Adam
Adam: A Method for Stochastic Optimization. We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
Keywords for this software
References in zbMATH (referenced in 137 articles )
Showing results 1 to 20 of 137.
Sorted by year (- Banert, Sebastian; Ringh, Axel; Adler, Jonas; Karlsson, Johan; Öktem, Ozan: Data-driven nonsmooth optimization (2020)
- Boehmke, Brad; Greenwell, Brandon M.: Hands-on machine learning with R (2020)
- Edward Ayers, Francisco Eiras, Majd Hawasly, Iain Whiteside: PaRoT: A Practical Framework for Robust Deep NeuralNetwork Training (2020) arXiv
- Hayase, Tomohiro: Cauchy noise loss for stochastic optimization of random matrix models via free deterministic equivalents (2020)
- Kim, Junhyuk; Lee, Changhoon: Prediction of turbulent heat transfer using convolutional neural networks (2020)
- Murata, Takaaki; Fukami, Kai; Fukagata, Koji: Nonlinear mode decomposition with convolutional neural networks for fluid dynamics (2020)
- Nguyen-Thanh, Vien Minh; Zhuang, Xiaoying; Rabczuk, Timon: A deep energy method for finite deformation hyperelasticity (2020)
- Spaen, Quico; Thraves Caro, Christopher; Velednitsky, Mark: The dimension of valid distance drawings of signed graphs (2020)
- Todescato, Marco; Bof, Nicoletta; Cavraro, Guido; Carli, Ruggero; Schenato, Luca: Partition-based multi-agent optimization in the presence of lossy and asynchronous communication (2020)
- Xie, Fangzhou: Wasserstein index generation model: automatic generation of time-series index with application to economic policy uncertainty (2020)
- Yang, Liu; Zhang, Dongkun; Karniadakis, George Em: Physics-informed generative adversarial networks for stochastic differential equations (2020)
- Ahmadi, Ahmadreza; Tani, Jun: A novel predictive-coding-inspired variational RNN model for online prediction and recognition (2019)
- Beck, Christian; E., Weinan; Jentzen, Arnulf: Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations (2019)
- Bubba, Tatiana A.; Kutyniok, Gitta; Lassas, Matti; März, Maximilian; Samek, Wojciech; Siltanen, Samuli; Srinivasan, Vignesh: Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography (2019)
- Buehler, H.; Gonon, L.; Teichmann, J.; Wood, B.: Deep hedging (2019)
- Chan, Shing; Elsheikh, Ahmed H.: Parametric generation of conditional geological realizations using generative neural networks (2019)
- Chan-Wai-Nam, Quentin; Mikael, Joseph; Warin, Xavier: Machine learning for semi linear PDEs (2019)
- Chen, Guorong; Li, Tiange; Chen, Qijun; Ren, Shaofei; Wang, Chao; Li, Shaofan: Application of deep learning neural network to identify collision load conditions based on permanent plastic deformation of shell structures (2019)
- Dahl, Astrid; Bonilla, Edwin V.: Grouped Gaussian processes for solar power prediction (2019)
- Do, Kien; Tran, Truyen; Nguyen, Thin; Venkatesh, Svetha: Attentional multilabel learning over graphs: a message passing approach (2019)