Postdoctoral Researcher in Machine Learning

PhD Position in Machine Learning

A core problem in statistics and probabilistic machine learning is to compute probability distributions and expectations. This is the fundamental problem of Bayesian statistics and machine...

Postdoctoral Researcher in Machine Learning

Diffusion models have been successful on a range of conditional generation tasks including molecular design and text-to-image generation. However, these achievements have primarily depended on...

Proceedings of the 6th Symposium on Advances in Approximate Bayesian Inference Held in Vienna, Austria on 21 July 2024 Published as Volume 253 by the Proceedings of Machine Learning Research on 29...

Variational inference often minimizes the "reverse" Kullbeck-Leibler (KL) KL(q||p) from the approximate distribution q to the posterior p. Recent work studies the "forward" KL KL(p||q), which...

Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways....

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics Held in Fort Lauderdale, FL, USA on 20-22 April 2017 Published as Volume 54 by the Proceedings of Machine...

Modern variational inference (VI) uses stochastic gradients to avoid intractable expectations, enabling large-scale probabilistic inference in complex models. VI posits a family of approximating...

Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data...

Please use this form to suggest members of the research community as reviewers, invited speakers, panelists, and organizing committee. Self-nominations are accepted.

Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse...

Conventional diffusion models typically relies on a fixed forward process, which implicitly defines complex marginal distributions over latent variables. This can often complicate the reverse...

We are looking for people to join the organization team for the 6th Symposium on Advances in Approximate Bayesian Inference (AABI), which will most likely be co-located with ICML 2024 in Vienna. If...

Variational inference often minimizes the "reverse" Kullbeck-Leibler (KL) KL(q||p) from the approximate distribution q to the posterior p. Recent work studies the "forward" KL KL(p||q), which...