Dachao Lin
7 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π Academic Marathon (6) π Cross-Pollinator (4)
πΊοΈ
Taxonomy Completionist
(10)
Conferences
NIPS (3)
ICML (2)
JMLR (2)
Top co-authors
Keywords
convergence analysis
(3)
gradient descent
(2)
bfgs method
(2)
sr1 method
(2)
quasi-newton method
(2)
superlinear convergence
(2)
policy iteration
(1)
variance reduction
(1)
smooth optimization
(1)
unconstrained optimization
(1)
learning rate
(1)
convergence rate
(1)
gradient flow
(1)
linear neural network
(1)
deep linear network
(1)
saddle point
(1)
step size
(1)
local optimum
(1)
sublinear convergence
(1)
neural network
(1)
Papers
On the Convergence of Projected Policy Gradient for Any Constant Step Sizes
JMLR 2025
Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis
NIPS 2023
On Non-local Convergence Analysis of Deep Linear Networks
ICML 2022
Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods
JMLR 2022
Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence
NIPS 2021
Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data
NIPS 2021
Toward Understanding the Importance of Noise in Training Neural Networks
ICML 2019