Show HN: Boldly go where Gradient Descent has never gone before with DiscoGrad

• DiscoGrad

  2 202 7.0 C++

  DiscoGrad - automatically differentiate across conditional branches in C++ programs

  

• InfluxDB

  www.influxdata.com featured

  Purpose built for real-time analytics at any scale. InfluxDB Platform is powered by columnar analytics, optimized for cost-efficient storage, and built with open data standards.

  

• StochasticAD.jl

  4 198 8.5 Julia

  Research package for automatic differentiation of programs containing discrete randomness.

  Yeah, those tricks are highly related to what we do, the main difference being that we don't require a priori information about the distributions involved in the program. Instead, we compute a density estimation of the distribution of branch conditions at runtime, which makes things quite general and fully automatic, at the cost of some accuracy.

  As an aside, the combination "known distributions + automation" is covered in the Julia world by stochasticAD (https://github.com/gaurav-arya/StochasticAD.jl).

• spytorch

  1 280 0.0 Jupyter Notebook

  Tutorial for surrogate gradient learning in spiking neural networks

Suggest a related project