The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Associate Professor, Department of Electrical Engineering and Computer Science; Lead, Programming Systems Group
Michael Carbin is an associate professor in MIT’s Department of Electrical Engineering and Computer Science and a principal investigator at the Computer Science and Artificial Intelligence Laboratory, where he leads the Programming Systems Group. His group investigates the semantics, design, and implementation of systems that operate in the presence of uncertainty in their environment (perception), implementation (neural networks or approximate transformations), or execution (unreliable hardware). Carbin has received a Sloan Research Fellowship, a Facebook Research Award, a Google Faculty Research Award and an NSF Career Award. He earned a BS in computer science at Stanford University and an MS and PhD in electrical engineering and computer science from MIT.
- Baudart, G., Mandel, L., Atkinson, E., Sherman, B., Pouzet, M., Carbin, M. (2020). Reactive Probabilistic Programming. Programming Language Design and Implementation (PLDI).
- Lew, A. K., Towner, M. F. C., Sherman, B., Carbin, M., Mansinghka, V. K. (2020). A Type System and Semantics for Sound Programmable Inference in Probabilistic Languages. Principles of Programming Languages (POPL).
- Renda, A., Frankle, J., Carbin, M. (2020). Comparing Fine-tuning and Rewinding in Neural Network Pruning. International Conference on Learning Representations (ICLR).
- Mendis, C., Renda, A., Amarasinghe, S., Carbin, M. (2019). Ithemal: Accurate, Portable, and Fast Basic Block Throughput Estimation using Deep Neural Networks. International Conference on Machine Learning (ICML).
- Frankle, J., Carbin, M. (2019). The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks. International Conference on Learning Representations (ICLR).
Publications with the MIT-IBM Watson AI Lab