English
Related papers

Related papers: Asymptotic Guarantees for Learning Generative Mode…

200 papers

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

Statistics Theory · Mathematics 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

We propose a new statistical model, the spiked transport model, which formalizes the assumption that two probability distributions differ only on a low-dimensional subspace. We study the minimax rate of estimation for the Wasserstein…

Statistics Theory · Mathematics 2019-09-18 Jonathan Niles-Weed , Philippe Rigollet

We propose an adjusted Wasserstein distributionally robust estimator -- based on a nonlinear transformation of the Wasserstein distributionally robust (WDRO) estimator in statistical learning. The classic WDRO estimator is asymptotically…

Machine Learning · Statistics 2024-05-13 Yiling Xie , Xiaoming Huo

Networks are popular for representing complex data. In particular, differentially private synthetic networks are much in demand for method and algorithm development. The network generator should be easy to implement and should come with…

Machine Learning · Statistics 2025-02-18 Leoni Carla Wirth , Gholamali Aminian , Gesine Reinert

This paper studies the optimization of the KL functional on the Wasserstein space of probability measures, and develops a sampling framework based on Wasserstein gradient descent (WGD). We identify two important subclasses of the…

Computation · Statistics 2026-02-04 Van Chien Ta , Thi Mai Hong Chu , Minh-Ngoc Tran

Data-driven methods for the solution of inverse problems have become widely popular in recent years thanks to the rise of machine learning techniques. A popular approach concerns the training of a generative model on additional data to…

Machine Learning · Statistics 2026-03-12 Bamdad Hosseini , Ziqi Huang

Although generative diffusion models (GDMs) are widely used in practice, their theoretical foundations remain limited, especially concerning the impact of different discretization schemes applied to the underlying stochastic differential…

Numerical Analysis · Mathematics 2026-01-27 Emanuel Pfarr , Radu Timofte , Frank Werner

We study rates of convergence for estimation of the Gromov-Wasserstein (GW) distance. For two marginals supported on compact subsets of $\R^{d_x}$ and $\R^{d_y}$, respectively, with $\min \{ d_x,d_y \} > 4$, prior work established the rate…

Statistics Theory · Mathematics 2025-09-03 Kengo Kato , Boyu Wang

Simulation-based inference (SBI) enables amortized Bayesian inference by first training a neural posterior estimator (NPE) on prior-simulator pairs, typically through low-dimensional summary statistics, which can then be cheaply reused for…

Machine Learning · Statistics 2026-02-11 Sherman Khoo , Dennis Prangle , Song Liu , Mark Beaumont

A growing number of generative statistical models do not permit the numerical evaluation of their likelihood functions. Approximate Bayesian computation (ABC) has become a popular approach to overcome this issue, in which one simulates…

Methodology · Statistics 2019-05-10 Espen Bernton , Pierre E. Jacob , Mathieu Gerber , Christian P. Robert

Statistical distances (SDs), which quantify the dissimilarity between probability distributions, are central to machine learning and statistics. A modern method for estimating such distances from data relies on parametrizing a variational…

Statistics Theory · Mathematics 2021-03-18 Sreejith Sreekumar , Zhengxin Zhang , Ziv Goldfeld

We present the first minimax risk bounds for estimators of the spectral measure in multivariate linear factor models, where observations are linear combinations of regularly varying latent factors. Non-asymptotic convergence rates are…

Statistics Theory · Mathematics 2024-11-12 Xuhui Zhang , Jose Blanchet , Youssef Marzouk , Viet Anh Nguyen , Sven Wang

We investigate the asymptotic behavior of parametric Bayes estimators under a broad class of loss functions that extend beyond the classical translation-invariant setting. To this end, we develop a unified theoretical framework for loss…

Statistics Theory · Mathematics 2026-03-16 Robin Requadt , Housen Li , Axel Munk

We analyze a number of natural estimators for the optimal transport map between two distributions and show that they are minimax optimal. We adopt the plugin approach: our estimators are simply optimal couplings between measures derived…

Statistics Theory · Mathematics 2024-06-18 Tudor Manole , Sivaraman Balakrishnan , Jonathan Niles-Weed , Larry Wasserman

This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples. Our main results establish the convergence rates of GANs under a collection of integral probability metrics defined…

Machine Learning · Computer Science 2022-06-10 Jian Huang , Yuling Jiao , Zhen Li , Shiao Liu , Yang Wang , Yunfei Yang

Score-based generative models (SGMs) aim at estimating a target data distribution by learning score functions using only noise-perturbed samples from the target.Recent literature has focused extensively on assessing the error between the…

Statistics Theory · Mathematics 2025-01-28 Stanislas Strasman , Antonio Ocello , Claire Boyer , Sylvain Le Corff , Vincent Lemaire

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family…

Machine Learning · Statistics 2020-02-19 Ziyu Wang , Shuyu Cheng , Yueru Li , Jun Zhu , Bo Zhang

Distance measures between graphs are important primitives for a variety of learning tasks. In this work, we describe an unsupervised, optimal transport based approach to define a distance between graphs. Our idea is to derive…

Computational Engineering, Finance, and Science · Computer Science 2024-04-11 Michael Scholkemper , Damin Kühn , Gerion Nabbefeld , Simon Musall , Björn Kampa , Michael T. Schaub

We consider distributed statistical optimization in one-shot setting, where there are $m$ machines each observing $n$ i.i.d. samples. Based on its observed samples, each machine sends a $B$-bit-long message to a server. The server then…

Machine Learning · Computer Science 2020-01-01 Saber Salehkaleybar , Arsalan Sharifnassab , S. Jamaloddin Golestani

The problem of learning functions over spaces of probabilities - or distribution regression - is gaining significant interest in the machine learning community. A key challenge behind this problem is to identify a suitable representation…

Machine Learning · Statistics 2022-06-20 Dimitri Meunier , Massimiliano Pontil , Carlo Ciliberto