Pith. sign in

REVIEW 3 cited by

OccamNet: A Fast Neural Model for Symbolic Regression at Scale

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.10784 v3 pith:5RKKVEAO submitted 2020-07-16 cs.LG cs.NEstat.ML

classification cs.LGcs.NEstat.ML
keywords functionssymbolicfitsmodelneuraloccamnetregressionanalytic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural networks' expressiveness comes at the cost of complex, black-box models that often extrapolate poorly beyond the domain of the training dataset, conflicting with the goal of finding compact analytic expressions to describe scientific data. We introduce OccamNet, a neural network model that finds interpretable, compact, and sparse symbolic fits to data, \`a la Occam's razor. Our model defines a probability distribution over functions with efficient sampling and function evaluation. We train by sampling functions and biasing the probability mass toward better fitting solutions, backpropagating using cross-entropy matching in a reinforcement-learning loss. OccamNet can identify symbolic fits for a variety of problems, including analytic and non-analytic functions, implicit functions, and simple image classification, and can outperform state-of-the-art symbolic regression methods on real-world regression datasets. Our method requires a minimal memory footprint, fits complicated functions in minutes on a single CPU, and scales on a GPU.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. KAN: Kolmogorov-Arnold Networks

    cs.LG 2024-04 conditional novelty 8.0 of 10

    KANs with learnable univariate spline activations on edges achieve better accuracy than MLPs with fewer parameters, faster scaling, and direct visualization for scientific discovery.

  2. Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches

    math.NA 2026-04 unverdicted novelty 5.0 of 10

    The work introduces a modulation-based analytical method for singularity proofs in singular PDEs and refines ML techniques like PINNs and KANs to identify blowup solutions, with application to the open 3D Keller-Segel...

  3. Data-driven Discovery of Digital Twins in Biomedical Research

    q-bio.QM 2025-08 conditional novelty 2.0 of 10

    Sparse regression, especially Bayesian approaches, generally outperform symbolic regression for ODE-based digital twin discovery in biology, though the evidence is qualitative and non-systematic.

Pith tools