YoVDO

Towards Understanding Generalization Properties of Score-Based Losses

Offered By: Simons Institute via YouTube

Tags

Generative Models Courses Discrete Probability Distributions Courses Energy-Based Models Courses Diffusion Models Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a comprehensive lecture on the generalization properties of score-based losses in machine learning. Delve into the comparison between score-based losses and maximum likelihood for fitting probabilistic generative models with intractable likelihoods. Examine the trade-offs between computational tractability and statistical efficiency. Investigate the emerging connection between statistical efficiency of generalized score losses and the algorithmic efficiency of diffusion-based sampling algorithms. Learn about the design space for score losses with favorable statistical behavior, drawing parallels to techniques for accelerating Markov chain convergence. Discover the analogous story for learning discrete probability distributions using masked prediction-like losses. Gain insights into the current state and future prospects of generative model theory, covering both short-term and long-term perspectives.

Syllabus

Towards Understanding Generalization Properties of Score-Based Losses


Taught by

Simons Institute

Related Courses

A Path Towards Autonomous Machine Intelligence - Paper Explained
Yannic Kilcher via YouTube
Author Interview - VOS- Learning What You Don't Know by Virtual Outlier Synthesis
Yannic Kilcher via YouTube
Self-Supervised Learning - The Dark Matter of Intelligence
Yannic Kilcher via YouTube
Backpropagation and Deep Learning in the Brain
Simons Institute via YouTube
On the Critic Function of Implicit Generative Models - Arthur Gretton
Institute for Advanced Study via YouTube