Pith. sign in

REVIEW 2 cited by

Scalars are universal: Equivariant machine learning, structured like classical physics

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 2106.06610 v4 pith:C4GUFSU3 submitted 2021-06-11 cs.LG math-phmath.MPstat.ML

Scalars are universal: Equivariant machine learning, structured like classical physics

classification cs.LG math-phmath.MPstat.ML
keywords equivariantscalarsomesymmetriesclassicaldifferentfunctionsfundamental
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible representations, some make use of high-order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), and permutations. Here we show that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincar\'e groups, at any dimensionality $d$. The key observation is that nonlinear O($d$)-equivariant (and related-group-equivariant) functions can be universally expressed in terms of a lightweight collection of scalars -- scalar products and scalar contractions of the scalar, vector, and tensor inputs. We complement our theory with numerical examples that show that the scalar-based method is simple, efficient, and scalable.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

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

  1. Explicit or Implicit? Encoding Physics at the Precision Frontier

    hep-ph 2026-03 conditional novelty 6.0

    On three precision classification tasks — reweighting-based unfolding, likelihood-ratio estimation, and weakly supervised anomaly detection — a Lorentz-equivariant transformer and a pretrained foundation model perform...

  2. Learning the Universe with the 2nd Generation of CAMELS: Varying 35 parameters of the IllustrisTNG model in (50Mpc/h)^3 boxes

    astro-ph.CO 2026-06 unverdicted novelty 4.0

    New CAMELS simulations in larger (50 Mpc/h)^3 boxes with 35 varied parameters produce tighter neural-network constraints on model parameters than prior smaller-volume runs, with public data release.