Misha Belkin
7 papers · 2020–2023 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
NIPS (5)
ICLR (2)
Top co-authors
Keywords
neural network
(3)
benign overfitting
(2)
transition to linearity
(2)
neural tangent kernel
(2)
gradient descent
(2)
signal-to-noise ratio
(1)
kernel regression
(1)
hessian matrix
(1)
convergence rate
(1)
convolutional neural network
(1)
overparameterized model
(1)
directed acyclic graph
(1)
interpolation regime
(1)
infinite width
(1)
network width
(1)
lazy training
(1)
interpolating method
(1)
statistical learning
(1)
deterministic gradient
(1)
stochastic gradient descent
(1)
Papers
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems
NIPS 2023
Restricted Strong Convexity of Deep Learning Models with Smooth Activations
ICLR 2023
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture
NIPS 2022
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models
ICLR 2022
Benign Overfitting in Two-layer Convolutional Neural Networks
NIPS 2022
Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting
NIPS 2022
On the linearity of large non-linear models: when and why the tangent kernel is constant
NIPS 2020