Tailoring nearest neighbors algorithms to boosting is an important problem. Recent papers study an approach, UNN, which provably minimizes particular convex surrogates under weak assumptions. However, numerical issues make it necessary to experimentally tweak parts of the UNN algorithm, at the possible expense of the algorithm's convergence and performance. In this paper, we propose a lightweight Newton-Raphson alternative optimizing proper scoring rules from a very broad set, and establish formal convergence rates under the boosting framework that compete with those known for UNN. To the best of our knowledge, no such boosting-compliant convergence rates were previously known in the popular Gentle Adaboost's lineage. We provide experiments on a dozen domains, including Caltech and SUN computer vision databases, comparing our approach to major families including support vector machines, (Ada)boosting and stochastic gradient descent. They support three major conclusions: (i) GNNB significantly outperforms UNN, in terms of convergence rate and quality of the outputs, (ii) GNNB performs on par with or better than computationally intensive large margin approaches, (iii) on large domains that rule out those latter approaches for computational reasons, GNNB provides a simple and competitive contender to stochastic gradient descent. Experiments include a divide-and-conquer improvement of GNNB exploiting the link with proper scoring rules optimization.

This paper deals with stego-image steganalysis to detect hidden information in natural images. Hidden bits are embedded by using the Least Significant Bit (LSB) replacement mechanism. We address the problem of learning the weights which characterize the structure and the performance of the standard Weighted Stego-image (WS) detector. In this paper we propose a new Hybrid Weighted Stego-detection (HWS) algorithm. We assume that the WS weights are related to the image pixels variance through an unknown function which is decomposed onto a set of known basis functions. This yields a linear detector which consists of a linear combination of parametric features derived from the structure of the standard WS detector. The coefficients of the linear combination are learnt by minimizing calibrated losses using stochastic gradient descent or a more efficient stochastic Newton descent approach. Thus, the HWS algorithm benefits from two fundamental advantages: the posterior probability of detection is well estimated and the numerical complexity of the algorithm is linear with the number of samples and the dimension of the features. The benchmark on real images shows that HWS method outperforms standard WS baseline method.

Large scale image classification requires efficient scalable learning methods with linear complexity in the number of samples. Although Stochastic Gradient Descent is an efficient alternative to classical Support Vector Machine, this method suffers from slow convergence. In this paper, our contribution is two folds. First we consider the minimization of specific calibrated losses, for which we show how to reliably estimate posteriors, binary entropy and margin. Secondly we propose a Boosting Stochastic Newton Descent (BSN) method for minimization in the primal space of these specific calibrated loss. BSN approximates the inverse Hessian by the best low-rank approximation. The original-itty of BSN relies on the fact that it does perform a boosting scheme without computing iterative weight update over the examples. We validate BSN by benchmarking it against several variants of the state-of-the-art SGD algorithm on the large scale Image Net dataset. The results on Image Net large scale image classification display that BSN improves significantly accuracy of the SGD baseline while being faster by orders of magnitude.

High-content imaging is an emerging technology for the analysis and quantification of biological phenomena. Thus, classifying a huge number of cells or quantifying markers from large sets of images by experts is a very time-consuming and poorly reproducible task. In order to over-come such limitations, we propose a supervised method for automatic cell classification. Our approach consists of two steps: the first one is an indexing stage based on specific bio-inspired features relying on the distribution of contrast information on segmented cells. The second one is a super-vised learning stage that selects the prototypical samples best representing the cell categories. These prototypes are used in a leveraged k-NN framework to predict the class of unlabeled cells. In this paper we have tested our new learning algorithm on cellular images acquired for the analysis of pathologies. In order to evaluate the automatic classification performances, we tested our algorithm on the HEp-2 Cells dataset of (Foggia et al, CBMS 2010). Results are very promising, showing classification precision larger than 96% on average, thus suggesting our method as a valuable decision-support tool in such cellular imaging applications.