3 citations · 3 across the 6 of their papers we have counts for
7 papers
Provably adaptive sampling with uniform and remasking discrete diffusion models
Daniil Dmitriev, Zhihan Huang, Yuting Wei
Discrete diffusion models offer a promising alternative to autoregressive generation by enabling parallel updates, but their sampling efficiency can depend strongly on the choice o…
Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
Daniil Dmitriev, Zhihan Huang, Yuting Wei
Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this paper, we study the sampling effi…
Learning in an Echo Chamber: Online Learning with Replay Adversary
Daniil Dmitriev, Harald Eskelund Franck, Carolin Heinzler +1
As machine learning systems increasingly train on self-annotated data, they risk reinforcing errors and becoming echo chambers of their own beliefs. We model this phenomenon by int…
The Lovász number of random circulant graphs
Afonso S. Bandeira, Jarosław Błasiok, Daniil Dmitriev +3
This paper addresses the behavior of the Lovász number for dense random circulant graphs. The Lovász number is a well-known semidefinite programming upper bound on the independence…
Robust Mixture Learning when Outliers Overwhelm Small Groups
Daniil Dmitriev, Rares-Darius Buhai, Stefan Tiegel +5
We study the problem of estimating the means of well-separated mixtures when an adversary may add arbitrary outliers. While strong guarantees are available when the outlier fractio…
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
Daniil Dmitriev, Kristóf Szabó, Amartya Sanyal
In this paper, we provide lower bounds for Differentially Private (DP) Online Learning algorithms. Our result shows that, for a broad class of -DP online algorithm…
Asymptotics of Learning with Deep Structured (Random) Features
Dominik Schröder, Daniil Dmitriev, Hugo Cui +1
For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where t…