paper-with-me

홈 › Papers

On the Limitations of Fractal Dimension as a Measure of Generalization

2024-06-04 · Charlie B. Tan, Inés García-Redondo, Qiquan Wang, Michael M. Bronstein, Anthea Monod

Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. There is a recent and growing body of literature that proposes the framework of fractals to model optimization trajectories of neural networks, motivating generalization bounds and measures based on the fractal dimension of the trajectory. Notably, the persistent homology dimension has been proposed to correlate with the generalization gap. This paper performs an empirical evaluation of these persistent homology-based generalization measures, with an in-depth statistical analysis. Our study reveals confounding effects in the observed correlation between generalization and topological measures due to the variation of hyperparameters. We also observe that fractal dimension fails to predict generalization of models trained from poor initializations. We lastly reveal the intriguing manifestation of model-wise double descent in these topological generalization measures. Our work forms a basis for a deeper investigation of the causal relationships between fractal geometry, topological data analysis, and neural network optimization.

📄 PDF Abstract BibTeX arXiv:2406.02234

Code (1)

charliebtan/fractal_dimensions 공식 구현

Tasks

Generalization BoundsLearning TheoryModel OptimizationTopological Data Analysis

Similar Papers 제목 키워드 기반

Fractal Dimension Generalization Measure

2020-12-22 · Valeri Alexiev

Developing a robust generalization measure for the performance of machine learning models is an important and challenging task. A lot of recent research in the area focuses on the model decision boundary when predicting …

BIG-bench Machine Learning

Fourier fractal dimension to predict the generalization of deep neural networks

2026-06-06 · Joao B. Florindo, Davi Wanderley Misturini arxiv

Predicting the generalization performance of deep neural networks without relying on hold-out validation data is a fundamental challenge in machine learning. While Stochastic Gradient Descent (SGD) drives the optimizatio…

What is the dimension of your binary data?

2019-02-04 · Nikolaj Tatti, Taneli Mielikainen, Aristides Gionis, Heikki Mannila

Many 0/1 datasets have a very large number of variables; on the other hand, they are sparse and the dependency structure of the variables is simpler than the number of variables would suggest. Defining the effective dime…

Clustering

Generalization Guarantees via Algorithm-dependent Rademacher Complexity

2023-07-04 · Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna 외

Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds tha…

Generalization Bounds

Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks

2021-11-25 · NeurIPS 2021 12 · Tolga Birdal, Aaron Lou, Leonidas Guibas, Umut Şimşekli

Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters. Recently, it has been shown that the trajectories of …

Learning TheoryTopological Data Analysis