Michael Munn
4 papers · 2020–2025 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
Venues
Top co-authors
Research topics
Deep Learning
(4)
Machine Learning
(4)
Optimization & Theory · Machine Learning
(4)
Artificial Intelligence
(3)
Core AI
(2)
Learning Types · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Mathematics & Optimization
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Optimization
(1)
Techniques
(1)
Keywords
geometric complexity
(2)
representation learning
(1)
few-shot learning
(1)
probabilistic modeling
(1)
transfer learning
(1)
optimal transport
(1)
time series
(1)
bayesian model selection
(1)
sinkhorn algorithm
(1)
sequential data
(1)
neural collapse
(1)
implicit regularization
(1)
foundation model
(1)
generative adversarial network
(1)
parameter initialization
(1)
few-shot setting
(1)
dirichlet energy
(1)
fine-tuning performance
(1)
spectral norm regularization
(1)
adaptability
(1)
Papers
A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
ICML 2025
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
NeurIPS 2024
Why neural networks find simple solutions: The many regularizers of geometric complexity
NeurIPS 2022
COT-GAN: Generating Sequential Data via Causal Optimal Transport
NeurIPS 2020