Not-So-Random Features
We propose a principled method for kernel learning, which relies on a Fourier-analytic characterization of translation-invariant or rotation-invariant kernels. Our method produces a sequence of feature maps, iteratively refining the SVM margin. We provide rigorous guarantees for optimality and generalization, interpreting our algorithm as online equilibrium-finding dynamics in a certain two-player min-max game. Evaluations on synthetic and real-world datasets demonstrate scalability and consistent improvements over related random features-based methods.
Code (1)
Tasks
TranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Orthogonal Random Features: Explicit Forms and Sharp Inequalities
Random features have been introduced to scale up kernel methods via randomization techniques. In particular, random Fourier features and orthogonal random features were used to approximate the popular Gaussian kernel. Ra…
On the Approximation Properties of Random ReLU Features
We study the approximation properties of random ReLU features through their reproducing kernel Hilbert space (RKHS). We first prove a universality theorem for the RKHS induced by random features whose feature maps are of…
Random Features for Sparse Signal Classification
Random features is an approach for kernel-based inference on large datasets. In this paper, we derive performance guarantees for random features on signals, like images, that enjoy sparse representations and show that t…
ClassificationGeneral ClassificationDeep Semi-Random Features for Nonlinear Function Approximation
We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For on…
Revisiting Random Binning Features: Fast Convergence and Strong Parallelizability
Kernel method has been developed as one of the standard approaches for nonlinear learning, which however, does not scale to large data set due to its quadratic complexity in the number of samples. A number of kernel appr…