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 187 articles )
Showing results 21 to 40 of 187.
Sorted by year (- Jin, Bangti; Zhou, Zehui; Zou, Jun: On the convergence of stochastic gradient descent for nonlinear ill-posed problems (2020)
- Jin, Lianghai; Song, Enmin; Zhang, Wenhua: Denoising color images based on local orientation estimation and CNN classifier (2020)
- Kim, Junhyuk; Lee, Changhoon: Prediction of turbulent heat transfer using convolutional neural networks (2020)
- Kissas, Georgios; Yang, Yibo; Hwuang, Eileen; Witschey, Walter R.; Detre, John A.; Perdikaris, Paris: Machine learning in cardiovascular flows modeling: predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks (2020)
- Koeppe, Arnd; Bamer, Franz; Markert, Bernd: An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new time-distributed residual U-net architecture (2020)
- Leong, Alex S.; Ramaswamy, Arunselvan; Quevedo, Daniel E.; Karl, Holger; Shi, Ling: Deep reinforcement learning for wireless sensor scheduling in cyber-physical systems (2020)
- Meister, Felix; Passerini, Tiziano; Mihalef, Viorel; Tuysuzoglu, Ahmet; Maier, Andreas; Mansi, Tommaso: Deep learning acceleration of total Lagrangian explicit dynamics for soft tissue mechanics (2020)
- Muammar El Khatib, Wibe A de Jong: ML4Chem: A Machine Learning Package for Chemistry and Materials Science (2020) arXiv
- 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)
- Palagi, Laura; Seccia, Ruggiero: Block layer decomposition schemes for training deep neural networks (2020)
- Pan, Shaowu; Duraisamy, Karthik: Physics-informed probabilistic learning of linear embeddings of nonlinear dynamics with guaranteed stability (2020)
- Paquette, Courtney; Scheinberg, Katya: A stochastic line search method with expected complexity analysis (2020)
- Parish, Eric J.; Carlberg, Kevin T.: Time-series machine-learning error models for approximate solutions to parameterized dynamical systems (2020)
- Rousseau, François; Drumetz, Lucas; Fablet, Ronan: Residual networks as flows of diffeomorphisms (2020)
- Ruehle, Fabian: Data science applications to string theory (2020)
- Spaen, Quico; Thraves Caro, Christopher; Velednitsky, Mark: The dimension of valid distance drawings of signed graphs (2020)
- Sun, Luning; Gao, Han; Pan, Shaowu; Wang, Jian-Xun: Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data (2020)
- Takbiri-Borujeni, Ali; Kazemi, Hadi; Nasrabadi, Nasser: A data-driven surrogate to image-based flow simulations in porous media (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)