Jackpot is a Python package implementing the methods described in this paper.
pip install -e .
-
Notifications
You must be signed in to change notification settings - Fork 0
Jackpot (Jacobian Kernel Projection Optimization) is a PyTorch-compatible algorithm for approximating uncertainty regions in inverse problems. Given noisy observations and a forward mapping, Jackpot constructs a low-dimensional adversarial manifold that approximates the set of all possible inputs consistent with the output within a tolerance.
munnath/jackpot
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Jackpot (Jacobian Kernel Projection Optimization) is a PyTorch-compatible algorithm for approximating uncertainty regions in inverse problems. Given noisy observations and a forward mapping, Jackpot constructs a low-dimensional adversarial manifold that approximates the set of all possible inputs consistent with the output within a tolerance.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published