Juntang Zhuang
5 papers · 2020–2022 · 3 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
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
neural ordinary differential equation
(2)
adjoint method
(2)
gradient estimation
(2)
gradient descent
(1)
convergence rate
(1)
memory efficiency
(1)
adaptive step size
(1)
flat minima
(1)
adaptive gradient
(1)
exponential moving average
(1)
adaptive optimizer
(1)
gradient decomposition
(1)
asynchronous update
(1)
stochastic non-convex optimization
(1)
momentum centering
(1)
continuous generative model
(1)
surrogate gap
(1)
image classification
(1)
perturbed loss
(1)
stochastic gradient descent
(1)
Papers
Surrogate Gap Minimization Improves Sharpness-Aware Training
ICLR 2022
MALI: A memory efficient and reverse accurate integrator for Neural ODEs
ICLR 2021
Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
NeurIPS 2021
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
NeurIPS 2020
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE
ICML 2020