Scalable inference of topic evolution via models for latent geometric structures
- Mikhail Yurochkin
- Zhiwei Fan
- et al.
- 2019
- NeurIPS 2019
Bio
Mikhail is a Research Staff Member at IBM Research and MIT-IBM Watson AI Lab in Cambridge, Massachusetts. His research interests are
- Algorithmic Fairness
- Out-of-Distribution Generalization
- Applications of Optimal Transport in Machine Learning
- Model Fusion and Federated Learning
Before joining IBM, he completed his PhD in Statistics at the University of Michigan, where he worked with Prof. XuanLong Nguyen on geometric inference in Bayesian models.
Personal Webpage: https://moonfolk.github.io/
Publications
Hierarchical optimal transport for document representation
- Mikhail Yurochkin
- Farzaneh Mirzazadeh
- et al.
- 2019
- NeurIPS 2019
Bayesian nonparametric federated learning of neural networks
- Mikhail Yurochkin
- Mayank Agarwal
- et al.
- 2019
- ICML 2019
Dirichlet simplex nest and geometric inference
- Mikhail Yurochkin
- Aritra Guha
- et al.
- 2019
- ICML 2019
Patents
Blog posts
Serving customized AI models at scale with LoRA
ResearchKim MartineauNew research helps make AI fairer in decision-making
ResearchMikhail Yurochkin and Yuekai Sun5 minute read
Top collaborators
KG
Kristjan Greenewald
Research Staff Member
MS
Mírian Silva
AI Engineer
MA
Mayank Agarwal
Senior Research Engineer
YM
Youssef Mroueh
Principal Research Scientist