Persistence-based topological optimization: a survey

• URL: http://arxiv.org/abs/2603.24613v1
• Date: Tue, 24 Mar 2026 09:14:46 GMT
• Title: Persistence-based topological optimization: a survey
• Abstract summary: Computational topology provides a tool, persistent homology, to extract quantitative descriptors from structured objects.<n>These descriptors can then be involved in optimization problems, typically as a way to incorporate topological priors or to regularize machine learning models.<n>Various techniques have been developed to enable optimization of persistence-based loss functions with gradient descent schemes.
• Score: 9.562812538351489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Computational topology provides a tool, persistent homology, to extract quantitative descriptors from structured objects (images, graphs, point clouds, etc). These descriptors can then be involved in optimization problems, typically as a way to incorporate topological priors or to regularize machine learning models. This is usually achieved by minimizing adequate, topologically-informed losses based on these descriptors, which, in turn, naturally raises theoretical and practical questions about the possibility of optimizing such loss functions using gradient-based algorithms. This has been an active research field in the topological data analysis community over the last decade, and various techniques have been developed to enable optimization of persistence-based loss functions with gradient descent schemes. This survey presents the current state of this field, covering its theoretical foundations, the algorithmic aspects, and showcasing practical uses in several applications. It includes a detailed introduction to persistence theory and, as such, aims at being accessible to mathematicians and data scientists newcomers to the field. It is accompanied by an open-source library which implements the different approaches covered in this survey, providing a convenient playground for researchers to get familiar with the field.

Related papers

• Generative Quantum Data Embeddings for Supervised Learning [0.21485350418225238]
  We propose an energy-based generative learning framework that synthesizes gate sequences to optimize embedding structures.<n> Empirically, the method improves classification performance across diverse settings.<n>The results establish a practically useful and theoretically motivated framework for searching effective quantum data embeddings.
  arXiv  Detail & Related papers  (2026-05-29T05:48:04Z)
• From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation [11.440362964307958]
  Generative models form the backbone of modern machine learning, underpinning state-of-the-art systems in text, vision, and multimodal applications.<n>These approaches depend on explicit reward signals, which are often unavailable in practice, leaving open the problem of how to align generative models when only high-quality datasets are accessible.<n>We address this challenge via a Bilevel Optimization framework, where the reward function is treated as the optimization variable of an outer-level problem, while a policy gradient objective defines the inner-level.
  arXiv  Detail & Related papers  (2025-10-08T23:45:37Z)
• Similarity-based fuzzy clustering scientific articles: potentials and challenges from mathematical and computational perspectives [0.0]
  Fuzzy clustering plays a vital role in analyzing publication data.<n>This problem can be formulated as a constrained optimization model, where the goal is to minimize the discrepancy between the similarity observed from data and the similarity derived from a predicted distribution.<n>We analyze potentials and challenges of the approach from both mathematical and computational perspectives.
  arXiv  Detail & Related papers  (2025-06-04T15:10:31Z)
• Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms [15.473123662393169]
  Deep neural networks (DNNs) show remarkable generalization properties.<n>The source of these capabilities remains elusive, defying the established statistical learning theory.<n>Recent studies have revealed that properties of training trajectories can be indicative of generalization.
  arXiv  Detail & Related papers  (2024-07-11T17:56:03Z)
• Deep Learning-Based Object Pose Estimation: A Comprehensive Survey [73.74933379151419]
  We discuss the recent advances in deep learning-based object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks.
  arXiv  Detail & Related papers  (2024-05-13T14:44:22Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Higher-order topological kernels via quantum computation [68.8204255655161]
  Topological data analysis (TDA) has emerged as a powerful tool for extracting meaningful insights from complex data. We propose a quantum approach to defining Betti kernels, which is based on constructing Betti curves with increasing order.
  arXiv  Detail & Related papers  (2023-07-14T14:48:52Z)
• Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors [58.340159346749964]
  We propose a new neural-symbolic method to support end-to-end learning using complex queries with provable reasoning capability. We develop a new dataset containing ten new types of queries with features that have never been considered. Our method outperforms previous methods significantly in the new dataset and also surpasses previous methods in the existing dataset at the same time.
  arXiv  Detail & Related papers  (2023-04-14T11:35:35Z)
• A survey and taxonomy of loss functions in machine learning [51.35995529962554]
  We present a comprehensive overview of the most widely used loss functions across key applications, including regression, classification, generative modeling, ranking, and energy-based modeling. We introduce 43 distinct loss functions, structured within an intuitive taxonomy that clarifies their theoretical foundations, properties, and optimal application contexts.
  arXiv  Detail & Related papers  (2023-01-13T14:38:24Z)
• Topologically Regularized Data Embeddings [22.222311627054875]
  We introduce a new set of topological losses, and propose their usage as a way for topologically regularizing data embeddings to naturally represent a prespecified model. We include experiments on synthetic and real data that highlight the usefulness and versatility of this approach.
  arXiv  Detail & Related papers  (2021-10-18T11:25:47Z)
• Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms [71.62575565990502]
  We prove that the generalization error of an optimization algorithm can be bounded on the complexity' of the fractal structure that underlies its generalization measure. We further specialize our results to specific problems (e.g., linear/logistic regression, one hidden/layered neural networks) and algorithms.
  arXiv  Detail & Related papers  (2021-06-09T08:05:36Z)

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.