Daniil Dmitriev

6 papers · 2020–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird

Venues

COLT (2) ICML (2) ICLR (1) NeurIPS (1)

Top co-authors

Dominik Schröder (2) Hugo Cui (2) Amartya Sanyal (2) Bruno Loureiro (2) Luis Barba (1) Tao LIN (1) Martin Jaggi (1) Stefan Tiegel (1) David Steurer (1) Zhihan Huang (1)

Research topics

Machine Learning (6) Optimization & Theory (5) Deep Learning (3) Learning Types · Machine Learning (2) Artificial Intelligence (1) Application Areas (1) Architectures (1) Bayesian & Probabilistic (1) Core AI (1) Core Methods (1) Learning Types · Deep Learning (1) Models (1) Techniques (1)

Keywords

test error (2) differential privacy (1) adversarial learning (1) online learning (1) ridge regression (1) mean estimation (1) kullback-leibler divergence (1) model pruning (1) robust estimation (1) sparse model (1) mistake bound (1) convergence guarantee (1) mixture learning (1) deep neural network (1) implicit regularization (1) lower bound (1) random feature (1) discrete diffusion model (1) inference latency (1) high-dimensional limit (1)

Papers

Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees COLT 2026 Asymptotics of Learning with Deep Structured (Random) Features ICML 2024 On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective COLT 2024 Robust Mixture Learning when Outliers Overwhelm Small Groups NeurIPS 2024 Deterministic equivalent and error universality of deep random features learning ICML 2023 Dynamic Model Pruning with Feedback ICLR 2020