We consider the framework of stochastic multi-armed bandit problems and study the
possibilities and limitations of strategies that perform an online exploration of the arms. The …

Abstract Harmonic analysis, and in particular the relation between function smoothness and
approximate sparsity of its wavelet coefficients, has played a key role in signal processing …

The k nearest neighbors (k NN) graph, perhaps the most popular graph in machine learning,
plays an essential role for graph-based learning methods. Despite its many elegant …

This paper studies the online node classification problem under a transductive learning
setting. Current methods either invert a graph kernel matrix with $\mathcal {O}(n^ 3) …

Twitter is one of the most popular micro-blogging services in the world, often studied in the
context of political opinion mining for its peculiar nature of online public discussion platform …

We investigate the problem of sequentially predicting the binary labels on the nodes of an
arbitrary weighted graph. We show that, under a suitable parametrization of the problem, the …

A relaxed randomized Kaczmarz algorithm is investigated in a least squares regression
setting by a learning theory approach. When the sampling values are accurate and the …

An additive spectral method for fuzzy clustering is proposed. The method operates on a
clustering model which is an extension of the spectral decomposition of a square matrix. The …

We characterize, up to constant factors, the number of mistakes necessary and sufficient for
sequentially predicting a given tree with binary labeled nodes. We provide an efficient …

Machine learning based on graph representation, or manifold learning, has attracted great
interest in recent years. As the discrete approximation of data manifold, the graph plays a …