English
Related papers

Related papers: Model non-collapse: Minimax bounds for recursive d…

200 papers

This paper considers a distributionally robust chance constraint model with a general ambiguity set. We show that a sample based approximation of this model converges under suitable sufficient conditions. We also show that upper and lower…

Optimization and Control · Mathematics 2025-01-17 Jiaqi Lei , Sanjay Mehrotra

Discrete flow models offer a powerful framework for learning distributions over discrete state spaces and have demonstrated superior performance compared to the discrete diffusion models. However, their convergence properties and error…

Statistics Theory · Mathematics 2026-05-27 Zhengyan Wan , Yidong Ouyang , Qiang Yao , Liyan Xie , Fang Fang , Hongyuan Zha , Guang Cheng

Synthetic samples from diffusion models are promising for leveraging in training discriminative models as replications of real training datasets. However, we found that the synthetic datasets degrade classification performance over real…

Artificial Intelligence · Computer Science 2023-11-23 Shin'ya Yamaguchi , Takuma Fukuda

Generative models have been successfully used for generating realistic signals. Because the likelihood function is typically intractable in most of these models, the common practice is to use "implicit" models that avoid likelihood…

Machine Learning · Computer Science 2024-05-07 Itai Alon , Amir Globerson , Ami Wiesel

The foundational concept of Max-Margin in machine learning is ill-posed for output spaces with more than two labels such as in structured prediction. In this paper, we show that the Max-Margin loss can only be consistent to the…

Machine Learning · Computer Science 2022-03-22 Alex Nowak-Vila , Alessandro Rudi , Francis Bach

The increasing popularity of regression discontinuity methods for causal inference in observational studies has led to a proliferation of different estimating strategies, most of which involve first fitting non-parametric regression models…

Methodology · Statistics 2018-06-11 Guido Imbens , Stefan Wager

We develop a framework for approximating collapsed Gibbs sampling in generative latent variable cluster models. Collapsed Gibbs is a popular MCMC method, which integrates out variables in the posterior to improve mixing. Unfortunately for…

Machine Learning · Statistics 2018-07-23 Christopher Aicher , Emily B. Fox

The rapid growth of digital devices and IoT has intensified the demand for collaborative learning. Since these devices generate sensitive and high-dimensional data, centralized transmission is often impractical, while local learning suffers…

Signal Processing · Electrical Eng. & Systems 2026-03-03 Nikola Stankovic

In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of distributions, given one \emph{single} sample from each distribution. We study mean estimation and linear…

Machine Learning · Computer Science 2020-07-08 Hui Yuan , Yingyu Liang

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Viet Nguyen , Giang Vu , Tung Nguyen Thanh , Khoat Than , Toan Tran

In experimental design, we are given a large collection of vectors, each with a hidden response value that we assume derives from an underlying linear model, and we wish to pick a small subset of the vectors such that querying the…

Machine Learning · Computer Science 2019-02-05 Michał Dereziński , Kenneth L. Clarkson , Michael W. Mahoney , Manfred K. Warmuth

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the…

Machine Learning · Computer Science 2023-04-03 Matthias De Lange , Gido van de Ven , Tinne Tuytelaars

Using the asymptotical minimax framework, we examine convergence rates equivalency between a continuous functional deconvolution model and its real-life discrete counterpart over a wide range of Besov balls and for the $L^2$-risk. For this…

Statistics Theory · Mathematics 2010-10-06 Marianna Pensky , Theofanis Sapatinas

Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with parallel updates. However, their evaluation is challenging: existing metrics conflate denoiser…

Machine Learning · Computer Science 2026-05-29 Luhan Tang , Longxuan Yu , Shaorong Zhang , Greg Ver Steeg

We consider the problem of estimating the unconditional distribution of a post-model-selection estimator. The notion of a post-model-selection estimator here refers to the combined procedure resulting from first selecting a model (e.g., by…

Statistics Theory · Mathematics 2007-11-08 Hannes Leeb , Benedikt M. Poetscher

Given observations from a circular random variable contaminated by an additive measurement error, we consider the problem of minimax optimal goodness-of-fit testing in a non-asymptotic framework. We propose direct and indirect testing…

Statistics Theory · Mathematics 2020-07-14 Sandra Schluttenhofer , Jan Johannes

This paper is concerned with the detection of multiple change-points in the joint distribution of independent categorical variables. The procedures introduced rely on model selection and are based on a penalized least-squares criterion.…

Statistics Theory · Mathematics 2008-01-08 Nathalie Akakpo

Statistical learning relies upon data sampled from a distribution, and we usually do not care what actually generated it in the first place. From the point of view of causal modeling, the structure of each distribution is induced by…

Machine Learning · Computer Science 2018-09-11 Giambattista Parascandolo , Niki Kilbertus , Mateo Rojas-Carulla , Bernhard Schölkopf

Quantile estimation in deconvolution problems is studied comprehensively. In particular, the more realistic setup of unknown error distributions is covered. Our plug-in method is based on a deconvolution density estimator and is minimax…

Statistics Theory · Mathematics 2016-01-18 Itai Dattner , Markus Reiß , Mathias Trabs

A common approach to statistical learning with big-data is to randomly split it among $m$ machines and learn the parameter of interest by averaging the $m$ individual estimates. In this paper, focusing on empirical risk minimization, or…

Machine Learning · Statistics 2016-06-14 Jonathan Rosenblatt , Boaz Nadler