activity
20242026
collaborators

10 papers

cs.LG2026

Ambient Dataloops: Generative Models for Dataset Refinement

Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans +3

We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets cont…

cs.LG2025

Estimating Ising Models in Total Variation Distance

Constantinos Daskalakis, Vardis Kandiros, Rui Yao

We consider the problem of estimating Ising models over variables in Total Variation (TV) distance, given independent samples from the model. While the statistical complexi…

cs.LG2025

Learning Gaussian DAG Models without Condition Number Bounds

Constantinos Daskalakis, Vardis Kandiros, Rui Yao

We study the problem of learning the topology of a directed Gaussian Graphical Model under the equal-variance assumption, where the graph has nodes and maximum in-degree . P…

cs.LG2025

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization

Danial Hosseintabar, Fan Chen, Giannis Daras +2

Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains…

cs.GR2025

Ambient Diffusion Omni: Training Good Models with Bad Data

Giannis Daras, Adrian Rodriguez-Munoz, Adam Klivans +2

We show how to use low-quality, synthetic, and out-of-distribution images to improve the quality of a diffusion model. Typically, diffusion models are trained on curated datasets t…

cs.LG2025

Learning High-dimensional Gaussians from Censored Data

Arnab Bhattacharyya, Constantinos Daskalakis, Themis Gouleakis +1

We provide efficient algorithms for the problem of distribution learning from high-dimensional Gaussian data where in each sample, some of the variable values are missing. We suppo…