Maksim Velikanov
7 papers · 2021–2025 · 4 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(6)
Optimization & Theory · Machine Learning
(6)
Mathematics & Optimization
(4)
Optimization
(4)
Deep Learning
(3)
Optimization & Theory · Deep Learning
(3)
Learning Types
(2)
Artificial Intelligence
(1)
Architectures
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Techniques
(1)
Keywords
momentum method
(3)
convergence rate
(3)
gradient descent
(3)
stochastic gradient descent
(3)
neural network
(2)
neural network optimization
(1)
asymptotic analysis
(1)
generalization error
(1)
spectral analysis
(1)
kernel ridge regression
(1)
conjugate gradient
(1)
weight sharing
(1)
quadratic optimization
(1)
spectral algorithm
(1)
data heterogeneity
(1)
confidence set
(1)
linear model
(1)
gradient descent dynamics
(1)
spectral distribution
(1)
embedded ensemble
(1)
Papers
SGD with memory: fundamental properties and stochastic acceleration
ICLR 2025
Efficient Conformal Prediction under Data Heterogeneity
AISTATS 2024
Generalization error of spectral algorithms
ICLR 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
Embedded Ensembles: infinite width limit and operating regimes
AISTATS 2022
Explicit loss asymptotics in the gradient descent training of neural networks
NeurIPS 2021