The machine learning community at Columbia University spans multiple departments, schools, and institutes. We have interest and expertise in a broad range of machine learning topics and related areas.

## Faculty

- Shipra Agrawal (IEOR)
- multi-armed bandits, reinforcement learning, online learning and optimization, sequential decision making

- Alexandr Andoni (CS)
- algorithms for massive data, nearest neighbor search, high-dimensional computational geometry, learning theory

- Marco Avella (Stats)
- Elias Bareinboim (CS)
- causal inference, decision-making, explainability

- David Blei (CS, Stats)
- probabilistic machine learning and applications, approximate Bayesian inference, causal inference

- Adam Cannon (CS)
- statistical learning theory, supervised learning

- Shih-Fu Chang (CS, EE)
- computer vision, multimedia knowledge extraction, meta learning and few shot learning, large-scale visual search

- Michael Collins (CS)
- John Cunningham (Stats)
- deep generative models, approximate inference, state space models, gaussian processes, computational neuroscience

- Daniel Hsu (CS)
- algorithmic statistics, interactive learning, learning theory

- Nicolas Hug (DSI)
- Garud Iyengar (IEOR)
- Tony Jebara (CS)
- Samory Kpotufe (Stats)
- statistical learning theory, nonparametrics and high-dimensional statistics, minimally supervised learning

- Po-Ling Loh (Stats)
- high-dimensional statistics, robustness, network inference

- Arian Maleki (Stats)
- Andreas Müller (DSI)
- machine learning software (in particular scikit-learn), automatic machine learning, supervised learning

- John Paisley (EE)
- Bayesian models and inference

- Liam Paninski (Stats)
- Cynthia Rush (Stats)
- high-dimensional statistics, sparse learning, information theory, statistical signal and image processing, learning theory

- Daniel Russo (DRO)
- Ansaf Salleb-Aouissi (CS)
- Rocco Servedio (CS)
- computational learning theory

- Shuran Song (CS)
- computer vision, robot learning

- Nakul Verma (CS)
- learning theory, metric learning, dimensionality reduction and embeddings, manifold learning, topological data analysis, fairness

- Carl Vondrick (CS)
- computer vision, unsupervised learning

- Chris Wiggins (APAM)
- computational biology, network data analysis, bandit problems, variational inference, statistics

- John Wright (EE)
- optimization, sparse and low-dimensional models, imaging

- Assaf Zeevi (DRO)
- bandit problems, statistical learning theory, reinforcement learning, stopping problems and sequential analysis, model predictive control

## PhD students and postdocs

- Jaan Altosaar
- Mariam Avagyan
- Espen Bernton
- Sam Buchanan
- Robert Colgan
- Juan Correa
- Adji Dieng
- Rishabh Dudeja
- Thomas Fan
- Dar Gilboa
- Zhanpeng He
- Sharon Huang
- Randy Jia
- Anand Kalvit
- Giannis Karamanolakis
- Yenson Lau
- Sanghack Lee
- Kathy Li
- Jackson Loper
- Aditya Makkar
- Andrew Miller
- Arunesh Mittal
- Gemma Moran
- Christian Naesseth
- Parita Pooj
- Sudeep Raja Putta
- Adele Ribeiro
- Clayton Sandford
- Aaron Schein
- Kevin Shi
- Sandip Sinha
- Dhanya Sridhar
- Didac Suris
- Robin (Yunhao) Tang
- Wesley Tansey
- Christopher Tosh
- Dustin Tran
- Iñigo Urteaga
- Keyon Vafa
- Victor Veitch
- Emmanouil Vlatakis
- Kiran Vodrahalli
- Tim Wang
- Yixin Wang
- Ji Xu
- Keyang Xu
- Yunbei Xu
- Zhenjia Xu
- Jingkai Yan
- Steven Yin
- Junzhe Zhang
- Tony Zhang
- Wei Zhang
- Peilin Zhong
- Wenda Zhou

## Mailing list

We maintain a low-volume mailing list to announce talks and events going on at Columbia that are relevant to machine learning. To subscribe, send an email to “machine-learning-columbia+subscribe at googlegroups dot com”.