Selecting Interpretable Circular Coordinates from Data

• URL: http://arxiv.org/abs/2607.08230v1
• Date: Thu, 09 Jul 2026 08:26:48 GMT
• Title: Selecting Interpretable Circular Coordinates from Data
• Abstract summary: We propose a method for selecting interpretable circle-valued coordinates from a user-supplied dictionary of scientifically meaningful candidates explaining the detected cohomology.<n>We prove that the introduced cochain inner product is a consistent estimator of the $L2$ inner product of fixed smooth 1-forms under non-uniform sampling.
• Score: 2.8802622551493773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Circular coordinates obtained from persistent cohomology reveal loop structure in data, but they usually remain abstract: A detected circle does not tell us which measured angle, phase, torsion, or decoder explains it. We propose a method for selecting interpretable circle-valued coordinates from a user-supplied dictionary of scientifically meaningful candidates explaining the detected cohomology. In the continuous setting, each candidate is represented by the cohomology class of its pulled-back angular form, and selecting a minimum-energy set of candidates spanning the relevant $H^1$ subspace becomes a minimum-weight basis problem in a vector matroid. We then introduce CIRCOL, a method for discrete point clouds sampled from the manifold. We prove that the introduced cochain inner product is a consistent estimator of the $L^2$ inner product of fixed smooth 1-forms under non-uniform sampling. The resulting projection matrix both helps selecting a basis of low-energy dictionary coordinates and diagnoses topologically trivial candidates or unexplained persistent classes. Finally, we verify the effectiveness of our method on synthetic examples, on molecular simulations, and neural recordings of head-direction cells.

Related papers

• Active Learning with Low-Rank Structure for Data Selection [85.43185363043362]
  We introduce a new data selection framework based on low-rank approximation and residual-based sampling.<n>We show that it is possible to select a weighted subset of $tildeOleft(k + frac1varepsilon2right)$ data points whose average loss approximates the average loss over the full dataset.
  arXiv  Detail & Related papers  (2026-06-14T22:29:59Z)
• Subsampling, aligning, and averaging to find circular coordinates in recurrent time series [3.8214695776749013]
  We introduce a new algorithm for finding robust circular coordinates on data that is expected to exhibit recurrence.<n>We validate our technique on both synthetic data sets and neuronal activity recordings.
  arXiv  Detail & Related papers  (2024-12-24T15:52:51Z)
• Resampling and averaging coordinates on data [1.660242118349614]
  We introduce algorithms for robustly computing intrinsic coordinates on point clouds. We identify a subset of representative embeddings by clustering the collection of candidate coordinates and using shape descriptors from topological data analysis. The final output is the embedding obtained as an average of the representative embeddings using generalized Procrustes analysis.
  arXiv  Detail & Related papers  (2024-08-02T16:37:33Z)
• Information-Theoretic Thresholds for Planted Dense Cycles [52.076657911275525]
  We study a random graph model for small-world networks which are ubiquitous in social and biological sciences. For both detection and recovery of the planted dense cycle, we characterize the information-theoretic thresholds in terms of $n$, $tau$, and an edge-wise signal-to-noise ratio $lambda$.
  arXiv  Detail & Related papers  (2024-02-01T03:39:01Z)
• Non-isotropic Persistent Homology: Leveraging the Metric Dependency of PH [5.70896453969985]
  We show that information on the point cloud is lost when restricting persistent homology to a single distance function. We numerically show that non-isotropic persistent homology can extract information on orientation, orientational variance, and scaling of randomly generated point clouds.
  arXiv  Detail & Related papers  (2023-10-25T08:03:17Z)
• A hybrid quantum algorithm to detect conical intersections [39.58317527488534]
  We show that for real molecular Hamiltonians, the Berry phase can be obtained by tracing a local optimum of a variational ansatz along the chosen path. We demonstrate numerically the application of our algorithm on small toy models of the formaldimine molecule.
  arXiv  Detail & Related papers  (2023-04-12T18:00:01Z)
• Toroidal Coordinates: Decorrelating Circular Coordinates With Lattice Reduction [1.9437538125261753]
  We describe a systematic procedure for constructing low energy torus-valued maps on data, starting from a set of linearly independent cohomology classes. Our main algorithm is based on the Lenstra--stra--Lov'asz algorithm from computational number theory.
  arXiv  Detail & Related papers  (2022-12-14T12:59:25Z)
• The Manifold Hypothesis for Gradient-Based Explanations [55.01671263121624]
  gradient-based explanation algorithms provide perceptually-aligned explanations. We show that the more a feature attribution is aligned with the tangent space of the data, the more perceptually-aligned it tends to be. We suggest that explanation algorithms should actively strive to align their explanations with the data manifold.
  arXiv  Detail & Related papers  (2022-06-15T08:49:24Z)
• GPCO: An Unsupervised Green Point Cloud Odometry Method [64.86292006892093]
  A lightweight point cloud odometry solution is proposed and named the green point cloud odometry (GPCO) method. GPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans. It is observed that GPCO outperforms benchmarking deep learning methods in accuracy while it has a significantly smaller model size and less training time.
  arXiv  Detail & Related papers  (2021-12-08T00:24:03Z)
• The decomposition of the higher-order homology embedding constructed from the $k$-Laplacian [5.076419064097734]
  The null space of the $k$-th order Laplacian $mathbfmathcal L_k$ encodes the non-trivial topology of a manifold or a network. We propose an algorithm to factorize the homology embedding into subspaces corresponding to a manifold's simplest topological components.
  arXiv  Detail & Related papers  (2021-07-23T00:40:01Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)
• Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds [145.79324955896845]
  We propose a permutable anisotropic convolutional operation (PAI-Conv) that calculates soft-permutation matrices for each point. Experiments on point clouds demonstrate that PAI-Conv produces competitive results in classification and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2020-05-27T02:42:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.