English
Related papers

Related papers: Contrastive Moments: Unsupervised Halfspace Learni…

200 papers

We present a framework that allows for the non-asymptotic study of the $2$-Wasserstein distance between the invariant distribution of an ergodic stochastic differential equation and the distribution of its numerical approximation in the…

Machine Learning · Statistics 2021-09-27 J. M. Sanz-Serna , Konstantinos C. Zygalakis

Sample- and computationally-efficient distribution estimation is a fundamental tenet in statistics and machine learning. We present SURF, an algorithm for approximating distributions by piecewise polynomials. SURF is: simple, replacing…

Machine Learning · Statistics 2021-02-15 Yi Hao , Ayush Jain , Alon Orlitsky , Vaishakh Ravindrakumar

Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation . However, most existing SSL methods predict pixels in a single image…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Lu Wen , Zhenghao Feng , Yun Hou , Peng Wang , Xi Wu , Jiliu Zhou , Yan Wang

We study active learning of homogeneous $s$-sparse halfspaces in $\mathbb{R}^d$ under the setting where the unlabeled data distribution is isotropic log-concave and each label is flipped with probability at most $\eta$ for a parameter $\eta…

Machine Learning · Computer Science 2021-08-16 Chicheng Zhang , Jie Shen , Pranjal Awasthi

In many applications, data is collected in batches, some of which are corrupt or even adversarial. Recent work derived optimal robust algorithms for estimating discrete distributions in this setting. We consider a general framework of…

Machine Learning · Statistics 2020-02-26 Ayush Jain , Alon Orlitsky

We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space from both paired and…

Machine Learning · Statistics 2026-03-05 Kwong Yu Chong , Long Feng

Sampling from a high-dimensional distribution is a fundamental task in statistics, engineering, and the sciences. A canonical approach is the Langevin Algorithm, i.e., the Markov chain for the discretized Langevin Diffusion. This is the…

Statistics Theory · Mathematics 2022-11-01 Jason M. Altschuler , Kunal Talwar

Approximating distributions from their samples is a canonical statistical-learning problem. One of its most powerful and successful modalities approximates every distribution to an $\ell_1$ distance essentially at most a constant times…

Machine Learning · Statistics 2022-06-22 Yi Hao , Ayush Jain , Alon Orlitsky , Vaishakh Ravindrakumar

Large crossed data sets, described by generalized linear mixed models, have become increasingly common and provide challenges for statistical analysis. At very large sizes it becomes desirable to have the computational costs of estimation,…

Methodology · Statistics 2017-06-15 Katelyn Gao , Art B. Owen

In this paper, contrast-independent partially explicit time discretization for wave equations in heterogeneous high-contrast media via mass lumping is concerned. By employing a mass lumping scheme to diagonalize the mass matrix, the matrix…

Numerical Analysis · Mathematics 2025-02-25 Shu Fan Li , Wing Tat Leung

We give a polynomial time algorithm for the lossy population recovery problem. In this problem, the goal is to approximately learn an unknown distribution on binary strings of length $n$ from lossy samples: for some parameter $\mu$ each…

Data Structures and Algorithms · Computer Science 2013-07-11 Ankur Moitra , Michael Saks

We propose a structure of a semiparametric two-component mixture model when one component is parametric and the other is defined through L-moments conditions. Estimation of a two-component mixture model with an unknown component is very…

Methodology · Statistics 2017-12-22 Diaa Al Mohamad

We study efficient algorithms for linear regression and covariance estimation in the absence of Gaussian assumptions on the underlying distributions of samples, making assumptions instead about only finitely-many moments. We focus on how…

We give the first polynomial time algorithm for \emph{list-decodable covariance estimation}. For any $\alpha > 0$, our algorithm takes input a sample $Y \subseteq \mathbb{R}^d$ of size $n\geq d^{\mathsf{poly}(1/\alpha)}$ obtained by…

Data Structures and Algorithms · Computer Science 2022-06-23 Misha Ivkov , Pravesh K. Kothari

The problem of generating random samples of high-dimensional posterior distributions is considered. The main results consist of non-asymptotic computational guarantees for Langevin-type MCMC algorithms which scale polynomially in key…

Statistics Theory · Mathematics 2022-03-25 Richard Nickl , Sven Wang

Unsupervised dimensionality reduction is one of the commonly used techniques in the field of high dimensional data recognition problems. The deep autoencoder network which constrains the weights to be non-negative, can learn a low…

Computer Vision and Pattern Recognition · Computer Science 2020-09-18 Anyong Qin , Zhaowei Shang , Zhuolin Tan , Taiping Zhang , Yuan Yan Tang

We study three problems that involve identifying homogeneous halfspaces under Gaussian distributions: agnostic learning, one-sided reliable learning, and fairness auditing. In each of these problems, we are given labeled examples…

Machine Learning · Computer Science 2026-04-30 Jizhou Huang , Brendan Juba

Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the…

Machine Learning · Computer Science 2015-03-11 Rong Ge , Qingqing Huang , Sham M. Kakade

Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled training examples, unlabeled test examples, and must make…

Data Structures and Algorithms · Computer Science 2026-05-19 Gautam Chandrasekaran , Georgios Gkrinias , Adam R. Klivans , Konstantinos Stavropoulos , Arsen Vasilyan

We revisit the problem of learning from untrusted batches introduced by Qiao and Valiant [QV17]. Recently, Jain and Orlitsky [JO19] gave a simple semidefinite programming approach based on the cut-norm that achieves essentially…

Machine Learning · Computer Science 2020-06-09 Sitan Chen , Jerry Li , Ankur Moitra