College of LAS Events

View Full Calendar

If you will need disability-related accommodations in order to participate, please email the contact person for the event.
Early requests are strongly encouraged to allow sufficient time to meet your access needs.

Statistics Seminar - Yun Yang (UIUC) "Generative Models for Implicit Distribution Estimation: a Statistical Perspective"

Event Type
Seminar/Symposium
Sponsor
Department of Statistics
Location
1306 Everitt Lab
Date
Mar 7, 2024   3:30 pm  
Views
132
Originating Calendar
Department of Statistics Event Calendar

Title: Generative Models for Implicit Distribution Estimation: a Statistical Perspective

Abstract: The estimation of distributions of complex objects from high-dimensional data with low-dimensional structures is an important topic in statistics and machine learning. Modern generative modeling techniques accomplish this by encoding and decoding data to generate new, realistic synthetic data objects, including images and texts. A key aspect of these models is the extraction of low-dimensional latent features, assuming the data lies on a low-dimensional manifold. Our study develops a minimax framework for distribution estimation on unknown submanifolds, incorporating smoothness assumptions on both the target distribution and the manifold. Through the perspective of minimax rates, we examine some existing popular generative models, such as variational autoencoders, generative adversarial networks, and score-based generative models. By analyzing their theoretical properties, we characterize their statistical capabilities in implicit distribution estimation and identify certain limitations that could lead to potential improvements.

link for robots only