Talk, MIDL, Montreal + Virtual
During the MIDL2020, I and Anna Kuzina presented our work on transfer learning for 3D MRI segmentation. How to learn deep and big 3D UNet-like model with only 5 or 10 training images? It is a common question for medical data. We address it by imposing prior distribution over the convolutional kernels as the generative model (VAE)!
Talk, HSE, Computer Science Faculty, Moscow, Russia
We have the meeting between “Machine Learning”-people and Physicists at the wonderful workshop Physics inspired Machine Learning. I presented our (Kirill Neklyudov, Evgenii Egorov, Dmitry Vetrov) paper on the fusion between MCMC and GANs. There is a video (in Russian) and very long slides. If you would like to take the global idea instantly, I propose to see our NeurIPS poster.
Talk, ISNN, Skoltech, Moscow
I presented our (Evgenii Egorov, Kirill Neklydov, Ruslan Kostoev and Evgeny Burnaev) work on greedy semi-parametric Variational Inference. We propose a version of the Frank-Wolfe algorithm with entropy regularization in the density space. There are slides and full-text on arXiv, as well as published version.
Tutorial, MLSS'19, Skoltech, Skoltech, Moscow
During MLSS at Skoltech, I give a small practical tutorial on MCMC for listners of wonderful Mark Gilorami talk on probabilistic numerics. There is notebook and video.