# Domain-independent Dominance of Adaptive Methods Source: [Domain-independent Dominance of Adaptive Methods]() Collection index: [llms.txt]() Data updated: 2025-12-14T17:27:23.893Z Authors: Pedro Savarese, David McAllester, Sudarshan Babu, Michael Maire Published: 2019-12-04T06:58:53.000Z ## Abstract From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. In light of this observation, we demonstrate that, against conventional wisdom, Adam can also outperform SGD on vision tasks, as long as the coupling between its learning rate and adaptability is taken into account. In practice, AvaGrad matches the best results, as measured by generalization accuracy, delivered by any existing optimizer (SGD or adaptive) across image classification (CIFAR, ImageNet) and character-level language modelling (Penn Treebank) tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-100 (test)](): Image Classification; CIFAR-100 (test); Accuracy: not recorded. - [Image Classification on CIFAR-10 (test)](): Image Classification; CIFAR-10 (test); Accuracy: not recorded. - [Image Classification on ImageNet (val)](): Image Classification; ImageNet (val); Top-1 Acc: not recorded. - [Language Modeling on Penn Treebank (test)](): Language Modeling; Penn Treebank (test); Perplexity: not recorded. ## Original sources and implementation [Original paper]() [PDF]()