paper-with-me

홈 › Papers

Demystifying Spectral Bias on Real-World Data

2024-06-04 · Itay Lavie, Zohar Ringel

Kernel ridge regression (KRR) and Gaussian processes (GPs) are fundamental tools in statistics and machine learning, with recent applications to highly over-parameterized deep neural networks. The ability of these tools to learn a target function is directly related to the eigenvalues of their kernel sampled on the input data distribution. Targets that have support on higher eigenvalues are more learnable. However, solving such eigenvalue problems on real-world data remains a challenge. Here, we consider cross-dataset learnability and show that one may use eigenvalues and eigenfunctions associated with highly idealized data measures to reveal spectral bias on complex datasets and bound learnability on real-world data. This allows us to leverage various symmetries that realistic kernels manifest to unravel their spectral bias.

📄 PDF Abstract BibTeX arXiv:2406.02663

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes

Similar Papers 제목 키워드 기반

Demystifying Deep Neural Networks Through Interpretation: A Survey

2020-12-13 · Giang Dao, Minwoo Lee

Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn. The problem is that the single metric is an incomplete description o…

FairnessSurvey

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction

2021-06-28 · NeurIPS 2021 12 · Dominik Stöger, Mahdi Soltanolkotabi

Recently there has been significant theoretical progress on understanding the convergence and generalization of gradient-based methods on nonconvex losses with overparameterized models. Nevertheless, many aspects of opti…

Demystifying the Hypercomplex: Inductive Biases in Hypercomplex Deep Learning

2024-05-11 · Danilo Comminiello, Eleonora Grassucci, Danilo P. Mandic, Aurelio Uncini

Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their superior results when dealing with multidimen…

Deep LearningInductive Bias

How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective

2024-04-18 · Siyi Lin, Chongming Gao, Jiawei Chen, Sheng Zhou 외

Recommendation Systems (RS) are often plagued by popularity bias. When training a recommendation model on a typically long-tailed dataset, the model tends to not only inherit this bias but often exacerbate it, resulting …

FairnessRecommendation Systems

Demystifying KAN for Vision Tasks: The RepKAN Approach

2026-03-06 · Minjong Cheon arxiv

Remote sensing image classification is essential for Earth observation, yet standard CNNs and Transformers often function as uninterpretable black-boxes. We propose RepKAN, a novel architecture that integrates the struct…

Remote Sensing Image Classification