DiscoGrad
Languages and libraries
automatic differentiation library
SHOW HN2024
232points
66comments
#321of 3,515 in 2024
Top 10%of 2024 by points
How HN took it
CuriousMostly questions and neutral comments
7 positive, 25 neutral or asking, 0 mixed, 2 critical, out of 34 comments about the project. Thread score +0.13.
Idea: 4 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Interesting approach to differentiating through branches
From 2 comments
When all you have is a hammer, ... you split up your house into wood and nails, and reduce it to a previously solved problem! In all seriousness, this is super interesting. I…
vessenes on HNThis is the sort of thing I expected to see when Chris Lattner moved to Google and started working on the Swift for Tensorflow project. I am so grateful that someone is making it…
dwrodri on HN
Objections
Existing autodiff tools like Enzyme and CppAD already work well
From 2 comments
So this confuses me slightly and I am keen to know the advantage of using this. I work on projects that heavily use auto-differentiation for complex models. The models are…
zaitanz on HNEnzyme is traditional, but super duper optimized, autodiff, that is, it returns the partial derivatives for one path taken through the program, ignoring other branches. DiscoGrad…
frankling_ on HN
Requests
Comparison with MCMC approaches
From 1 comment
Does that imply that every possible branch is optimised separately and then convoluted thereafter? If so, does it scale for very branchy programs? Do you have any comparisons to…
usgroup on HN
Questions
How does it compare to Enzyme and other autodiff tools
From 2 comments
How does this compare to Enzyme (https://enzyme.mit.edu/)?
s_tim on HNSo this confuses me slightly and I am keen to know the advantage of using this. I work on projects that heavily use auto-differentiation for complex models. The models are…
zaitanz on HN
Whether gradients are finite differences
From 1 comment
Obviously, some of this branching, etc. is not differentiable. Is it doing finite differences?
epr on HN
Alternatives named
Enzyme
From 1 comment
How does this compare to Enzyme (https://enzyme.mit.edu/)?
s_tim on HN
Ceres Solver
From 1 comment
Talk about the differences between this and ceres http://ceres-solver.org/.
ipunchghosts on HN
CppAD, ADOL-C, TMB
From 1 comment
So this confuses me slightly and I am keen to know the advantage of using this. I work on projects that heavily use auto-differentiation for complex models. The models are…
zaitanz on HN
Tapenade
From 1 comment
You should take a look at the Tapenade[0] automatic differentiation engine, more than 20 years of active development for Fortran and C. [0]:…
Loic on HN
Stan / MCMC
From 1 comment
Not really. The world of Bayesian modelling has much fancier tools: Hamiltonian MC. See MC Stan. There’s also been Gibbs samplers and other techniques which support discrete…
usgroup on HN