Chaoyue Liu
9 papers · 2016–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4) π Academic Marathon (8)
π
Interdisciplinary Bridge
π
Cross-Pollinator
(10)
π₯
Unstoppable
(5)
Conferences
NIPS (4)
ICLR (3)
ICML (1)
IJCAI (1)
Top co-authors
Keywords
neural network
(3)
transition to linearity
(2)
neural tangent kernel
(2)
k-means clustering
(1)
optimal transport
(1)
deep learning theory
(1)
deep learning
(1)
asymptotic analysis
(1)
procrustes analysis
(1)
bregman divergence
(1)
gradient descent
(1)
hessian matrix
(1)
convergence rate
(1)
overparameterized model
(1)
directed acyclic graph
(1)
interpolation regime
(1)
infinite width
(1)
correspondence learning
(1)
gauss-seidel method
(1)
network width
(1)
Papers
Quadratic models for understanding catapult dynamics of neural networks
ICLR 2024
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
ICML 2024
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems
NIPS 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
Two-Sided Wasserstein Procrustes Analysis
IJCAI 2021
Accelerating SGD with momentum for over-parameterized learning
ICLR 2020
On the linearity of large non-linear models: when and why the tangent kernel is constant
NIPS 2020
Clustering with Bregman Divergences: an Asymptotic Analysis
NIPS 2016