Dylan Foster
I am a postdoctoral researcher at the
MIT Institute for Foundations of Data Science.
I was previously (2014-2018) a PhD student in the
Department of Computer Science
at Cornell University advised by Karthik Sridharan.
I received my BS and MS in electrical engineering from the University of Southern California in 2014.
I work on theory for machine learning.
Research
I am interested in all aspects of generalization, sample complexity, and related algorithmic problems, especially for real-world problems such as interactive learning, deep learning, and non-convex learning. Specific topics include
interactive learning (contextual bandits, reinforcement learning,...).
deep learning.
stochastic/non-convex/distributed/... optimization.
statistical learning, especially agnostic learning.
online learning and sequential prediction.
adaptivity and instance dependence.
high-dimensional statistics.
concentration inequalities and empirical process theory.
Selected awards
News
- In summer 2019 I will be a long-term visitor at the Simons Institute for the Foundations of Deep Learning program.
- I have officially completed my PhD and started my postdoc at MIT!
- I was featured on the Facebook research blog.
- I am on the PC for ALT 2019. Submit your best work!
- In summer 2018 I will be interning with Vasilis Syrgkanis at MSR New England.
- Two new papers at NIPS 2017 with spotlight presentations!
- New paper ZigZag on online learning, decoupling, and Burkholder functions.
- Spending summer 2017 with Rob Schapire and Miroslav Dudik at MSR NYC.
- In Berkeley until May 2017 at the Simons Institute for the Foundations of Machine Learning program.
- Learning in Games: Robustness of Fast Convergence at NIPS 2016
- Spending summer in Sanjiv Kumar's group at Google Research NYC.
- I am a 2016 NDSEG Fellow.
- Gave invited talk at Learning Faster from Easy Data II at NIPS 2015.
- Attending NIPS 2015 in Montreal to present Adaptive Online Learning.
- Adaptive Online Learning accepted into NIPS 2015.
Preprints
Model Selection for Contextual Bandits
Dylan J. Foster, Akshay Krishnamurthy, and Haipeng Luo
2019.Orthogonal Statistical Learning
Dylan J. Foster and Vasilis Syrgkanis.
2019.
Publications
Distributed Learning with Sublinear Communication
Jayadev Acharya, Christopher De Sa, Dylan J. Foster, and Karthik Sridharan.
ICML 2019. Long talk.
Best spotlight talk, 13th Annual New York Academy of Science ML Symposium.Sum-of-Squares Meets Square Loss:
Fast Rates for Agnostic Tensor Completion
Dylan J. Foster and Andrej Risteski.
COLT 2019.
The Complexity of Making the Gradient Small in
Stochastic Convex Optimization
Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan,
and Blake Woodworth.
COLT 2019. Best Student Paper Award.
Statistical Learning with a Nuisance Component
Dylan J. Foster and Vasilis Syrgkanis.
COLT 2019. Best Paper Award.
Extended abstract for Orthogonal Statistical Learning.Contextual Bandits with Surrogate Losses: Margin Bounds
and Efficient Algorithms
Dylan J. Foster and Akshay Krishnamurthy.
NeurIPS 2018.
Paper, PosterUniform Convergence of Gradients for Non-Convex
Learning and Optimization
Dylan J. Foster, Ayush Sekhari, and Karthik Sridharan.
NeurIPS 2018. Short version at ICML 2018 Nonconvex Optimization workshop.
Paper, PosterPractical Contextual Bandits with Regression Oracles
Dylan J. Foster, Alekh Agarwal, Miroslav Dudík, Haipeng Luo, and Robert E. Schapire.
ICML 2018. Long talk.
Paper, PosterLogistic Regression: The Importance of Being Improper
Dylan J. Foster, Satyen Kale, Haipeng Luo, Mehryar Mohri, and Karthik Sridharan.
COLT 2018. Best Student Paper Award.
Paper, PosterOnline Learning: Sufficient Statistics and the Burkholder Method
Dylan J. Foster, Alexander Rakhlin, and Karthik Sridharan.
COLT 2018.
Paper, PosterInference in Sparse Graphs with Pairwise Measurements
and Side Information
Dylan J. Foster, Daniel Reichman, and Karthik Sridharan.
AISTATS 2018.
Paper, PosterParameter-Free Online Learning via Model Selection
Dylan J. Foster, Satyen Kale, Mehryar Mohri, and Karthik Sridharan.
NeurIPS 2017. Spotlight presentation.
Paper, PosterSpectrally-Normalized Margin Bounds for Neural Networks
Peter Bartlett, Dylan J. Foster, and Matus Telgarsky.
NeurIPS 2017. Spotlight presentation.
Paper, PosterZigZag: A New Approach to Adaptive Online Learning
Dylan J. Foster, Alexander Rakhlin, and Karthik Sridharan.
COLT 2017.
Paper, PosterLearning in Games: Robustness of Fast Convergence
Dylan J. Foster, Zhiyuan Li, Thodoris Lykouris, Karthik Sridharan, and Éva Tardos.
NeurIPS 2016. Preliminary version at Ad Auctions workshop at EC 2016.
Paper, PosterDylan J. Foster, Alexander Rakhlin, and Karthik Sridharan.
NeurIPS 2015. Spotlight presentation.
Paper, Poster
Thesis
Adaptive Learning: Algorithms and Complexity
Dylan J. Foster
Ph.D. Thesis. Department of Computer Science, Cornell University, 2019.
Technical reports, notes, etc.
Hypothesis Set Stability and Generalization
Dylan J. Foster, Spencer Greenberg, Satyen Kale, Haipeng Luo, Mehryar Mohri,
and Karthik Sridharan.
Technical report, 2019.
Service
Reviewing: COLT, NeurIPS, ICML, STOC, FOCS, SODA, JMLR, ALT, AISTATS, AAAI.Program Committee: ALT 2019.
Teaching
Machine Learning Theory
Cornell University, Spring 2018.
Professor Karthik Sridharan.
Introduction to Analysis of Algorithms
Cornell University, Spring 2015.
Professors Éva Tardos and David Steurer.
Received outstanding teaching award.Foundations of Artificial Intelligence
Cornell University, Fall 2014.
Professor Bart Selman.
Contact
I can be reached at dylanf at mit dot edu. My office is E17-481 in IDSS.
© Dylan Foster 2015.