frankling_

↗ HN profile [ 78.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool…

  2. We just pushed a new-and-improved version of DiscoGrad, a tool to do automatic differentiation across C++ programs with parameter-dependent control flow ("if (f(x) < c) { ... }") and randomness. This is needed to…