2000 character limit reached
LALR: Theoretical and Experimental validation of Lipschitz Adaptive Learning Rate in Regression and Neural Networks (2006.13307v1)
Published 19 May 2020 in cs.LG and stat.ML
Abstract: We propose a theoretical framework for an adaptive learning rate policy for the Mean Absolute Error loss function and Quantile loss function and evaluate its effectiveness for regression tasks. The framework is based on the theory of Lipschitz continuity, specifically utilizing the relationship between learning rate and Lipschitz constant of the loss function. Based on experimentation, we have found that the adaptive learning rate policy enables up to 20x faster convergence compared to a constant learning rate policy.