decile-team / cords

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.
https://cords.readthedocs.io/en/latest/
MIT License
322 stars 54 forks source link

CORDS gradient calculations for different loss functions #1

Closed krishnatejakk closed 3 years ago

krishnatejakk commented 3 years ago

a) Implement gradient calculation for Squared Loss, Negative logistic loss, General loss function gradient computation, Hinge loss.

b) Integrate the new gradient calculation with different selection strategies

krishnatejakk commented 3 years ago

Integrated the gradient calculation with torch loss functions