Research Pod

Machine Learning Research Pod

The Research Pod in Machine Learning brings together researchers from theoretical computer science, mathematics, statistics, electrical engineering, and economics to develop the theoretical foundations of machine learning and data science. Led by Simons Institute Associate Director Peter Bartlett, this pod is partially funded by a $12.5 million award made under the National Science Foundation's program on Transdisciplinary Research in Principles of Data Science to establish the Foundations of Data Science Institute (FODSI). This institute, a collaboration between UC Berkeley and MIT, partnering with Boston, Northeastern, Harvard and Howard universities, as well as Bryn Mawr College, aims to improve our understanding of critical issues in data science, including modeling, statistical inference, computational efficiency, and societal impacts. NSF, together with the Simons Foundation, is also supporting the activities of the pod through the Collaboration on the Theoretical Foundations of Deep Learning. This is a collaboration of 11 PIs from eight institutions around the world that aims to understand the mathematical mechanisms that underpin the practical success of deep learning. The Simons Institute will act as the convening center for many of these activities, hosting public events such as summer schools, research workshops, and other collaborative research opportunities.


Postdoctoral Fellows:
Stephen Bates (UC Berkeley), Lin Chen (UC Berkeley), Sitan Chen (Massachusetts Institute of Technology), Mahsa Derakhshan(University of Maryland), Spencer Frei (UC Los Angeles), Yanjun Han (UC Berkeley), Wei Hu (Princeton University), Frederic Koehler (Massachusetts Institute of Technology), Adil Salim (KAUST), Dennis Shen (Massachusetts Institute of Technology), Ellen Vitercik (Carnegie Mellon University), Carrie Wu (Stanford University), Emmanouil Zampetakis (UC Berkeley), Andrea Zanette (Stanford University), Angela Zhou (Cornell University), Luiz Chamon(University of Pennsylvania), Jan van den Brand (KTH Royal Institute of Technology)

Machine Learning Postdoctoral Researchers

High-Dimensional Statistics, Causal Inference, Statistical Inference With Ml Models
Machine Learning Theory
ML Theory (Robust Statistics, Deep Learning, Distribution Learning) And Quantum Learning
Optimization, Constrained Learning, Signal Processing, Control
Deep Learning, Statistical Learning Theory, Optimization
High-Dimensional And Nonparametric Statistics, Information Theory, Online Learning And Bandits
Machine Learning Theory, Deep Learning Theory
Computational Learning Theory, Algorithms, Sampling, High-Dimensional Statistics
Optimization, Sampling, Probability, Optimal Transport, Machine Learning
Causal Inference, Machine Learning, Statistics
Data Structures, Algebraic Algorithms, Optimization
Machine Learning Theory; Algorithm Design; Economics And Computation
Reinforcement Learning, Optimization, High Dimensional Statistics
Reinforcement Learning, Machine Learning, Optimization, Statistics
Statistical Machine Learning, Causal Inference, Sequential Decision Making Under Uncertainty

Past Participants

Sitan Chen, Massachusetts Institute of Technology, Machine Learning Postdoctoral Researcher
Adil Salim, KAUST, Machine Learning Postdoctoral Researcher
Angela Zhou, UC Berkeley, Machine Learning Postdoctoral Researcher
Lin Chen, UC Berkeley, Machine Learning Postdoctoral Researcher
Frederic Koehler, Massachusetts Institute of Technology, Machine Learning Postdoctoral Researcher


Dec. 6Dec. 7, 2021