paper-with-me

홈 › Papers

Dimensionless machine learning: Imposing exact units equivariance

2022-04-02 · Soledad Villar, Weichi Yao, David W. Hogg, Ben Blum-Smith, Bianca Dumitrascu

Units equivariance (or units covariance) is the exact symmetry that follows from the requirement that relationships among measured quantities of physics relevance must obey self-consistent dimensional scalings. Here, we express this symmetry in terms of a (non-compact) group action, and we employ dimensional analysis and ideas from equivariant machine learning to provide a methodology for exactly units-equivariant machine learning: For any given learning task, we first construct a dimensionless version of its inputs using classic results from dimensional analysis, and then perform inference in the dimensionless space. Our approach can be used to impose units equivariance across a broad range of machine learning methods which are equivariant to rotations and other groups. We discuss the in-sample and out-of-sample prediction accuracy gains one can obtain in contexts like symbolic regression and emulation, where symmetry is important. We illustrate our approach with simple numerical examples involving dynamical systems in physics and ecology.

📄 PDF Abstract BibTeX arXiv:2204.00887

Code (1)

weichiyao/scalaremlp 공식 구현 jax

Tasks

BIG-bench Machine LearningSymbolic Regression

Similar Papers 제목 키워드 기반

Approximate Equivariance in Reinforcement Learning

2024-11-06 · Jung Yeon Park, Sujay Bhatt, Sihan Zeng, Lawson L. S. Wong 외

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is p…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1

The Algebra of Units: From Buckingham's Pi-grec Theorem to Latent-Variable Learning

2026-06-15 · Mauro Valorani arxiv

Engineers often measure many quantities-speed, pressure, temperature, length-expressed in different physical units. The Buckingham Pi-grec theorem states that these variables can always be combined into a smaller set of …

The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry

2022-11-16 · Dian Wang, Jung Yeon Park, Neel Sortur, Lawson L. S. Wong 외

Extensive work has demonstrated that equivariant neural networks can significantly improve sample efficiency and generalization by enforcing an inductive bias in the network architecture. These applications typically ass…

Inductive Bias

Exact Symmetry as Algebra: A Machine-Verified Tensor Calculus that Enforces Physical Selection Rules

2026-05-19 · Paulina Hoyos, Shashanka Ubaru, Dongsung Huh, Vasileios Kalantzis 외 arxiv

Symmetry is central to the physical sciences, yet machine learning usually captures it only approximately, leaving a residual per-step equivariance error $\varepsilon$ that compounds with depth $M$ as $M\varepsilon$, whe…

Measuring Uncertainty in Transformer Circuits with Effective Information Consistency

2025-09-08 · Anatoly A. Krasnovsky arxiv

Mechanistic interpretability has identified functional subgraphs within large language models (LLMs), known as Transformer Circuits (TCs), that appear to implement specific algorithms. Yet we lack a formal, single-pass w…