AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

End-to-end Symbolic Regression with Transformers

Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Guillaume Lample, Francois Charton

NeurIPS 2022 · Learning theory and algorithms › Combinatorial and search optimization · approach: Decision-focused optimization · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
predict full expression with constants (E2E) instead of skeleton only, both with BFGS refinement (ablation)Transformer symbolic regression · In-domain validationAcc_0.001: 0.17 -> 0.29Improved
add BFGS refinement initialized from model-predicted constants (ablation)E2E model · In-domain validationAcc_0.001: 0.09 -> 0.29Improved
E2E without refinement vs skeleton + BFGS (ablation)E2E model · In-domain validationR^2 / Acc_0.001: R^2 0.43 -> 0.62; Acc_0.001 0.17 -> 0.09Mixed
initialize BFGS with model predictions instead of random init (ablation)E2E + BFGS · In-domain validationR^2: 0.44 -> 0.68Improved
BFGS refinement with random init instead of no refinement (ablation)E2E model · In-domain validationR^2: 0.62 -> 0.44Hurt
increase number of input points N (ablation)E2E and skeleton models · In-domain validationaccuracyImproved
increase target noise without refinement (ablation)E2E no BFGS · In-domain validationaccuracyHurt
use beam search instead of sampling for decoding candidates (ablation)E2E model without refinement · SRBench black-boxmedian R^2Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy