Jiaoyang Huang
7 papers · 2020–2024 · 4 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🏆 Keyword Champion (2) 🔥 Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Keywords
neural network
(2)
deep learning theory
(2)
gradient descent
(2)
adversarial robustness
(1)
function approximation
(1)
convergence analysis
(1)
information bottleneck
(1)
adversarial training
(1)
deep learning
(1)
markov decision process
(1)
mutual information
(1)
value iteration
(1)
kernel regression
(1)
generalization error
(1)
model-based reinforcement learning
(1)
neural network training
(1)
hidden layer
(1)
neural network dynamics
(1)
hessian matrix
(1)
stochastic gradient descent
(1)
Papers
High-dimensional SGD aligns with emerging outlier eigenspaces
ICLR 2024
How Does Information Bottleneck Help Deep Learning?
ICML 2023
Power Iteration for Tensor PCA
JMLR 2022
Robustness Implies Generalization via Data-Dependent Generalization Bounds
ICML 2022
Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization
NeurIPS 2021
Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
ICML 2020
Towards Understanding the Dynamics of the First-Order Adversaries
ICML 2020