Maxim Kodryan

Hi! My name is Max and I'm a PhD in Computer Science who does research and teaching in the field of Machine Learning. My main research interests are the foundations of Deep Learning, in particular the problems of optimization and generalization of neural networks, their relationship to the training process and the properties of the loss landscape. In my research, I have developed model compression methods, investigated power laws in the loss of deep ensembles, studied the properties of training dynamics and loss landscape of neural networks with scale-invariant parameters, etc.

Currently, I am a Research Fellow at HSE University and a member of the Bayesian Methods Research Group. I received my Bachelor's and Master's degrees in Applied Mathematics and Computer Science from Lomonosov Moscow State University and completed a PhD in Computer Science at HSE University (advised by Dmitry Vetrov).

Email  /  CV  /  Google Scholar  /  Github

profile photo