In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate O( 1 ε2 ) improving over the projection-free, Online Frank-Wolfe based stochastic gradient descent of Hazan and Kale [2012] with convergence rate O( 1 ε4 ).

With a weighting scheme proportional to t, a traditional stochastic gradient descent (SGD) algorithm achieves a high probability convergence rate of O(κ/T ) for strongly convex functions, instead of O(κ ln(T )/T ). We also prove that an accelerated SGD algorithm also achieves a rate of O(κ/T ).

This paper reports preliminary results of our effort to address the acoustic-to-articulatory inversion problem. We tested an approach that simulates speech production acquisition as a distal learning task, with acoustic signals of natural utterances in the form of MFCC as input, VocalTractLab — a 3D articulatory synthesizer controlled by target approximation models as the learner, and stochasti...

In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent cooccurrences while still accounting for negative co-occurrence. Evaluation on word simila...

We describe an analog VLSI implementation of a multi-dimensional gradient estimation and descent technique for minimizing an onchip scalar function fO. The implementation uses noise injection and multiplicative correlation to estimate derivatives, as in [Anderson, Kerns 92]. One intended application of this technique is setting circuit parameters on-chip automatically, rather than manually [Kir...

We present a novel method for frequentist statistical inference in M -estimation problems, based on stochastic gradient descent (SGD) with a fixed step size: we demonstrate that the average of such SGD sequences can be used for statistical inference, after proper scaling. An intuitive analysis using the OrnsteinUhlenbeck process suggests that such averages are asymptotically normal. From a prac...

Training Non-linear Structured Prediction Models with Stochastic Gradient Descent Thomas Gärtner [email protected] Shankar Vembu [email protected] Fraunhofer IAIS, Schloß Birlinghoven, 53754 Sankt Augustin, Germany

In a recent article we described a new type of deep neural network– a Perpetual Learning Machine (PLM) – which is capable of learning ‘on the fly’ like a brain by existing in a state of Perpetual Stochastic Gradient Descent (PSGD). Here, by simulating the process of practice, we demonstrate both selective memory and selective forgetting when we introduce statistical recall biases during PSGD. F...

We propose to solve the link prediction problem in graphs using a supervised matrix factorization approach. The model learns latent features from the topological structure of a (possibly directed) graph, and is shown to make better predictions than popular unsupervised scores. We show how these latent features may be combined with optional explicit features for nodes or edges, which yields bett...

We consider the problem of constructing an aggregated estimator from a finite class of base functions which approximately minimizes a convex risk functional under the l1 constraint. For this purpose, we propose a stochastic procedure, the mirror descent, which performs gradient descent in the dual space. The generated estimates are additionally averaged in a recursive fashion with specific weig...