Yang Song | Sliced Score Matching: A Scalable Approach to Density and Score Estimation

Yang Song's academic website.

Sliced Score Matching: A Scalable Approach to Density and Score Estimation | Yang Song Sliced Score Matching: A Scalable Approach to Density and Score Estimation An overview for our UAI 2019 paper on Sliced Score Matching. We show how to use random projections to scale up score matching—a classic method to learn unnormalized probabilisic models—to high-dimensional data. Theoretically, sliced score matching produces a consistent and asymptotic normal estimator under some regularity conditions. We apply sliced score matching to training deep energy-based models, learning VAEs with implicit encod

saved by

• João Araújo

related reading

• Generative Modeling by Estimating Gradients of the Data Distribution | Yang Songyang-song.github.io
• ML vs. Score matchingarxiv.org
• Deep Energy Estimator.pdfarxiv.org
• Regularized by Score Matching (LeCun)papers.nips.cc
• score matching (hyvarinen)jmlr.org
• Yang Songyang-song.net
• Generative Modeling by Estimating Gradients of the Data Distribution | Yang Songyang-song.github.io
• What are Diffusion Models?lilianweng.github.io
• Anas Aldadi on X: "We know VAEs try to match *Density values* using KL-Divergence, while score-matching try to match *Density gradients* using Fisher-Divergence but do you know that if you take KL and add Gaussian noise to it, the derivative of KL with respect to noise level is actually F-Div https://t.co/e6k6hhUhFT" / Xx.com
• What are Diffusion Models? | Lil'Loglilianweng.github.io
• https://arxiv.org/pdf/2006.11239arxiv.org
• Denoising Density Estimatorsarxiv.org