Roy Frostig

Roy Frostig

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
You Only Linearize Once: Tangents Transpose to Gradients
Alexey Radul
Adam Paszke
Roy Frostig
Matthew Johnson
Dougal Maclaurin
POPL (2023), pp. 1246-1274
The advantages of multiple classes for reducing overfitting from test set reuse
Vitaly Feldman
Roy Frostig
Moritz Hardt
ICML (2019)
Compiling machine learning programs via high-level tracing
Roy Frostig
Matthew Johnson
Chris Leary
SysML (2018)
Measuring the Effects of Data Parallelism on Neural Network Training
Chris Shallue
Jaehoon Lee
Joseph Antognini
Jascha Sohl-dickstein
Roy Frostig
George Dahl
Journal of Machine Learning Research (JMLR) (2018)
Random Features for Compositional Kernels
Amit Daniely
Roy Frostig
Vineet Gupta
Yoram Singer
arXiv (2017)
Search on Google Scholar