Mutual Information Free Topological Generalization Bounds via Stability

• URL: http://arxiv.org/abs/2507.06775v1
• Date: Wed, 09 Jul 2025 12:03:25 GMT
• Title: Mutual Information Free Topological Generalization Bounds via Stability
• Authors: Mario Tuci, Lennart Bastian, Benjamin Dupuis, Nassir Navab, Tolga Birdal, Umut Şimşekli,
• Abstract summary: We introduce a novel learning theoretic framework that departs from the existing strategies.<n>We prove that the generalization error of trajectory-stable algorithms can be upper bounded in terms of TDA terms.
• Score: 46.63069403118614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Providing generalization guarantees for stochastic optimization algorithms is a major challenge in modern learning theory. Recently, several studies highlighted the impact of the geometry of training trajectories on the generalization error, both theoretically and empirically. Among these works, a series of topological generalization bounds have been proposed, relating the generalization error to notions of topological complexity that stem from topological data analysis (TDA). Despite their empirical success, these bounds rely on intricate information-theoretic (IT) terms that can be bounded in specific cases but remain intractable for practical algorithms (such as ADAM), potentially reducing the relevance of the derived bounds. In this paper, we seek to formulate comprehensive and interpretable topological generalization bounds free of intractable mutual information terms. To this end, we introduce a novel learning theoretic framework that departs from the existing strategies via proof techniques rooted in algorithmic stability. By extending an existing notion of \textit{hypothesis set stability}, to \textit{trajectory stability}, we prove that the generalization error of trajectory-stable algorithms can be upper bounded in terms of (i) TDA quantities describing the complexity of the trajectory of the optimizer in the parameter space, and (ii) the trajectory stability parameter of the algorithm. Through a series of experimental evaluations, we demonstrate that the TDA terms in the bound are of great importance, especially as the number of training samples grows. This ultimately forms an explanation of the empirical success of the topological generalization bounds.

Related papers

• Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel [55.82768375605861]
  We establish a generalization bound for gradient flow that aligns with the classical Rademacher complexity for kernel methods.<n>Unlike static kernels such as NTK, the LPK captures the entire training trajectory, adapting to both data and optimization dynamics.
  arXiv  Detail & Related papers  (2025-06-12T23:17:09Z)
• 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)
• A Unified Theory of Stochastic Proximal Point Methods without Smoothness [52.30944052987393]
  Proximal point methods have attracted considerable interest owing to their numerical stability and robustness against imperfect tuning. This paper presents a comprehensive analysis of a broad range of variations of the proximal point method (SPPM)
  arXiv  Detail & Related papers  (2024-05-24T21:09:19Z)
• Generalization Guarantees via Algorithm-dependent Rademacher Complexity [33.408679482592426]
  We propose a measure to control generalization error, which is the empirical Rademacher complexity of an algorithm- and data-dependent hypothesis class. We obtain novel bounds based on the finite fractal dimension, which (a) extend previous fractal-type bounds from continuous to finite hypothesis classes, and (b) avoid a mutual information term.
  arXiv  Detail & Related papers  (2023-07-04T18:37:38Z)
• A unified framework for information-theoretic generalization bounds [8.04975023021212]
  This paper presents a general methodology for deriving information-theoretic generalization bounds for learning algorithms. The main technical tool is a probabilistic decorrelation lemma based on a change of measure and a relaxation of Young's inequality in $L_psi_p$ Orlicz spaces.
  arXiv  Detail & Related papers  (2023-05-18T15:36:20Z)
• Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective [11.255943520955764]
  We propose a novel information theoretical measure: kernelized Renyi's entropy. We establish the generalization error bounds for gradient/Langevin descent (SGD/SGLD) learning algorithms under kernelized Renyi's entropy. We show that our information-theoretical bounds depend on the statistics of the gradients, and are rigorously tighter than the current state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2023-05-02T01:17:15Z)
• On Leave-One-Out Conditional Mutual Information For Generalization [122.2734338600665]
  We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI) Contrary to other CMI bounds, our loo-CMI bounds can be computed easily and can be interpreted in connection to other notions such as classical leave-one-out cross-validation. We empirically validate the quality of the bound by evaluating its predicted generalization gap in scenarios for deep learning.
  arXiv  Detail & Related papers  (2022-07-01T17:58:29Z)
• 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)
• Joint Network Topology Inference via Structured Fusion Regularization [70.30364652829164]
  Joint network topology inference represents a canonical problem of learning multiple graph Laplacian matrices from heterogeneous graph signals. We propose a general graph estimator based on a novel structured fusion regularization. We show that the proposed graph estimator enjoys both high computational efficiency and rigorous theoretical guarantee.
  arXiv  Detail & Related papers  (2021-03-05T04:42:32Z)

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.