Uniform Convergence of Adaptive Graph-Based Regularization
نویسنده
چکیده
The regularization functional induced by the graph Laplacian of a random neighborhood graph based on the data is adaptive in two ways. First it adapts to an underlying manifold structure and second to the density of the data-generating probability measure. We identify in this paper the limit of the regularizer and show uniform convergence over the space of Hölder functions. As an intermediate step we derive upper bounds on the covering numbers of Hölder functions on compact Riemannian manifolds, which are of independent interest for the theoretical analysis of manifold-based learning methods.
منابع مشابه
Linear Manifold Regularization with Adaptive Graph for Semi-supervised Dimensionality Reduction
Many previous graph-based methods perform dimensionality reduction on a pre-defined graph. However, due to the noise and redundant information in the original data, the pre-defined graph has no clear structure and may not be appropriate for the subsequent task. To overcome the drawbacks, in this paper, we propose a novel approach called linear manifold regularization with adaptive graph (LMRAG)...
متن کاملSpeech Enhancement by Modified Convex Combination of Fractional Adaptive Filtering
This paper presents new adaptive filtering techniques used in speech enhancement system. Adaptive filtering schemes are subjected to different trade-offs regarding their steady-state misadjustment, speed of convergence, and tracking performance. Fractional Least-Mean-Square (FLMS) is a new adaptive algorithm which has better performance than the conventional LMS algorithm. Normalization of LMS ...
متن کاملMRF Regularization Models For Adaptive Binarization Of Non-Uniform Images
In this paper, we present two connected MRF models, the edge-preserving smoothing model followed by the modified standard regularization, for the adaptive binarization of the non-uniform images in the presence of noise. In particular, we have developed the computational model for the modified standard regularization method to be used to calculate the adaptive threshold surface for noisy images....
متن کاملA new critically sampled non-uniform subband adaptive structure
In this paper, a non-uniform subband adaptive structure with critical sampling of the subband signals is derived. With the assumption of non-overlapping between non-adjacent analysis filters, the resulting structure yields exact modeling of an arbitrary FIR system. An LMS-type adaptation algorithm, which minimizes the sum of the subband squared-errors, is obtained for updating the coefficients ...
متن کاملAn inexact alternating direction method with SQP regularization for the structured variational inequalities
In this paper, we propose an inexact alternating direction method with square quadratic proximal (SQP) regularization for the structured variational inequalities. The predictor is obtained via solving SQP system approximately under significantly relaxed accuracy criterion and the new iterate is computed directly by an explicit formula derived from the original SQP method. Under appropriat...
متن کامل