arXiv subjects

Joseph Keshet

Publications and source records attributed to Joseph Keshet.

58 records · Page 4Linked to original sources

arXiv2016

Sequence Segmentation Using Joint RNN and Structured Prediction Models

We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks. We propose a neural architecture that is composed of two modules trained jointly: a recurrent neural network (RNN) module and a structured prediction model. The RNN outputs are considered as feature functions to the structured model. The overall model is trained with a structured loss function which can be designed to the given segmentation task. We demonstrate the effectiveness of our method by applying it to two simple tasks commonly used in phonetic studies: word segmentation and voice onset time segmentation. Results sug- gest the proposed model is superior to previous methods, ob- taining state-of-the-art results on the tested datasets.

cs.CL↗

arXiv2016

Context-Based Prediction of App Usage

There are around a hundred installed apps on an average smartphone. The high number of apps and the limited number of app icons that can be displayed on the device's screen requires a new paradigm to address their visibility to the user. In this paper we propose a new online algorithm for dynamically predicting a set of apps that the user is likely to use. The algorithm runs on the user's device and constantly learns the user's habits at a given time, location, and device state. It is designed to actively help the user to navigate to the desired app as well as to provide a personalized feeling, and hence is aimed at maximizing the AUC. We show both theoretically and empirically that the algorithm maximizes the AUC, and yields good results on a set of 1,000 devices.

cs.LG↗

arXiv2015

Risk Minimization in Structured Prediction using Orbit Loss

We introduce a new surrogate loss function called orbit loss in the structured prediction framework, which has good theoretical and practical advantages. While the orbit loss is not convex, it has a simple analytical gradient and a simple perceptron-like learning rule. We analyze the new loss theoretically and state a PAC-Bayesian generalization bound. We also prove that the new loss is consistent in the strong sense; namely, the risk achieved by the set of the trained parameters approaches the infimum risk achievable by any linear decoder over the given features. Methods that are aimed at risk minimization, such as the structured ramp loss, the structured probit loss and the direct loss minimization require at least two inference operations per training iteration. In this sense, the orbit loss is more efficient as it requires only one inference operation per training iteration, while yields similar performance. We conclude the paper with an empirical comparison of the proposed loss function to the structured hinge loss, the structured ramp loss, the structured probit loss and the direct loss minimization method on several benchmark datasets and tasks.

cs.LG↗

arXiv2011

Explicit Approximations of the Gaussian Kernel

We investigate training and using Gaussian kernel SVMs by approximating the kernel with an explicit finite- dimensional polynomial feature representation based on the Taylor expansion of the exponential. Although not as efficient as the recently-proposed random Fourier features [Rahimi and Recht, 2007] in terms of the number of features, we show how this polynomial representation can provide a better approximation in terms of the computational cost involved. This makes our "Taylor features" especially attractive for use on very large data sets, in conjunction with online or stochastic training.

cs.AI↗