16 citations · 16 across the 3 of their papers we have counts for
3 papers
BOND: License to Train with Black-Box Functions
Andrew Clark, Jack Moursounidis, Osmaan Rasouli +3
We introduce Bounded Numerical Differentiation (BOND), a perturbative method for estimating the gradients of black-box functions. BOND is distinguished by its formulation, which ad…
Minimax Active Learning
Sayna Ebrahimi, William Gan, Dian Chen +5
Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either…
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul +4
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory…