University of Cambridge > Talks.cam > CCIMI Seminars > Generative Modeling by Estimating Gradients of the Data Distribution

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Generative Modeling by Estimating Gradients of the Data Distribution

Download to your calendar using vCal

If you have a question about this talk, please contact Randolf Altmeyer .

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

This talk is part of the CCIMI Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Goldsmiths 1, Lecture Theatre, Department of Materials Science & Metallurgy Small Lecture Theatre, Bragg Building, Cavendish Average on Saturdays: 7803.03947368 kWh

Other talks

Title to be confirmed Formal Dinner at Selwyn College Discussion II The Neurophenomenology of Surrender: Agency, Renewal, and Social Engagement in Speaking in Tongues "Gods, Monsters & Middle-class Uncles: Indian Comics in a Time between Worlds" Secrets of the Surface: The Mathematical Vision of Maryam Mirzakhani ( EDI Film Screening)
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity