Deep Symbolic Optimization: A Framework for Symbolic Optimization Using Deep Learning
Date:
Workshop Talk at Center for Advanced Signal and Image Sciences (CASIS) 25th Annual Workshop, Virtual
Workshop talk introducing Deep Symbolic Optimization as a framework for symbolic optimization using deep learning. DSO uses a recurrent neural network to generate candidate solutions as sequences of discrete symbols, such as mathematical expressions, and trains it with a risk-seeking policy gradient that focuses learning on the best-performing samples. The talk illustrated the framework on symbolic regression and interpretable control, two tasks where compact, human-readable solutions are especially valuable.
The DSO framework introduced in this talk is developed in the following papers: Deep Symbolic Regression, ICLR 2021 (Oral) ยท A Unified Framework for Deep Symbolic Regression, NeurIPS 2022