Zhenxun Zhuang
4 papers · 2019–2022 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
non-convex optimization
(4)
stochastic gradient descent
(3)
gradient clipping
(2)
neural network optimization
(1)
online convex optimization
(1)
distributed training
(1)
communication efficiency
(1)
adaptive learning rate
(1)
communication complexity
(1)
polyak-lojasiewicz condition
(1)
adaptive gradient
(1)
step size tuning
(1)
exponential step size
(1)
cosine step size
(1)
unbounded smoothness
(1)
self-tuned stepsize
(1)
adam algorithm
(1)
Papers
A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
NeurIPS 2022
Robustness to Unbounded Smoothness of Generalized SignSGD
NeurIPS 2022
A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
ICML 2021
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
ICML 2019