Dmitrii Avdiukhin
9 papers · 2020–2024 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(19)
🏆
Grand Slam
Top co-authors
Research topics
Keywords
metric learning
(2)
learning theory
(2)
second-order stationary point
(2)
approximation algorithm
(2)
hierarchical clustering
(2)
contrastive learning
(2)
saddle point
(2)
sample complexity
(2)
representation learning
(2)
stochastic gradient descent
(1)
distributed learning
(1)
communication complexity
(1)
federated learning
(1)
distributed optimization
(1)
communication efficiency
(1)
pac learning
(1)
graph partitioning
(1)
linear programming
(1)
gradient descent
(1)
constrained optimization
(1)
Papers
Approximation Scheme for Weighted Metric Clustering via Sherali-Adams
AAAI 2024
Embedding Dimension of Contrastive Learning and k-Nearest Neighbors
NeurIPS 2024
Optimal Sample Complexity of Contrastive Learning
ICLR 2024
HOUDINI: Escaping from Moderately Constrained Saddles
IJCAI 2023
Tree Learning: Optimal Sample Complexity and Algorithms
AAAI 2023
Escaping Saddle Points with Compressed SGD
NeurIPS 2021
Federated Learning under Arbitrary Communication Patterns
ICML 2021
Objective-Based Hierarchical Clustering of Deep Embedding Vectors
AAAI 2021
“Bring Your Own Greedy”+Max: Near-Optimal 1/2-Approximations for Submodular Knapsack
AISTATS 2020