[Buttons840]

I recently ported a reinforcement learning algorithm from PyTorch to Julia. I did my best to keep the implementations the same, with the same hyperparameters, network sizes, etc. I think I did a pretty good job because the performance was similar, solving the CartPole environment in the a similar number of steps, etc.

The Julia implementation ended up being about 2 to 3 times faster. I timed the core learning loops, the network evaluations and gradient calculations and applications, and PyTorch and Julia performed similar here. So it wasn't that Julia was faster at learning. Instead it was all the in-between, all the "book keeping" in Python ended up being much faster in Julia, enough so that overall it was 2 to 3 times faster.

(I was training on a CPU though. Things may be different if you're using a GPU, I don't know.)

[gdpr]

Similar experience over here. (G)ARCH models are severely underserved in Python, and I could not be bothered to learn a Probabilistic programming abstraction like Pyro or Stan just to build a quick prototype myself.

Chose Julia instead. Took 4 hours to get everything sorted out (including getting IT to allow Julias package manager to actually download stuff) and have the first model running just putting a paper into code. Since code is just writing the math, this is a vast communication improvement.

After fiddling around withit at home for a week, this was the first professional experience and I'm blown away.

[wiz21c]

could you tell us more ? It looks like a very in depth / interesting benchmark

[Buttons840]

I will make a blog post about it.

[stellalo]

That’s interesting: did you use Flux?

[Buttons840]

Yes. I used Flux.