paper-with-me

홈 › Papers

Dimension Free Generalization Bounds for Non Linear Metric Learning

2021-02-07 · Mark Kozdoba, Shie Mannor

In this work we study generalization guarantees for the metric learning problem, where the metric is induced by a neural network type embedding of the data. Specifically, we provide uniform generalization bounds for two regimes -- the sparse regime, and a non-sparse regime which we term \emph{bounded amplification}. The sparse regime bounds correspond to situations where $\ell_1$-type norms of the parameters are small. Similarly to the situation in classification, solutions satisfying such bounds can be obtained by an appropriate regularization of the problem. On the other hand, unregularized SGD optimization of a metric learning loss typically does not produce sparse solutions. We show that despite this lack of sparsity, by relying on a different, new property of the solutions, it is still possible to provide dimension free generalization guarantees. Consequently, these bounds can explain generalization in non sparse real experimental situations. We illustrate the studied phenomena on the MNIST and 20newsgroups datasets.

📄 PDF Abstract BibTeX arXiv:2102.03802

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsMetric Learning

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Sharp concentration of uniform generalization errors in binary linear classification

2025-05-22 · Shogo Nakakita

We examine the concentration of uniform generalization errors around their expectation in binary linear classification problems via an isoperimetric argument. In particular, we establish Poincar\'{e} and log-Sobolev ineq…

Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces

2024-02-08 · Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer

Machine learning models with inputs in a Euclidean space $\mathbb{R}^d$, when implemented on digital computers, generalize, and their generalization gap converges to $0$ at a rate of $c/N^{1/2}$ concerning the sample siz…

Generalization Bounds

Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid

2025-09-25 · Alexis Ayme, Bruno Loureiro arxiv

In this work, we address the following question: What minimal structural assumptions are needed to prevent the degradation of statistical learning bounds with increasing dimensionality? We investigate this question in th…

Tropical Support Vector Machines: Evaluations and Extension to Function Spaces

2021-01-27 · Ruriko Yoshida, Misaki Takamori, Hideyuki Matsumoto, Keiji Miura

Support Vector Machines (SVMs) are one of the most popular supervised learning models to classify using a hyperplane in an Euclidean space. Similar to SVMs, tropical SVMs classify data points using a tropical hyperplane …

On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions

2025-11-16 · Yulong Lu, Tong Mao, Jinchao Xu, Yahong Yang arxiv

Deep neural networks have been widely used as universal approximators for functions with inherent physical structures, including permutation symmetry. In this paper, we construct symmetric deep neural networks to approxi…