← Search

Chandrashekar Lakshminarayanan

2 accepted papers

2020

Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning

NeurIPS 2020poster

Rectified linear unit (ReLU) activations can also be thought of as 'gates', which, either pass or stop their pre-activation input when they are 'on' (when the pre-activation input is positive) or 'off' (when the pre-activation input is negative) respectively. A deep neural network (DNN) with ReLU ac…

Cited by 13SourcePDFScholar
2018

Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go?

AISTATS 2018poster

Temporal difference learning algorithms such as TD(0) and GTD in reinforcement learning (RL) and the stochastic gradient descent (SGD) for linear prediction are linear stochastic approximation (LSA) algorithms. These algorithms make only $O(d)$ ($d$ is parameter dimension) computations per iteration…

Cited by 0SourcePDFScholar