Workshop on Symbolic Regression
24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing
Research Institute for Symbolic Computation, Johannes Kepler University, Linz, Austria
12-15 September 2022
- 10 July 2022: Paper submission (strict deadline)
- 5 August 2022: Notification of acceptance
- 5 September 2022: Registration
- 12-15 September 2022: Symposium
- 31 October 2022: Revised papers for post-proceedings
- Gabriel Kronberger, University of Applied Sciences Upper Austria
- Michael Kommenda, University of Applied Sciences Upper Austria
- Fabrício Olivetti de França, Universidade Federal do ABC, Sao Paulo
Aim and description
Symbolic regression (SR) designates symbolic methods for the identification of regression models. Especially with the focus on interpretability and explainability in AI research, symbolic regression takes a leading role among machine learning methods, whenever model inspection and understanding by a domain expert is desired. Traditionally the most popular solution method for SR is genetic programming – an evolutionary algorithm. In recent years several non-evolutionary techniques have emerged including techniques based on artificial neuronal networks. Nowadays, the best SR algorithms combine symbolic and numeric methods for instance for optimization of numeric parameters.
Examples where symbolic regression already produces outstanding results include modeling where interpretability is desired, modeling of non-linear dependencies, modeling with small data sets or noisy data, modeling with additional constraints, or modeling of differential equation systems.
The focus of this workshop is to further advance the state-of-the-art in symbolic regression by gathering experts in the field of symbolic regression and facilitating an exchange of novel research ideas. Therefore, we encourage submissions presenting novel symbolic, numeric or hybrid techniques for symbolic regression, theoretical work on issues of generalization, size and interpretability of the models, or algorithmic improvements to make the techniques more efficient, more reliable and generally better controlled.
Particular topics of interest include, but are not limited to:
- Evolutionary and non-evolutionary algorithms for symbolic regression
- Improving stability of symbolic regression algorithms
- Integration of side-information (physical laws, constraints, …)
- Optimization of numeric parameters in non-linear symbolic regression models
- Novel representations to reduce the size of the search space
- SR for (partial) differential equations
- SR prediction intervals and parameter confidence intervals
- Benchmarking symbolic regression algorithms
- Symbolic regression for scientific machine learning
- Innovative symbolic regression applications
We invite submissions containing original research results in the form of:
+ full research papers
+ short papers (work in progress)
Papers of up to 8 pages prepared according to the CPS template must be submitted electronically using the submission system that will be later accessible through EasyChair.
Research papers must contain original research results not submitted and not published elsewhere. Authors who want to present work in progress or discuss new aspects or a survey of their older research results at the workshop are welcome to submit an extended abstract (up to 4 pages). Papers will be refereed and accepted on the basis of their scientific merit and relevance to the workshop topics.
The research papers that are accepted and presented at the symposium will be collected as post-proceedings published by Conference Publishing Services (CPS) and will be submitted for indexing by the ISI Web of Science, DBLP, SCOPUS, etc.
- Michael Affenzeller – University of Applied Sciences Upper Austria
- Bogdan Burlacu – University of Applied Sciences Upper Austria
- Fabrício Olivetti de França – Universidade Federal do ABC, Sao Paulo
- Steven Gustafson – Noonum, Inc
- Michael Kommenda – University of Applied Sciences Upper Austria
- Gabriel Kronberger – University of Applied Sciences Upper Austria
- William La Cava – Boston Children’s Hospital and Harvard Medical School