Dmitry Yarotsky
12 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🏃 Academic Marathon (7) 🐝 Cross-Pollinator (8)
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(6)
🐺
Lone Wolf
(4)
🧬
Topic Evolution
💎
Century Club
(12)
🔥
Unstoppable
(6)
Conferences
NIPS (4)
ICLR (3)
ICML (2)
AISTATS (1)
COLT (1)
JMLR (1)
Top co-authors
Keywords
neural network
(5)
function approximation
(4)
deep neural network
(2)
neural network approximation
(2)
gradient descent
(2)
activation function
(2)
approximation rate
(2)
relu network
(2)
universal approximation
(2)
neural network optimization
(1)
high-dimensional learning
(1)
deep learning theory
(1)
spectral analysis
(1)
conjugate gradient
(1)
ensemble learning
(1)
vc dimension
(1)
gradient flow
(1)
neural network theory
(1)
convergence rate
(1)
sublevel sets
(1)
Papers
SGD with memory: fundamental properties and stochastic acceleration
ICLR 2025
Generalization error of spectral algorithms
ICLR 2024
Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions
JMLR 2024
Learnability of high-dimensional targets by two-parameter models and gradient flow
NIPS 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
NIPS 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
NIPS 2021
The phase diagram of approximation rates for deep neural networks
NIPS 2020
Low-loss connection of weight vectors: distribution-based approaches
ICML 2020
Optimal approximation of continuous functions by very deep ReLU networks
COLT 2018