Generative Modeling by Estimating Gradients of the Data Distribution
With Stefano Ermon (Stanford University)
Generative Modeling by Estimating Gradients of the Data Distribution
Existing generative models are typically based on explicit representations of probability distributions (e.g., autoregressive or VAEs) or implicit sampling procedures (e.g., GANs). We propose an alternative approach based on modeling directly the vector field of gradients of the data distribution (scores). Our framework allows flexible architectures, requires no sampling during training or the use of adversarial training methods. Additionally, score-based generative models enable exact likelihood evaluation through connections with normalizing flows. We produce samples comparable to GANs, achieving new state-of-the-art inception scores, and competitive likelihoods on image datasets.
Join Zoom Meeting
https://maths-cam-ac-uk.zoom.us/j/94812219444?pwd=K00vZUVUU2NDbHozR2h1UzdLRlI1QT09
Meeting ID: 948 1221 9444
Passcode: 485548
- Speaker: Stefano Ermon (Stanford University)
- Wednesday 27 April 2022, 16:00–17:00
- Venue: Virtual (Zoom details under abstract).
- Series: CCIMI Seminars; organiser: Randolf Altmeyer.