Dmitry Yarotsky
12 papers · 2018–2025 · 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (17)
π
Keyword Champion
(2)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(56)
Top co-authors
Research topics
Keywords
neural network
(5)
function approximation
(4)
momentum method
(3)
stochastic gradient descent
(3)
convergence rate
(3)
gradient descent
(3)
universal approximation
(2)
neural network approximation
(2)
activation function
(2)
relu network
(2)
deep neural network
(2)
approximation rate
(2)
high-dimensional learning
(1)
generalization error
(1)
neural network optimization
(1)
vc dimension
(1)
deep learning theory
(1)
ensemble learning
(1)
asymptotic analysis
(1)
quadratic optimization
(1)
Papers
SGD with memory: fundamental properties and stochastic acceleration
ICLR 2025
Generalization error of spectral algorithms
ICLR 2024
Learnability of high-dimensional targets by two-parameter models and gradient flow
NeurIPS 2024
Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions
JMLR 2024
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
ICLR 2023
Structure of universal formulas
NeurIPS 2023
Embedded Ensembles: infinite width limit and operating regimes
AISTATS 2022
Elementary superexpressive activations
ICML 2021
Explicit loss asymptotics in the gradient descent training of neural networks
NeurIPS 2021
Low-loss connection of weight vectors: distribution-based approaches
ICML 2020
The phase diagram of approximation rates for deep neural networks
NeurIPS 2020
Optimal approximation of continuous functions by very deep ReLU networks
COLT 2018