Timezone: »

Symbolic Regression via Deep Reinforcement Learning Enhanced Genetic Programming Seeding
Terrell Mundhenk · Mikel Landajuela · Ruben Glatt · Claudio P Santiago · Daniel faissol · Brenden K Petersen

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @ Virtual #None

Symbolic regression is the process of identifying mathematical expressions that fit observed output from a black-box process. It is a discrete optimization problem generally believed to be NP-hard. Prior approaches to solving the problem include neural-guided search (e.g. using reinforcement learning) and genetic programming. In this work, we introduce a hybrid neural-guided/genetic programming approach to symbolic regression and other combinatorial optimization problems. We propose a neural-guided component used to seed the starting population of a random restart genetic programming component, gradually learning better starting populations. On a number of common benchmark tasks to recover underlying expressions from a dataset, our method recovers 65% more expressions than a recently published top-performing model using the same experimental setup. We demonstrate that running many genetic programming generations without interdependence on the neural-guided component performs better for symbolic regression than alternative formulations where the two are more strongly coupled. Finally, we introduce a new set of 22 symbolic regression benchmark problems with increased difficulty over existing benchmarks. Source code is provided at www.github.com/brendenpetersen/deep-symbolic-optimization.

Author Information

Terrell Mundhenk (Lawrence Livermore National Lab)
Mikel Landajuela (Lawrence Livermore National Labs)
Ruben Glatt (Lawrence Livermore National Laboratory)

Ruben has a background in Mechatronics and Mechanical Engineering and has turned to Artificial Intelligence (AI) where his main interest lies in Machine Learning (ML) research, particular in Reinforcement Learning (RL) with a focus on human-inspired learning approaches that rely on reuse of previously acquired knowledge. He received his Ph.D. in Computer Engineering in the area of ML at the Escola Politécnica of the University of São Paulo (USP), Brazil, holds a master degree in Mechanical Engineering in the area of controlling mechanical systems from the São Paulo State University (UNESP), Brazil, and a Diplom-Ingenieur degree in Mechatronics in the area of sensors and robotics from the Karlsruhe Institute of Technology (KIT), Germany. During his Ph.D., Ruben’s efforts were recognized through various prestigious awards, like the Google Research Award for Latin-America, the Upsilon Pi Epsilon Honor Society Award for academic excellence, an invitation to the Heidelberg Laureate Forum as Outstanding Young Researcher, various travel grants to conferences and events, as well as best paper, best student poster, and distinguished work awards for his contributions at international events. Apart from his academic experiences, Ruben has acquired years of professional experiences before and during his studies while working in the technology and energy sector and more recently with the organization of international ML conferences. He also has been actively building the ML community in São Paulo by organizing meetups and workshops with a strong emphasis on diversity and inclusion. Currently, Ruben is a Postdoc Researcher at the Lawrence Livermore National Laboratory, USA, working on ML projects with a focus on Multiagent RL in a collaborative setting.

Claudio P Santiago (Lawrence Livermore National Laboratory)
Daniel faissol (Lawrence Livermore National Labs)
Brenden K Petersen (Lawrence Livermore National Laboratory)

More from the Same Authors

  • 2019 : Lunch + Poster Session »
    Frederik Gerzer · Bill Yang Cai · Pieter-Jan Hoedt · Kelly Kochanski · Soo Kyung Kim · Yunsung Lee · Sunghyun Park · Sharon Zhou · Martin Gauch · Jonathan Wilson · Joyjit Chatterjee · Shamindra Shrotriya · Dimitri Papadimitriou · Christian Schön · Valentina Zantedeschi · Gabriella Baasch · Willem Waegeman · Gautier Cosne · Dara Farrell · Brendan Lucier · Letif Mones · Caleb Robinson · Tafara Chitsiga · Victor Kristof · Hari Prasanna Das · Yimeng Min · Alexandra Puchko · Alexandra Luccioni · Kyle Story · Jason Hickey · Yue Hu · Björn Lütjens · Zhecheng Wang · Renzhi Jing · Genevieve Flaspohler · Jingfan Wang · Saumya Sinha · Qinghu Tang · Armi Tiihonen · Ruben Glatt · Muge Komurcu · Jan Drgona · Juan Gomez-Romero · Ashish Kapoor · Dylan J Fitzpatrick · Alireza Rezvanifar · Adrian Albert · Olya (Olga) Irzak · Kara Lamb · Ankur Mahesh · Kiwan Maeng · Frederik Kratzert · Sorelle Friedler · Niccolo Dalmasso · Alex Robson · Lindiwe Malobola · Lucas Maystre · Yu-wen Lin · Surya Karthik Mukkavili · Brian Hutchinson · Alexandre Lacoste · Yanbing Wang · Zhengcheng Wang · Yinda Zhang · Victoria Preston · Jacob Pettit · Draguna Vrabie · Miguel Molina-Solana · Tonio Buonassisi · Andrew Annex · Tunai P Marques · Catalin Voss · Johannes Rausch · Max Evans