1 code implementation • 4 Mar 2023 • Deval Shah, Tor M. Aamodt
Underlying RLEL is our observation that the search space of label encodings can be constrained and efficiently explored by using a continuous search space of real-valued label encodings combined with a regularization function designed to encourage encodings with certain properties.
1 code implementation • ICLR 2022 • Deval Shah, Zi Yu Xue, Tor M. Aamodt
Prior work has shown that solving a regression problem with a set of binary classifiers can improve accuracy by utilizing well-studied binary classification algorithms.
1 code implementation • NeurIPS 2020 • Md Aamir Raihan, Tor M. Aamodt
For ResNet-50 on ImageNet SWAT reduces total floating-point operations (FLOPS) during training by 80% resulting in a 3. 3$\times$ training speedup when run on a simulated sparse learning accelerator representative of emerging platforms while incurring only 1. 63% reduction in validation accuracy.