We consider the ability of deep neural networks to represent data that lies near a low-dimensional manifold in a high-dimensional space. We show that deep networks can efficiently extract the intrinsic, low-dimensional coordinates of such data. Specifically we show that the first two layers of a deep network can exactly embed points lying on a monotonic chain, a special type of piecewise linear...

Gradient descent learning algorithms have proven effective in solving mixed strategy games. The policy hill climbing (PHC) variants of WoLF (Win or Learn Fast) and PDWoLF (Policy Dynamics based WoLF) have both shown rapid convergence to equilibrium solutions by increasing the accuracy of their gradient parameters over standard Q-learning. Likewise, cooperative learning techniques using weighted...

In this work, we present a family of vector quantization schemes vqSGD (Vector-Quantized Stochastic Gradient Descent) that provide an asymptotic reduction in the communication cost with convergence guarantees first-order distributed optimization. process derive following fundamental information...

This contribution presents an overview of the theoretical and practical aspects of the broad family of learning algorithms based on Stochastic Gradient Descent, including Perceptrons, Adalines, K-Means, LVQ, Multi-Layer Networks, and Graph Transformer Networks.

The R-FoE model of Sec. 3 of the main paper was trained on a database of 5000 natural images (50 × 50 pixels) using persistent contrastive divergence [12] (also known as stochastic maximum likelihood). Learning was done with stochastic gradient descent using mini-batches of 100 images (and model samples) for a total of 10000 (exponentially smoothed) gradient steps with an annealed learning rate...

In the era of big data, optimizing large scale machine learning problems becomes a challenging task and draws significant attention. Asynchronous optimization algorithms come out as a promising solution. Recently, decoupled asynchronous proximal stochastic gradient descent (DAP-SGD) is proposed to minimize a composite function. It is claimed to be able to offload the computation bottleneck from...

In this article, we study the relationship between the two techniques known as ant colony optimization (ACO) and stochastic gradient descent. More precisely, we show that some empirical ACO algorithms approximate stochastic gradient descent in the space of pheromones, and we propose an implementation of stochastic gradient descent that belongs to the family of ACO algorithms. We then use this i...

The practical performance of online stochastic gradient descent algorithms is highly dependent on the chosen step size, which must be tediously hand-tuned in many applications. The same is true for more advanced variants of stochastic gradients, such as SAGA, SVRG, or AdaGrad. Here we propose to adapt the step size by performing a gradient descent on the step size itself, viewing the whole perf...

Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closely related Dual Coordinate Ascent (DCA) method has been implemented in various software packages, it has so far lacked good convergence analysis. This paper presents a new analysis of Stochastic Dua...

Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks’ information without affecting the current task’s learning. ...