PySR
StaticCompiler.jl
PySR | StaticCompiler.jl | |
---|---|---|
7 | 16 | |
1,911 | 471 | |
- | - | |
9.6 | 6.9 | |
4 days ago | about 1 month ago | |
Python | Julia | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PySR
-
Potential of the Julia programming language for high energy physics computing
> Yes, julia can be called from other languages rather easily
This seems false to me. StaticCompiler.jl [1] puts in their limitations that "GC-tracked allocations and global variables do not work with compile_executable or compile_shlib. This has some interesting consequences, including that all functions within the function you want to compile must either be inlined or return only native types (otherwise Julia would have to allocate a place to put the results, which will fail)." PackageCompiler.jl [2] has the same limitations if I'm not mistaken. So then you have to fall back to distributing the Julia "binary" with a full Julia runtime, which is pretty heavy. There are some packages which do this. For example, PySR [3] does this.
There is some word going around though that there is an even better static compiler in the making, but as long as that one is not publicly available I'd say that Julia cannot easily be called from other languages.
[1]: https://github.com/tshort/StaticCompiler.jl
[2]: https://github.com/JuliaLang/PackageCompiler.jl
[3]: https://github.com/MilesCranmer/PySR
- Symbolicregression.jl – High-Performance Symbolic Regression in Julia and Python
-
[D] Is there any research into using neural networks to discover classical algorithms?
I first learned about it with PySR https://github.com/MilesCranmer/PySR, they have an arxiv paper with some use cases as well.
-
Symbolic Regression is NP-hard
I encourage everyone to read this paper. It's well written and easy to follow along. To the uninitiated, SR is the problem of finding a mathematical (symbolic) expression that most accurately describes a dataset of input-output examples (regression). The most naive implementation of SR is basically a breath first search starting from the simplest program tree: x -> sin(x) -> cos(x) ... sin(cos(tan(x))) until timeout. However, we can prune out equivalent expressions and, in general, the problem is embarrassingly parallel which alludes to some hope that we can solve this pretty fast (check out PySR[1] for a modern implementation). I find SR fascinating because it can be used for model distillation: learn a DNN approximation and "distill" it to a symbolic program.
Note that the paper talks about the decision version of the SR problem. ie: can we discover the global optimum expression. I think this proof is important for the SR community but not particularly surprising (to me). However, I'm excited by the potential future work for this paper! A couple of discussion points:
* First, SR is technically a bottom up program synthesis problem where the DSL (math) has an equivalence operator. Can we use this proof to impose stronger guarantees on the "hyperparameters" for bottom up synthesis. Conversely, does the theoretical foundation of the inductive synthesis literature [2] help us define tighter bounds?
* Second, while SR itself is NP hard, can we say anything about the approximate algorithms (eg: distilling a deep neural network to find a solution[3])? Specifically, what proof tell us about the PAC learnability of SR?
Anyhow, pretty cool seeing such work getting more attention!
[1] https://github.com/MilesCranmer/PySR
[2] https://susmitjha.github.io/papers/togis17.pdf
[3] https://astroautomata.com/paper/symbolic-neural-nets/
-
‘Machine Scientists’ Distill the Laws of Physics from Raw Data
I found it curious that one of the implementations of symbolic regression (the "machine scientist" referenced in the article) is a Python wrapper on Julia: https://github.com/MilesCranmer/PySR
I don't think I've seen a Python wrapper on Julia code before.
- Is it possible to create a Python package with Julia and publish it on PyPi?
-
[D] Inferring general physical laws from observations in 300 lines of code
This is really neat! Since you're interested in this subject, you may also appreciate PySR and the corresponding paper which uses Graph Neural Networks to perform symbolic regression.
StaticCompiler.jl
-
Potential of the Julia programming language for high energy physics computing
Yes, julia can be called from other languages rather easily, Julia functions can be exposed and called with a C-like ABI [1], and then there's also various packages for languages like Python [2] or R [3] to call Julia code.
With PackageCompiler.jl [4] you can even make AOT compiled standalone binaries, though these are rather large. They've shrunk a fair amount in recent releases, but they're still a lot of low hanging fruit to make the compiled binaries smaller, and some manual work you can do like removing LLVM and filtering stdlibs when they're not needed.
Work is also happening on a more stable / mature system that acts like StaticCompiler.jl [5] except provided by the base language and people who are more experienced in the compiler (i.e. not a janky prototype)
[1] https://docs.julialang.org/en/v1/manual/embedding/
[2] https://pypi.org/project/juliacall/
[3] https://www.rdocumentation.org/packages/JuliaCall/
[4] https://github.com/JuliaLang/PackageCompiler.jl
[5] https://github.com/tshort/StaticCompiler.jl
-
Julia App Deployment
PackageCompiler, but it' s a fat runtime and not cross compile. A thin runtime is currently not possible without sacrifices for feature as https://github.com/tshort/StaticCompiler.jl.
-
JuLox: What I Learned Building a Lox Interpreter in Julia
https://github.com/tshort/StaticCompiler.jl/issues/59 Would working on this feasible?
- Making Python 100x faster with less than 100 lines of Rust
- What's Julia's biggest weakness?
-
Size of a "hello world" application
I just read the project's documentation at https://github.com/tshort/StaticCompiler.jl. It does produce a "hello world" application that is only 8.4k in size 👍. I do like that it can work on Mac OS. Hopefully Windows support will come soon.
-
Why Julia 2.0 isn’t coming anytime soon (and why that is a good thing)
See https://github.com/tshort/StaticCompiler.jl
- My Experiences with Julia
-
Julia for health physics/radiation detection
You're probably dancing around the edges of what [PackageCompiler.jl](https://github.com/JuliaLang/PackageCompiler.jl) is capable of targeting. There are a few new capabilities coming online, namely [separating codegen from runtime](https://github.com/JuliaLang/julia/pull/41936) and [compiling small static binaries](https://github.com/tshort/StaticCompiler.jl), but you're likely to hit some snags on the bleeding edge.
-
We Use Julia, 10 Years Later
using StaticCompiler # `] add https://github.com/tshort/StaticCompiler.jl` to get latest master
What are some alternatives?
GeneticAlgorithmPython - Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).
julia - The Julia Programming Language
TorchGA - Train PyTorch Models using the Genetic Algorithm with PyGAD
PackageCompiler.jl - Compile your Julia Package
mljar-supervised - Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation
acados - Fast and embedded solvers for nonlinear optimal control
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
GPUCompiler.jl - Reusable compiler infrastructure for Julia GPU backends.
diffeqpy - Solving differential equations in Python using DifferentialEquations.jl and the SciML Scientific Machine Learning organization
oneAPI.jl - Julia support for the oneAPI programming toolkit.
python-bigsimr
LoopVectorization.jl - Macro(s) for vectorizing loops.