paper-with-me

홈 › Papers

Generalization bounds for regression and classification on adaptive covering input domains

2024-07-29 · Wen-Liang Hwang

Our main focus is on the generalization bound, which serves as an upper limit for the generalization error. Our analysis delves into regression and classification tasks separately to ensure a thorough examination. We assume the target function is real-valued and Lipschitz continuous for regression tasks. We use the 2-norm and a root-mean-square-error (RMSE) variant to measure the disparities between predictions and actual values. In the case of classification tasks, we treat the target function as a one-hot classifier, representing a piece-wise constant function, and employ 0/1 loss for error measurement. Our analysis underscores the differing sample complexity required to achieve a concentration inequality of generalization bounds, highlighting the variation in learning efficiency for regression and classification tasks. Furthermore, we demonstrate that the generalization bounds for regression and classification functions are inversely proportional to a polynomial of the number of parameters in a network, with the degree depending on the hypothesis class and the network architecture. These findings emphasize the advantages of over-parameterized networks and elucidate the conditions for benign overfitting in such systems.

📄 PDF Abstract BibTeX arXiv:2407.19715

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneralization Boundsregression

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Multiple Source Domain Adaptation

2018-12-01 · NeurIPS 2018 12 · Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura 외

While domain adaptation has been actively researched, most algorithms focus on the single-source-single-target adaptation setting. In this paper we propose new generalization bounds and algorithms under both classificati…

ClassificationDomain AdaptationGeneral ClassificationGeneralization Bounds+3

Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regression

2024-10-08 · Weigutian Ou, Helmut Bölcskei

Covering numbers of families of (deep) ReLU networks have been used to characterize their approximation-theoretic performance, upper-bound the prediction error they incur in nonparametric regression, and quantify their c…

Quantizationregression

Error Bounds for Piecewise Smooth and Switching Regression

2017-07-25 · Fabien Lauer

The paper deals with regression problems, in which the nonsmooth target is assumed to switch between different operating modes. Specifically, piecewise smooth (PWS) regression considers target functions switching determi…

regression

Non-parametric Binary regression in metric spaces with KL loss

2020-10-19 · Ariel Avital, Klim Efremenko, Aryeh Kontorovich, David Toplin 외

We propose a non-parametric variant of binary regression, where the hypothesis is regularized to be a Lipschitz function taking a metric space to [0,1] and the loss is logarithmic. This setting presents novel computation…

Generalization Boundsregression

Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods

2018-07-01 · ICML 2018 7 · Junhong Lin, Volkan Cevher

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We investigate distributed stochastic gradient methods (SGM), w…

regression