Misha Belkin
7 papers · 2020–2023 · 2 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
🗺️
Taxonomy Completionist
(10)
Venues
Top co-authors
Research topics
Keywords
neural network
(4)
gradient descent
(4)
neural tangent kernel
(3)
transition to linearity
(2)
benign overfitting
(2)
neural network optimization
(1)
generalization error
(1)
signal-to-noise ratio
(1)
kernel regression
(1)
restricted strong convexity
(1)
hessian matrix
(1)
geometric convergence
(1)
convergence rate
(1)
convolutional neural network
(1)
overparameterized model
(1)
directed acyclic graph
(1)
interpolation regime
(1)
infinite width
(1)
network width
(1)
wide neural network
(1)
Papers
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems
NeurIPS 2023
Restricted Strong Convexity of Deep Learning Models with Smooth Activations
ICLR 2023
Benign Overfitting in Two-layer Convolutional Neural Networks
NeurIPS 2022
Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting
NeurIPS 2022
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture
NeurIPS 2022
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models
ICLR 2022
On the linearity of large non-linear models: when and why the tangent kernel is constant
NeurIPS 2020