Theoretical bounds on data requirements for the ray-based classification

Abstract

The problem of classifying high-dimensional shapes in real-world data grows in complexity as the dimension of the space increases. For the case of identifying convex shapes of different geometries, a new classification framework has recently been proposed in which the intersections of a set of one-dimensional representations, called rays, with the boundaries of the shape are used to identify the specific geometry. This ray-based classification (RBC) has been empirically verified using a synthetic dataset of two- and three-dimensional shapes (Zwolak et al. in Proceedings of Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020), Vancouver, Canada [December 11, 2020], arXiv:2010.00500, 2020) and, more recently, has also been validated experimentally (Zwolak et al., PRX Quantum 2:020335, 2021). Here, we establish a bound on the number of rays necessary for shape classification, defined by key angular metrics, for arbitrary convex shapes. For two dimensions, we derive a lower bound on the number of rays in terms of the shape's length, diameter, and exterior angles. For convex polytopes in ${\mathbb{R}}^N$, we generalize this result to a similar bound given as a function of the dihedral angle and the geometrical parameters of polygonal faces. This result enables a different approach for estimating high-dimensional shapes using substantially fewer data elements than volumetric or surface-based approaches.

arXiv comment10 pages, 5 figures

References in corpus (16)

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Soundness and completeness of quantum root-mean-square errors
• Machine Learning techniques for state recognition and auto-tuning in quantum dots
• Machine learning enables completely automatic tuning of a quantum device faster than human experts
• Automated tuning of double quantum dots into specific charge states using neural networks
• Experimental study of energy-minimizing point configurations on spheres
• Autonomous tuning and charge state detection of gate defined quantum dots
• QFlow lite dataset: A machine-learning approach to the charge states in quantum dot experiments
• Quantum device fine-tuning using unsupervised embedding learning
• Ray-based framework for state identification in quantum dot devices
• Autonomous estimation of high-dimensional Coulomb diamonds from sparse measurements
• Estimation of Convex Polytopes for Automatic Discovery of Charge State Transitions in Quantum Dot Arrays
• Ray-based classification framework for high-dimensional data
• Learning to Segment 3D Point Clouds in 2D Image Space
• 3D Object Classification via Spherical Projections
• PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations

Cited by in corpus (3)

• Colloquium: Advances in automation of quantum dot devices control
• Estimation of Convex Polytopes for Automatic Discovery of Charge State Transitions in Quantum Dot Arrays
• Learning Coulomb Diamonds in Large Quantum Dot Arrays