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 615 articles )
Showing results 1 to 20 of 615.
Sorted by year (- Chen, Qipin; Hao, Wenrui; He, Juncai: A weight initialization based on the linear product structure for neural networks (2022)
- Chou, Ping; Chuang, Howard Hao-Chun; Chou, Yen-Chun; Liang, Ting-Peng: Predictive analytics for customer repurchase: interdisciplinary integration of buy till you die modeling and machine learning (2022)
- Jia, Yichen; Jeong, Jong-Hyeon: Deep learning for quantile regression under right censoring: deepquantreg (2022)
- Kovacs, Alexander; Exl, Lukas; Kornell, Alexander; Fischbacher, Johann; Hovorka, Markus; Gusenbauer, Markus; Breth, Leoni; Oezelt, Harald; Yano, Masao; Sakuma, Noritsugu; Kinoshita, Akihito; Shoji, Tetsuya; Kato, Akira; Schrefl, Thomas: Conditional physics informed neural networks (2022)
- Mo, Yifan; Ling, Liming; Zeng, Delu: Data-driven vector soliton solutions of coupled nonlinear Schrödinger equation using a deep learning algorithm (2022)
- Oseledets, Ivan; Fanaskov, Vladimir: Direct optimization of BPX preconditioners (2022)
- Petchrompo, Sanyapong; Wannakrairot, Anupong; Parlikad, Ajith Kumar: Pruning Pareto optimal solutions for multi-objective portfolio asset management (2022)
- Schnaubelt, Matthias: Deep reinforcement learning for the optimal placement of cryptocurrency limit orders (2022)
- Stehr, Mark-Oliver; Kim, Minyoung; Talcott, Carolyn L.: A probabilistic approximate logic for neuro-symbolic learning and reasoning (2022)
- Adam Pocock: Tribuo: Machine Learning with Provenance in Java (2021) arXiv
- Adcock, Ben; Dexter, Nick: The gap between theory and practice in function approximation with deep neural networks (2021)
- Ainsworth, Mark; Dong, Justin: Galerkin neural networks: a framework for approximating variational equations with error control (2021)
- Alfke, Dominik; Stoll, Martin: Pseudoinverse graph convolutional networks. Fast filters tailored for large eigengaps of dense graphs and hypergraphs (2021)
- Amini Niaki, Sina; Haghighat, Ehsan; Campbell, Trevor; Poursartip, Anoush; Vaziri, Reza: Physics-informed neural network for modelling the thermochemical curing process of composite-tool systems during manufacture (2021)
- Anderson, Lara B.; Gerdes, Mathis; Gray, James; Krippendorf, Sven; Raghuram, Nikhil; Ruehle, Fabian: Moduli-dependent Calabi-Yau and SU(3)-structure metrics from machine learning (2021)
- Andersson, Kristoffer; Oosterlee, Cornelis W.: A deep learning approach for computations of exposure profiles for high-dimensional Bermudan options (2021)
- Andersson, Kristoffer; Oosterlee, Cornelis W.: Deep learning for CVA computations of large portfolios of financial derivatives (2021)
- Angeli, Andrea; Desmet, Wim; Naets, Frank: Deep learning for model order reduction of multibody systems to minimal coordinates (2021)
- Angeli, Andrea; Desmet, Wim; Naets, Frank: Deep learning of multibody minimal coordinates for state and input estimation with Kalman filtering (2021)
- Ao, Wenqi; Li, Wenbin; Qian, Jianliang: A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms (2021)