paper-with-me

홈 › Papers

Iteratively reweighted kernel machines efficiently learn sparse functions

2025-05-13 · Libin Zhu, Damek Davis, Dmitriy Drusvyatskiy, Maryam Fazel

The impressive practical performance of neural networks is often attributed to their ability to learn low-dimensional data representations and hierarchical structure directly from data. In this work, we argue that these two phenomena are not unique to neural networks, and can be elicited from classical kernel methods. Namely, we show that the derivative of the kernel predictor can detect the influential coordinates with low sample complexity. Moreover, by iteratively using the derivatives to reweight the data and retrain kernel machines, one is able to efficiently learn hierarchical polynomials with finite leap complexity. Numerical experiments illustrate the developed theory.

📄 PDF Abstract BibTeX arXiv:2505.08277

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Iteratively-Reweighted Least-Squares Fitting of Support Vector Machines: A Majorization--Minimization Algorithm Approach

2017-05-12 · Hien D. Nguyen, Geoffrey J. McLachlan

Support vector machines (SVMs) are an important tool in modern data analysis. Traditionally, support vector machines have been fitted via quadratic programming, either using purpose-built or off-the-shelf algorithms. We …

Kernel based regression with robust loss function via iteratively reweighted least squares

2019-03-27 · Hongwei Dong, Liming Yang

Least squares kernel based methods have been widely used in regression problems due to the simple implementation and good generalization performance. Among them, least squares support vector regression (LS-SVR) and extre…

regression

Natural Reweighted Wake-Sleep

2020-08-15 · NeurIPS Workshop DL-IG 2020 12 · Csongor Várady, Riccardo Volpi, Luigi Malagò, Nihat Ay

Helmholtz Machines (HMs) are a class of generative models composed of two Sigmoid Belief Networks (SBNs), acting respectively as an encoder and a decoder. These models are commonly trained using a two-step optimization a…

Decoder

Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise

2018-11-06 · Arun Venkitaraman, Pascal Frossard, Saikat Chatterjee

In presence of sparse noise we propose kernel regression for predicting output vectors which are smooth over a given graph. Sparse noise models the training outputs being corrupted either with missing samples or large pe…

regression

Blind Image Deblurring via Reweighted Graph Total Variation

2017-12-24 · Yuanchao Bai, Gene Cheung, Xian-Ming Liu, Wen Gao

Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimat…

Blind Image DeblurringDeblurringImage Deblurring