Daniil Dmitriev

I am a fourth-year PhD student at ETH Zurich, Department of Mathematics.
My PhD is generously funded by ETH AI Center and ETH FDS initiative.
I am supervised by Afonso Bandeira and Fanny Yang.

I am broadly interested in topics at the intersection of mathematics, theoretical computer science and machine learning, with a current focus on the interplay between structure and randomness in algorithm analysis.

I have a MS in Data Science from EPFL, where I worked with Lenka Zdeborová and Martin Jaggi.

Google Scholar  /  CV  /  GitHub  /  LinkedIn  /  X

Robust mixture learning when outliers overwhelm small groups

We propose an efficient meta-algorithm for recoving means of a mixture model in the presence of large additive contaminations.

On the growth of mistakes in differentially private online learning: a lower bound perspective

We prove that for a certain class of algorithms, the number of mistakes for online learning under differential privacy constraint must grow logarithmically.

Asymptotics of learning with deep structured (random) features

We derive a deterministic equivalent for the generalization error of general Lipschitz functions. Furthermore, we prove a linearization for a sample covariance matrix of a structured random feature model with two hidden layers.

Greedy heuristics and linear relaxations for the random hitting set problem

We prove that the standard greedy algorithm is order-optimal for the hitting set problem in the random bernoulli case.

Deterministic equivalent and error universality of deep random features learning

We rigorously establish 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

We analyze properties of the CDF of binomial random variable near its median.

Dynamic model pruning with feedback

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

Invited Talks

Robust mixture learning when outliers overwhelm small groups

Robust mixture learning when outliers overwhelm small groups

Lower bounds for online private learning

On integrality gaps for the random hitting set problem

Integrality gaps for vertex covers on sparse Bernoulli hypergraphs

Teaching