paper-with-me

홈 › Papers

For interpolating kernel machines, minimizing the norm of the ERM solution minimizes stability

2020-06-28 · Akshay Rangamani, Lorenzo Rosasco, Tomaso Poggio

We study the average $\mbox{CV}_{loo}$ stability of kernel ridge-less regression and derive corresponding risk bounds. We show that the interpolating solution with minimum norm minimizes a bound on $\mbox{CV}_{loo}$ stability, which in turn is controlled by the condition number of the empirical kernel matrix. The latter can be characterized in the asymptotic regime where both the dimension and cardinality of the data go to infinity. Under the assumption of random kernel matrices, the corresponding test error should be expected to follow a double descent curve.

📄 PDF Abstract BibTeX arXiv:2006.15522

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

To Each Optimizer a Norm, To Each Norm its Generalization

2020-06-11 · Sharan Vaswani, Reza Babanezhad, Jose Gallego, Aaron Mishkin 외

We study the implicit regularization of optimization methods for linear models interpolating the training data in the under-parametrized and over-parametrized regimes. Since it is difficult to determine whether an optimi…

ClassificationGeneral Classification

Interpolating Classifiers Make Few Mistakes

2021-01-28 · Tengyuan Liang, Benjamin Recht

This paper provides elementary analyses of the regret and generalization of minimum-norm interpolating classifiers (MNIC). The MNIC is the function of smallest Reproducing Kernel Hilbert Space norm that perfectly interpo…

To understand deep learning we need to understand kernel learning

2018-02-05 · ICML 2018 7 · Mikhail Belkin, Siyuan Ma, Soumik Mandal

Generalization performance of classifiers in deep learning has recently become a subject of intense study. Deep models, typically over-parametrized, tend to fit the training data exactly. Despite this "overfitting", they…

Deep LearningGeneralization Bounds

Kernel Flows: from learning kernels from data into the abyss

2018-08-13 · Houman Owhadi, Gene Ryan Yoo

Learning can be seen as approximating an unknown function by interpolating the training data. Kriging offers a solution to this problem based on the prior specification of a kernel. We explore a numerical approximation a…

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality

2024-09-05 · Marko Medvedev, Gal Vardi, Nathan Srebro

We consider the overfitting behavior of minimum norm interpolating solutions of Gaussian kernel ridge regression (i.e. kernel ridgeless regression), when the bandwidth or input dimension varies with the sample size. For …

regression