@folivetti
Researcher and professor at Federal University of ABC (https://www.ufabc.edu.br/) Working on symbolic regression, program synthesis, and optimization. https://github.com/folivetti/ https://www.instagram.com/fabriciolivetti/
TinyverseGP: Minimalistic implementations of different representations for Genetic Programming github.com/gpbench/tiny... #mlsky #artificialintelligence #geneticprogramming
Here's a little summary of the #symbolicregression in Physical Sciences meeting hosted at the #royalsociety . Plenty of interesting discussions and perspectives for the future of SR: www.linkedin.com/posts/gabrie...
This new algorithm pairs well with another tool we just released bsky.app/profile/foli...
This paper will be presented at #GECCO2025 but you can already read the pre-print at arxiv.org/abs/2501.17859
The source-code and binaries are available at github.com/folivetti/sr... together with additional info.
#GECCO2025 #SymbolicRegression #GeneticProgramming
This tool is compatible with a lot of popular SR algorithms such as ππ©ππ«π¨π§, ππ²ππ, ππ’π§π π¨, π
πππ, ππππ, πππ, ππ-πππππ, and many more!
It is especially compatible with the new algorithm eggp (bsky.app/profile/foli...)
You can also search for the top building blocks by frequency and average fitness. This can help unlock new discoveries from the knowledge built during the search.
A little demo of what it can do:
asciinema.org/a/713509
Once you load the expressions, you can explore them by requesting the top-N expressions associated with different filters: by size, by number of parameters or ... ππ² π©πππππ«π§ π¦ππππ‘π’π§π parts of the expressions!
With this tool, you can load a set of symbolic models obtained from any combination of multiple runs from the same or different algorithms, or with different hyper-parameters, using only the returned Pareto front or the entire search history.
β οΈ(another) New paper alert
rEGGression: an Interactive and Agnostic Tool for the Exploration of Symbolic Regression Models introduces a new tool for symbolic models that allow the user to go beyond the traditional Pareto front.
#GECCO2025 #SymbolicRegression #GeneticProgramming
This work will be presented at #GECCO2025 but we already got an arXiv version available at arxiv.org/abs/2501.17848 and the source-code at github.com/folivetti/sr...
All the experiments can be replicated with github.com/folivetti/eg...
This improves the results to such an extent that a traditional GP (as in tinyGP) can compete with the popular Operon and PySR algorithms.
The current implementation comes with many customization options including exporting the generated e-graph for further exploration.
For example, if in the first generation the search visits the expression (x+x) it will avoid generating this expression again in future generations and most of their equivalents, such as 2x, 3x/x, 3x - x, etc.
β οΈNew paper alert β οΈ
Improving Genetic Programming for Symbolic Regression with Equality Graphs exploits e-graphs to generate equivalent expressions proposes new operators that creates unvisited expressions during the search.
#GECCO2025 #SymbolicRegression #GeneticProgramming
Time is on your side? Yes it is!
The deadline for the #symbolicregression workshop at #gecco2025, was just extended to April 2nd! We are looking forward for your submissions! More info: heal.heuristiclab.com/research/sym...
You are all preparing some cool papers for #symbolicregression workshop at #gecco2025, right? Just remember, the deadline is on March 26! Share your new and cool ideas with this ever growing community! More info: heal.heuristiclab.com/research/sym...
Tell me about it :-D We're currently fighting to split the course into CS and non-CS version. But I'm already happy that we don't teach this course in Java anymore :-P
The main challenge here is to make them understand how a function works, what are variables, and why the order of instructions matter :-) not the easiest of the courses to teach...
Here we have the course "Information Processing" (which I'm teaching right now) that is basically programming 101 for a mix of students (CS and non-CS). The main goal here is to teach the very basics so each student is prepared to learn their respective niche language when time comes.
5 PhD positions for a project on Wireless THz Communication between TU Wien and University of Applied Sciences Upper Austria. One of such positions is about equation learning with #symbolicregression . Don't miss this opportunity! More info: jobs.tuwien.ac.at/Job/246521
I feel the same, and not only as a reviewer, as an author as well, especially when we get good reviewers :)
Is the evolution metaphor still necessary or even useful for genetic programming? link.springer.com/article/10.1... #geneticprogramming #machinelearning #artificialintelligence #datascience
We have a date! #symbolicregression workshop at #gecco2025 now has a deadline: March 26. Be sure to share your cool ideas with us heal.heuristiclab.com/research/sym...
Meeting on βSymbolic Regression in the Physical Sciencesβ.
Date: 28 - 29 April 2025,
Location: The Royal Society, 6 β 9 Carlton House Terrace, London, SW1Y 5AG
Details and registration:
royalsociety.org/science-even...
is it really useful in practice to have explicit feature transformation in these templates? (e.g. f(x1^2,x1*x2)). It seems to me that the user is doing the SR job :-P Wouldn't a syntax like `p1 * x1 + f1 - sin(f2)` be enough and cleaner?
Hey #symbolicregression folks! Are you working on something novel, crazy, bound to uncover the secrets of the universe? Don't keep it to yourself, join us at #gecco2025 SymReg workshop and let's discuss it over a coffee: heal.heuristiclab.com/research/sym... (deadline tbd) #geneticprogramming
This looks really cool!