ding1 [at] csail.mit.edu
I am an NSF Computing Innovation Fellow and Postdoctoral Associate at MIT CSAIL mentored by Michael Carbin since Jan 2021. Previously, I received my Ph.D. in Computer Science from The University of Chicago advised by Henry Hoffmann in Dec. 2020.
I have been a Visiting Researcher at Meta Infrasucture Data Center since Oct. 2021. I work with research scientists and engineers from USA, Dublin, and London to improve maintenance efficiency of millions of servers in real-world hyperscale datacenters.
Find me on Google scholar, Twitter, Medium.
I am a machine learning for systems researcher. My research co-designs machine learning and systems approaches that enhance computer system performance and resource efficiency. I have demonstrated that improving prediction accuracy of machine learning methods does not always improve system outcomes. Instead, my approaches incorporate the unique structure of each systems problem into machine learning solutions to align the optimization goals between machine learning methods and systems problems. One of my solutions (for predicting system maintenance time) is currently being deployed on real-world hyperscale datacenters that serve billions of users.
2022-08-16: Gave a talk at Meta Infrastructure Data Science Faculty Workshop at KDD 2022, DC.
2022-06-16: CAFQA accepted to ASPLOS 2023. I introduce Bayesian optimization to search the Clifford ansatz efficiently for quantum accuracy.
2022-04-08: Minimax designs for long-term causal effects accepted to Biometrika, a top theoretical statistics journal.
2022-01-14: NURD for online datacenter straggler prediction accepted to MLSys 2022.
2021-08-17: Won Meta Research Award on Statistics for Improving Insights, Models, and Decisions.
2021-07-29: Programming with Neural Surrogates of Programs accepted to Onward! 2021.
2021-05-20: GIL for generalizable and interpretable configuration extrapolation accepted to ESEC/FSE 2021.
2021-03-18: CIFellows Project Spotlight on CCC Blog and CRA Bulletin!
2021-01-04: Start my postdoc at PSG, MIT CSAIL!
2020-11-09: Attended EECS Rising Stars Workshop at UC Berkeley, virtually.
2020-11-03: Successfully defended my Ph.D. thesis!
2020-07-21: Selected as a 2020 Computing Innovation Fellow by CRA/CCC!
Acela: Predictable Datacenter-level Maintenance Job Scheduling
Yi Ding, Aijia Gao, Thibaud Ryden, Kaushik Mitra, Sukumar Kalmanje, Yanai Golany, Michael Carbin, Henry Hoffmann
SCOPE: Safe Exploration for Dynamic Computer Systems Optimization
Hyunji Kim, Ahsan Pervaiz, Henry Hoffmann, Michael Carbin, Yi Ding
Cello: Efficient Computer Systems Optimization with Predictive Early Termination and Censored Regression
Yi Ding, Alex Renda, Ahsan Pervaiz, Michael Carbin, Henry Hoffmann
CAFQA: A Classical Simulation Bootstrap for Variational Quantum Algorithms
Gokul Ravi, Pranav Gokhale, Yi Ding, William Kirby, Kaitlin Smith, Peter Love, Kenneth Brown, Henry Hoffmann, Frederic Chong
ASPLOS 2023: The 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
Minimax Designs for Causal Effects in Temporal Experiments with Treatment Habituation
Guillaume Basse, Yi Ding, Panos Toulis
Biometrika, 2023 (a top theoretical statistics journal)
NURD : Negative-Unlabeled Learning for Online Datacenter Straggler Prediction
Yi Ding, Avinash Rao, Hyebin Song, Rebecca Willett, Henry Hoffmann
MLSys 2022: The 5th Conference on Machine Learning and Systems
Programming with Neural Surrogates of Programs
Alex Renda, Yi Ding, Michael Carbin
Onward! 2021: The ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software
Generalizable and Interpretable Learning for Configuration Extrapolation
Yi Ding, Ahsan Pervaiz, Michael Carbin, Henry Hoffmann
ESEC/FSE 2021: The 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
Neighborhood Street Activity and Greenspace Usage Uniquely Contribute to Predicting Crime
Kathryn E Schertz, James Saxon, Carlos Cardenas-Iniguez, Luís MA Bettencourt, Yi Ding, Henry Hoffmann, Marc G Berman
npj Urban Sustainability, Nature Research Journal, 2021
A Polynomial-time Algorithm for Learning Nonparametric Causal Graphs
Ming Gao, Yi Ding, Bryon Aragam
NeurIPS 2020: The 34th Conference on Neural Information Processing Systems
Dynamical Systems Theory for Causal Inference with Application to Synthetic Control Methods
Yi Ding, Panos Toulis
AISTATS 2020: The 23rd International Conference on Artificial Intelligence and Statistics
Generative and Multi–phase Learning for Computer Systems Optimization
Yi Ding, Nikita Mishra, Henry Hoffmann
ISCA 2019: The 46th International Symposium on Computer Architecture
Multiresolution Kernel Approximation for Gaussian Process Regression
Yi Ding, Risi Kondor, Jonathan Eskreis-Winkler
NeurIPS 2017, Spotlight: The 31st Conference on Neural Information Processing Systems
Large Scale Kernel Methods for Online AUC Maximization
Yi Ding, Chenghao Liu, Peilin Zhao, Steven CH Hoi
ICDM 2017, Long Oral: The IEEE International Conference on Data Mining
An Adaptive Gradient Method for Online AUC Maximization
Yi Ding, Peilin Zhao, Steven CH Hoi, Yew-Soon Ong
AAAI 2015, Oral: The 29th AAAI Conference on Artificial Intelligence
Learning Relative Similarity by Stochastic Dual Coordinate Ascent
Pengcheng Wu, Yi Ding, Peilin Zhao, Chunyan Miao, Steven CH Hoi
AAAI 2014: The 28th AAAI Conference on Artificial Intelligence