DiffTaichi: Differentiable Programming for Physical Simulation · HackerPapers discussions

DiffTaichi: Differentiable Programming for Physical Simulation — mentioned by montebicyclelo

Mon, 08 Mar 2021 15:17:31 GMT

That's a really nice write up. It's insane how similar our approaches are. Could it be a case of [1] (but on a non grand scale) :P? I can list my sources of inspiration: [2] [3] [4]. I also tried training convolutional networks, using the soft life set-up, but failed to get them to converge. [1] https://en.wikipedia.org/wiki/Multiple_discovery [2] https://kevingal.com/blog/mona-lisa-gol.html [3] https://arxiv.org/abs/1910.00935 [4] https://nicholasrui.com/2017/12/18/convolutions-and-the-game...

Paper and discussion history. A mention is not an endorsement.

DiffTaichi: Differentiable Programming for Physical Simulation — HN submission

Wed, 29 Jan 2020 11:08:32 GMT

DiffTaichi: Differentiable Programming for Physical Simulation

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

DiffTaichi: Differentiable Programming for Physical Simulation — mentioned by MrMoenty

Tue, 05 Nov 2019 03:53:48 GMT

My point is that the parent's comment is mostly right: a frequent challenge in ML is black box computational units which don't expose the necessary information to run autograd. Even if the underlying mathematical function is not differentiable everywhere, but only on most points, having autograd available is valuable for use in training. Hence you get works like this [1] which reimplement existing systems in a way that is amenable to autograd. [1] https://arxiv.org/abs/1910.00935

Paper and discussion history. A mention is not an endorsement.

DiffTaichi: Differentiable Programming for Physical Simulation — HN submission

Wed, 30 Oct 2019 11:32:40 GMT

DiffTaichi: Differentiable Programming for Physical Simulation

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.