Daniel Kunin
9 papers · 2019–2025 · 3 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
🏃
Academic Marathon · Sprint
🗺️
Taxonomy Completionist
(21)
🐣
Hot Topic Early Bird
🗃️
Keyword Collector
(50)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Deep Learning
(7)
Optimization & Theory · Machine Learning
(7)
Architectures
(4)
Optimization & Theory · Deep Learning
(4)
Artificial Intelligence
(2)
Core AI
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Application Areas
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Techniques
(1)
Keywords
learning dynamics
(3)
neural network
(3)
gradient descent
(2)
neural network optimization
(2)
learning theory
(2)
stochastic gradient descent
(2)
representation learning
(2)
probabilistic pca
(1)
sample complexity
(1)
neural tangent kernel
(1)
local learning
(1)
principal component analysis
(1)
lottery ticket hypothesis
(1)
variational inference
(1)
sparse optimization
(1)
maximum margin
(1)
exponential loss
(1)
learning rate
(1)
convolutional neural network
(1)
feature learning
(1)
Papers
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
ICLR 2025
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
NeurIPS 2024
Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
NeurIPS 2023
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
ICLR 2023
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
ICLR 2021
Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks
NeurIPS 2021
Pruning neural networks without any data by iteratively conserving synaptic flow
NeurIPS 2020
Two Routes to Scalable Credit Assignment without Weight Symmetry
ICML 2020
Loss Landscapes of Regularized Linear Autoencoders
ICML 2019