Learn More
The purpose of this paper is to describe one-shot-learning gesture recognition systems developed on the ChaLearn Gesture Dataset (ChaLearn). We use RGB and depth images and combine appearance (Histograms of Oriented Gradients) and motion descriptors (Histogram of Optical Flow) for parallel temporal segmentation and recognition. The Quadratic-Chi distance(More)
We present and analyze several strategies for improving the performance of stochastic variance-reduced gradient (SVRG) methods. We first show that the convergence rate of these methods can be preserved under a decreasing sequence of errors in the control variate, and use this to derive variants of SVRG that use growing-batch strategies to reduce the number(More)
General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every(More)
We propose a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent applied to the problem of minimizing a strongly convex composite function represented as the sum of an average of a large number of smooth convex functions, and simple nonsmooth convex function. Our method first performs a(More)
We propose mS2GD: a method incorporating a mini-batching scheme for improving the theoretical complexity and practical performance of semi-stochastic gradient descent (S2GD). We consider the problem of minimizing a strongly convex function represented as the sum of an average of a large number of smooth convex functions, and a simple nonsmooth convex(More)
Messenger RNA sequences often have to preserve functional secondary structure elements in addition to coding for proteins. We present a statistical analysis of retroviral mRNA which supports the hypothesis that the natural genetic code is adapted to such complementary coding. These sequences are still able to explore efficiently the space of possible(More)
We introduce a new and increasingly relevant setting for distributed optimization in machine learning , where the data defining the optimization are distributed (unevenly) over an extremely large number of nodes, but the goal remains to train a high-quality centralized model. We refer to this setting as Federated Optimization. In this setting, communication(More)