Shiyun Xu
4 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
๐
Interdisciplinary Bridge
๐
Conference Polyglot
(3)
๐ฃ
Hot Topic Early Bird
๐
Cross-Pollinator
(9)
๐บ๏ธ
Taxonomy Completionist
(11)
Conferences
AISTATS (2)
ICLR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
overparameterized neural network
(2)
neural tangent kernel
(1)
vision transformer
(1)
feature selection
(1)
model architecture
(1)
deep learning
(1)
neural network optimization
(1)
efficient computing
(1)
gradient descent
(1)
optimization algorithm
(1)
dynamical system
(1)
convergence rate
(1)
convolutional neural network
(1)
model training
(1)
gradient clipping
(1)
private training
(1)
semi-parametric model
(1)
linear model
(1)
differential privacy
(1)
post-selection inference
(1)
Papers
Gradient descent with generalized Newtonโs method
ICLR 2025
Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy
NIPS 2022
DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks
AISTATS 2021
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
AISTATS 2021