Search Results for author:
Found 6 papers, 0 papers with code
Score-Aware Policy-Gradient Methods and Performance Guarantees using Local Lyapunov Conditions: Applications to Product-Form Stochastic Networks and Queueing Systems
As a second contribution, we show that, under appropriate assumptions, the policy under a SAGE-based policy-gradient method has a large probability of converging to an optimal policy, provided that it starts sufficiently close to it, even with a nonconvex objective function and multiple maximizers.
Noise-Resilient Designs for Optical Neural Networks
Specifically, we investigate a probabilistic framework for the first design that establishes that the design is correct, i. e., for any feed-forward NN with Lipschitz continuous activation functions, an ONN can be constructed that produces output arbitrarily close to the original.
Detection and Evaluation of Clusters within Sequential Data
We address this issue and investigate the suitability of these clustering algorithms in exploratory data analysis of real-world sequential data.
Universal Approximation in Dropout Neural Networks
The first theorem applies to dropout networks in the random mode.
Asymptotic convergence rate of Dropout on shallow linear neural networks
We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can also be viewed as doing matrix factorization using a particular regularizer.
Almost Sure Convergence of Dropout Algorithms for Neural Networks
We investigate the convergence and convergence rate of stochastic training algorithms for Neural Networks (NNs) that have been inspired by Dropout (Hinton et al., 2012).
