A tiny repository containing just one notebook. The notebook shows how to efficiently approximate the trace of a Hessian, using automatic differentiation (PyTorch) and a recently published randomized algorithm called Hutch++.
forked from akshayka/hessian_trace_estimation
-
Notifications
You must be signed in to change notification settings - Fork 0
Hessian trace estimation using PyTorch and Hutch++
License
eneamc/hessian_trace_estimation
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Hessian trace estimation using PyTorch and Hutch++
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 100.0%