Junsoo Ha
4 papers · 2019–2026 · 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(11)
Venues
Top co-authors
Research topics
Keywords
continual learning
(1)
catastrophic forgetting
(1)
dirichlet process
(1)
bayesian nonparametrics
(1)
non-convex optimization
(1)
convergence analysis
(1)
conditional generation
(1)
image-to-image translation
(1)
image inpainting
(1)
gradient clipping
(1)
generative adversarial network
(1)
mixture of expert
(1)
lookahead optimizer
(1)
smooth game
(1)
gan training
(1)
gradient method
(1)
stochastic gradient descent ascent
(1)
heavy-tailed noise
(1)
high probability convergence
(1)
task-free learning
(1)
Papers
High Probability Convergence Guarantees of Stochastic Gradient Descent Ascent in Structured Nonconvex Min-Max Games
COLT 2026
On Convergence of Lookahead in Smooth Games
AISTATS 2022
A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
ICLR 2020
Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation
ICLR 2019