general Gaussians which do not impose…

Machine Learning · Statistics 2020-10-21 Ishaq Aden-Ali , Hassan Ashtiani , Gautam Kamath

We consider the problem of inferring a latent function in a probabilistic model of data. When dependencies of the latent function are specified by a Gaussian process and the data likelihood is complex, efficient computation often involve…

Machine Learning · Statistics 2018-07-23 Martin Tegner , Benjamin Bloem-Reddy , Stephen Roberts

We propose an efficient way to sample from a class of structured multivariate Gaussian distributions which routinely arise as conditional posteriors of model parameters that are assigned a conditionally Gaussian prior. The proposed…

Computation · Statistics 2016-06-28 Anirban Bhattacharya , Antik Chakraborty , Bani K. Mallick

Randomized smoothing is a popular way of providing robustness guarantees against adversarial attacks: randomly-smoothed functions have a universal Lipschitz-like bound, allowing for robustness certificates to be easily computed. In this…

Machine Learning · Computer Science 2020-12-16 Alexander Levine , Aounon Kumar , Thomas Goldstein , Soheil Feizi

Gaussian processes are frequently deployed as part of larger machine learning and decision-making systems, for instance in geospatial modeling, Bayesian optimization, or in latent Gaussian models. Within a system, the Gaussian process model…

We show that a tessellation generated by a small number of random affine hyperplanes can be used to approximate Euclidean distances between any two points in an arbitrary bounded set $T$, where the random hyperplanes are generated by…

Information Theory · Computer Science 2018-08-14 Sjoerd Dirksen , Shahar Mendelson

We address numerical differentiation under coarse, non-uniform sampling and Gaussian noise. A maximum-likelihood estimator with $L_2$-norm constraint on a higher-order derivative is obtained, yielding spline-based solution. We introduce a…

Methodology · Statistics 2025-07-31 Konstantin E. Avrachenkov , Leonid B. Freidovich