Adam: A Method for Stochastic Optimization

By Diederik P. Kingma, Jimmy Ba. International Conference on Learning Representations, 2014

168,773 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research, Optimization & Training

View Paper: https://arxiv.org/abs/1412.6980

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Yoshua Bengio
  3. Jianfeng Gao
  4. Sergey Levine
  5. Percy Liang
  6. Quoc V. Le
  7. Luke S. Zettlemoyer
  8. Kyunghyun Cho

In Management Science and Operations Research

  1. Sergey Levine
  2. Pieter Abbeel
  3. R´emi Munos
  4. Shimon Whiteson
  5. Frank Hutter
  6. Ofir Nachum
  7. Lihong Li
  8. Chelsea Finn

In Optimization & Training

  1. Yoshua Bengio
  2. Peter Richtárik
  3. Simon Lacoste-Julien
  4. Quoc V. Le
  5. Martin Jaggi
  6. Sebastian U. Stich
  7. Jakub Konecný
  8. Frank Hutter

Citations in the corpus