cords
cords copied to clipboard
decile-team
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.
I tried to run some experiments as follows: - Ran full cifar10 without any subset selection method to train resnet50 which took around 32m 31s. - Ran Gradmatch cifar10 subset...
Implement the following versions of OMP: 1. FNNOMP (https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7012095) 2. SNNOMP (https://hal.univ-lorraine.fr/hal-01585253/document)
Fixes #16 submodlib is now used for the CRAIG strategy/dataloader as well as the submodular strategy/dataloader. Please let me know if you have any feedback! Notes: - I am not...
1. Update readitdocs with new documentation and release the latest version of CORDS
1. Implement the CRUST strategy in the supervised learning setting. 2. Create the CRUST data loader class building it on top of adaptive_dataloader class.
Metadata
Owner
Metadata
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.