8 citations · 10 across the 4 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 1 cited
How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy
Badr AlKhamissi, Akshay Srinivasan, Zeb-Kurth Nelson +1
Alchemy is a new meta-learning environment rich enough to contain interesting abstractions, yet simple enough to make fine-grained analysis tractable. Further, Alchemy provides an…
math.OC2021
Computing the Newton-step faster than Hessian accumulation
Akshay Srinivasan, Emanuel Todorov
Computing the Newton-step of a generic function with decision variables takes flops. In this paper, we show that given the computational graph of the function, this bo…