NO SEMINAR THIS WEEK - see you next week!
Speaker
TBA
Speaker
TBA
Speaker
Shuwei Wang, PhD student at the University of Alberta, supervised by Dr. Vadim Bulitko
Title
Synthesizing Physics Formulae via Transformers
Abstract
Finding a compact formula that fits a set of input-output pairs and predicts outputs on unseen inputs is a fundamental problem in science. Symbolic regression automates the search for such formulae: search-based methods explore the space of possible formulae directly, while transformers pre-trained on synthetic data produce formulae of comparable quality substantially faster. Existing transformers, however, are prone to overfitting --- they find formulae that fit the training data well but do not extrapolate to input ranges unseen during training. We address this by shaping the set of formulae used to train a transformer, and show that the resulting formulae extrapolate substantially better. Fine-tuning the transformer on data with noise-corrupted target values further makes the synthesized formulae robust to noise in the observations. On SRBench and LLM-SRBench our transformer synthesizes a formula in about ten seconds and extrapolates better than all evaluated methods at a comparable budget. Search-based methods surpass our accuracy only when given one to three orders of magnitude more time.
Bio
My name is Shuwei Wang. I am a third-year PhD student in the department of Computing Science under the supervision of professor Bulitko, Vadim. My area of research is symbolic regression.
Timing & Location
UComm Seminar Room 2-108
pizza from 11:30, seminar from noon to 1 MDT
Add event to calendar
NO SEMINARS - Winter Closure
Now scheduling fall & winter term seminars - stay tuned!