Pavel Izmailov

Photo of Pavel Izmailov

I’m a PhD student in Operations Research and Information Engineering at Cornell University, working with Professor Andrew Wilson. I am primarily interested in better understanding Deep Neural Networks and finding more efficient ways of training them. In particular my interests include loss surface analysis, optimization and regularization in deep learning. I am also excited about deep semi-supervised learning, reinforcement learning, Bayesian deep learning, efficient inference in Gassian processes and other topics.

I received a BS in applied math and computer science from the faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University. During the last two years of my undergraduate program I was working in the Bayesian Methods Research Group under supervision of Dmitry Vetrov and Dmitry Kropotov focusing on inference in Gaussian Process models.

I will be joining Amazon in Palo Alto as a research intern for summer 2019.

You can contact me at and follow me on Twitter.



Workshop Papers