Guodong Zhang
16 papers · 2017–2023 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🏃 Academic Marathon (6) 🌍 Conference Polyglot (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(6)
👑
Triple Crown
🗃️
Keyword Collector
(57)
⚡
Prolific Year
(5)
💎
Century Club
(16)
🔥
Unstoppable
(7)
❓
The Questioner
Conferences
ICLR (5)
AISTATS (3)
ICML (3)
NIPS (3)
ICCV (1)
JMLR (1)
Top co-authors
Keywords
convergence rate
(3)
integral quadratic constraint
(2)
natural gradient
(2)
minimax optimization
(2)
smooth game
(2)
bayesian inference
(1)
game theory
(1)
stochastic gradient descent
(1)
neural network optimization
(1)
convergence analysis
(1)
convex optimization
(1)
kernel learning
(1)
marginal likelihood
(1)
gaussian process
(1)
differentiable programming
(1)
global convergence
(1)
gradient descent
(1)
bayesian optimization
(1)
annealed importance sampling
(1)
gaussian processes
(1)
Papers
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
ICLR 2023
Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
AISTATS 2022
Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers
ICLR 2022
Differentiable Annealed Importance Sampling and the Perils of Gradient Noise
NIPS 2021
On the Suboptimality of Negative Momentum for Minimax Optimization
AISTATS 2021
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints
JMLR 2021
An Empirical Study of Stochastic Gradient Descent with Structured Covariance Noise
AISTATS 2020
Picking Winning Tickets Before Training by Preserving Gradient Flow
ICLR 2020
FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKS
ICLR 2019
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
NIPS 2019
Three Mechanisms of Weight Decay Regularization
ICLR 2019
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
NIPS 2019
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
ICML 2019
Noisy Natural Gradient as Variational Inference
ICML 2018
Differentiable Compositional Kernel Learning for Gaussian Processes
ICML 2018
Deformable Convolutional Networks
ICCV 2017