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 224 articles )
Showing results 1 to 20 of 224.
Sorted by year (- Abbasi, Babak; Babaei, Toktam; Hosseinifard, Zahra; Smith-Miles, Kate; Dehghani, Maryam: Predicting solutions of large-scale optimization problems via machine learning: a case study in blood supply chain management (2020)
- Aggarwal, Charu C.: Linear algebra and optimization for machine learning. A textbook (2020)
- Ali Shahin Shamsabadi, Adria Gascon, Hamed Haddadi, Andrea Cavallaro: PrivEdge: From Local to Distributed Private Training and Prediction (2020) arXiv
- Banert, Sebastian; Ringh, Axel; Adler, Jonas; Karlsson, Johan; Öktem, Ozan: Data-driven nonsmooth optimization (2020)
- Barbeiro, Sílvia; Lobo, Diogo: Learning stable nonlinear cross-diffusion models for image restoration (2020)
- Bertocchi, Carla; Chouzenoux, Emilie; Corbineau, Marie-Caroline; Pesquet, Jean-Christophe; Prato, Marco: Deep unfolding of a proximal interior point method for image restoration (2020)
- Boehmke, Brad; Greenwell, Brandon M.: Hands-on machine learning with R (2020)
- Bougie, Nicolas; Ichise, Ryutaro: Skill-based curiosity for intrinsically motivated reinforcement learning (2020)
- Chan, Shing; Elsheikh, Ahmed H.: Data-driven acceleration of multiscale methods for uncertainty quantification: application in transient multiphase flow in porous media (2020)
- Cheng, M.; Fang, F.; Pain, C. C.; Navon, I. M.: Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network (2020)
- Cheung, Siu Wun; Chung, Eric T.; Efendiev, Yalchin; Gildin, Eduardo; Wang, Yating; Zhang, Jingyan: Deep global model reduction learning in porous media flow simulation (2020)
- Chris Cummins, Zacharias V. Fisches, Tal Ben-Nun, Torsten Hoefler, Hugh Leather: ProGraML: Graph-based Deep Learning for Program Optimization and Analysis (2020) arXiv
- Cohen, William; Yang, Fan; Mazaitis, Kathryn Rivard: TensorLog: a probabilistic database implemented using deep-learning infrastructure (2020)
- Cui, Ying; He, Ziyu; Pang, Jong-Shi: Multicomposite nonconvex optimization for training deep neural networks (2020)
- Dal Santo, Niccolò; Deparis, Simone; Pegolotti, Luca: Data driven approximation of parametrized PDEs by reduced basis and neural networks (2020)
- Darbon, Jérôme; Langlois, Gabriel P.; Meng, Tingwei: Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures (2020)
- Discacciati, Niccolò; Hesthaven, Jan S.; Ray, Deep: Controlling oscillations in high-order discontinuous Galerkin schemes using artificial viscosity tuned by neural networks (2020)
- Edward Ayers, Francisco Eiras, Majd Hawasly, Iain Whiteside: PaRoT: A Practical Framework for Robust Deep NeuralNetwork Training (2020) arXiv
- Erway, Jennifer B.; Griffin, Joshua; Marcia, Roummel F.; Omheni, Riadh: Trust-region algorithms for training responses: machine learning methods using indefinite Hessian approximations (2020)
- Fangzhou Xie: Pruned Wasserstein Index Generation Model and wigpy Package (2020) arXiv