I am an Assistant Professor in the Computer Science department at Cornell University. My research interests include algorithmic, software, and hardware techniques for high-performance machine learning, with a focus on relaxed-consistency variants of stochastic algorithms such as asynchronous and low-precision stochastic gradient descent (SGD). My work builds towards using these techniques to construct data analytics and machine learning frameworks, including for deep learning, that are efficient, parallel, and distributed.
I graduated from Stanford University in 2017, where I was advised by Kunle Olukotun and by Chris Ré.
Advanced Machine Learning Systems
- A Two Pronged Progress in Structured Dense Matrix Multiplication,Christopher De Sa, Albert Gu, Rohan Puttagunta, Christopher Ré, Atri Rudra In SODA: ACM-SIAM Symposium on Discrete Algorithms (SODA18), January 2018.
- Gaussian Quadrature for Kernel Features Spotlight,Tri Dao, Christopher De Sa, Christopher Ré In NIPS: Proceedings of the 30th Neural Information Processing Systems Conference, December 2017.
- Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent, Chris De Sa, Matt Feldman, Christopher Ré, and Kunle Olukotun, In ISCA: 44th International Symposium on Computer Architecture, June 2017.
- Flipper: A Systematic Approach to Debugging Training Sets, Paroma Varma, Dan Iter, Christopher De Sa, and Christopher Ré, In HILDA: Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics, May 2017.
- Data Programming: Creating Large Training Sets, Quickly, Alex Ratner, Chris De Sa, Sen Wu, Daniel Selsam, and Christopher Ré. In NIPS: Proceedings of the 29th Neural Information Processing Systems Conference, December 2016.