Daniil Dmitriev

I am a PhD student at the ETH AI Center, part of ETH Zurich.
My PhD advisors are Afonso Bandeira and Fanny Yang.

I have a MS in Data Science from EPFL, where I was a research assistant for Martin Jaggi working on optimization in machine learning. For my master thesis on statistical physics in neural network theory I was supervised by Lenka Zdeborová.

I am broadly interested in topics at the intersection of mathematics, theoretical computer science and machine learning. In particular, I am working currently on robustness, privacy and random matrix theory.

CV  /  Email  /  GitHub  /  Google Scholar  /  LinkedIn

Greedy heuristics and linear relaxations for the random hitting set problem

Proved that the standard greedy algorithm is optimal for the hitting set problem in the random bernoulli case.

Deterministic equivalent and error universality of deep random features learning

Rigorously established Gaussian universality for the test error in ridge regression in deep networks with frozen intermediate layers.

On monotonicity of Ramanujan function for binomial random variables

Analyzed properties of the CDF of binomial random variable near its median.

Dynamic model pruning with feedback

Proposed a novel model compression method that generates a sparse trained model without additional overhead.

Invited Talks