Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
The ADAM optimizer is exceedingly popular in the deep learning community. Often it works very well, sometimes it doesn't. Why? We interpret ADAM as a combination of two aspects: for each weight, the update direction is determined by the sign of stochastic gradients, whereas the update magnitude is determined by an estimate of their relative variance. We disentangle these two aspects and analyze them in isolation, gaining insight into the mechanisms underlying ADAM. This analysis also extends recent results on adverse effects of ADAM on generalization, isolating the sign aspect as the problematic one. Transferring the variance adaptation to SGD gives rise to a novel method, completing the practitioner's toolbox for problems where ADAM fails.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dissecting adaptive methods in GANs
Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to pinpoint the "marginal value of adaptive methods" in standard tasks, it remains …
High Probability Convergence of Adam Under Unbounded Gradients and Affine Variance Noise
In this paper, we study the convergence of the Adaptive Moment Estimation (Adam) algorithm under unconstrained non-convex smooth stochastic optimizations. Despite the widespread usage in machine learning areas, its theor…
Adam$^+$: A Stochastic Method with Adaptive Variance Reduction
Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problematic from a theoretical point of view sinc…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)image-classificationImage Classification+5Divergence Results and Convergence of a Variance Reduced Version of ADAM
Stochastic optimization algorithms using exponential moving averages of the past gradients, such as ADAM, RMSProp and AdaGrad, have been having great successes in many applications, especially in training deep neural net…
Stochastic OptimizationOn Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
The Adaptive Momentum Estimation (Adam) algorithm is highly effective in training various deep learning tasks. Despite this, there's limited theoretical understanding for Adam, especially when focusing on its vanilla for…
Stochastic Optimization