Pavel Dvurechensky
13 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (18) 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6)
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(10)
🗃️
Keyword Collector
(57)
💎
Century Club
(13)
🔥
Unstoppable
(7)
Conferences
ICML (9)
COLT (2)
AISTATS (1)
NIPS (1)
Top co-authors
Keywords
convex optimization
(4)
optimal transport
(4)
non-convex optimization
(2)
complexity bound
(2)
oracle complexity
(2)
entropic regularization
(2)
stochastic optimization
(2)
iteration complexity
(2)
convergence rate
(2)
variational inequality
(1)
reproducing kernel hilbert space
(1)
empirical risk minimization
(1)
gradient descent
(1)
learning theory
(1)
distributed optimization
(1)
linear convergence
(1)
communication complexity
(1)
projection-free optimization
(1)
accelerated gradient
(1)
maximum mean discrepancy
(1)
Papers
Interaction-Force Transport Gradient Flows
NIPS 2024
Analysis of Kernel Mirror Prox for Measure Optimization
AISTATS 2024
Barrier Algorithms for Constrained Non-Convex Optimization
ICML 2024
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
ICML 2024
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
ICML 2023
The power of first-order smooth optimization for black-box non-smooth problems
ICML 2022
Newton Method over Networks is Fast up to the Statistical Precision
ICML 2021
On a Combination of Alternating Minimization and Nesterov’s Momentum
ICML 2021
Self-Concordant Analysis of Frank-Wolfe Algorithms
ICML 2020
Near Optimal Methods for Minimizing Convex Functions with Lipschitz $p$-th Derivatives
COLT 2019
On the Complexity of Approximating Wasserstein Barycenters
ICML 2019
Optimal Tensor Methods in Smooth Convex and Uniformly ConvexOptimization
COLT 2019
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm
ICML 2018