Daniil Dmitriev
5 papers · 2020–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🧭
Keyword Pioneer
🌍
Conference Polyglot
(4)
🐝
Cross-Pollinator
(12)
🌉
Interdisciplinary Bridge
Conferences
ICML (2)
COLT (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
differential privacy
(1)
adversarial learning
(1)
online learning
(1)
ridge regression
(1)
mean estimation
(1)
robust estimation
(1)
mistake bound
(1)
mixture learning
(1)
deep neural network
(1)
implicit regularization
(1)
lower bound
(1)
test error
(1)
random feature model
(1)
cluster recovery
(1)
adversarial outlier
(1)
gaussian universality
(1)
list-decodable learning
(1)
Papers
Robust Mixture Learning when Outliers Overwhelm Small Groups
NIPS 2024
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
COLT 2024
Asymptotics of Learning with Deep Structured (Random) Features
ICML 2024
Deterministic equivalent and error universality of deep random features learning
ICML 2023
Dynamic Model Pruning with Feedback
ICLR 2020