REVIEW 2 cited by
EAdam Optimizer: How $\epsilon$ Impact Adam
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Many adaptive optimization methods have been proposed and used in deep learning, in which Adam is regarded as the default algorithm and widely used in many deep learning frameworks. Recently, many variants of Adam, such as Adabound, RAdam and Adabelief, have been proposed and show better performance than Adam. However, these variants mainly focus on changing the stepsize by making differences on the gradient or the square of it. Motivated by the fact that suitable damping is important for the success of powerful second-order optimizers, we discuss the impact of the constant $\epsilon$ for Adam in this paper. Surprisingly, we can obtain better performance than Adam simply changing the position of $\epsilon$. Based on this finding, we propose a new variant of Adam called EAdam, which doesn't need extra hyper-parameters or computational costs. We also discuss the relationships and differences between our method and Adam. Finally, we conduct extensive experiments on various popular tasks and models. Experimental results show that our method can bring significant improvement compared with Adam. Our code is available at https://github.com/yuanwei2019/EAdam-optimizer.
Forward citations
Cited by 2 Pith papers
-
On MUON optimization: From non-convergence to an error analysis with Polar Express and the Newton-Schulz polynomial from implementations
For a one-dimensional quadratic stochastic optimization problem, MUON with Newton-Schulz steps provably fails to converge to the minimizer for all sufficiently large mini-batch sizes when the data is skewed, while a n...
-
Unified convergence analysis for gradient descent optimization methods in the training of deep neural networks
Bounded trajectories of a broad class of GD optimizers (Adam, RMSprop, NAG, Adan, etc.) converge with polynomial rates to critical points of KL objectives with locally Lipschitz gradients, covering analytic-activation...
Discussion (0). Continue with ORCID to comment.