November 30, 2022
We provide a simple proof of convergence covering both the Adam and Adagrad adaptive optimization algorithms when applied to smooth (possibly non-convex) objective functions with bounded gradients. We show that in expectation, the squared norm of the objective gradient averaged over the trajectory has an upper-bound which is explicit in the constants of the problem, parameters of the optimizer, the dimension d, and the total number of iterations N. This bound can be made arbitrarily small, and with the right hyper-parameters, Adam can be shown to converge with the same rate of convergence O(d ln(N)/sqrt{N}). When used with the default parameters, Adam doesn't converge, however, and just like constant step-size SGD, it moves away from the initialization point faster than Adagrad, which might explain its practical success. Finally, we obtain the tightest dependency on the heavy ball momentum decay rate β_1 among all previous convergence bounds for non-convex Adam and Adagrad, improving from O((1-β_1)^{-3}) to O((1-β_1)^{-1}).
Publisher
TMLR
Research Topics
May 01, 2023
Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm, Maria-Florina Balcan
May 01, 2023
November 23, 2022
Tal Hassner, Cuong N. Nguyen, Cuong V. Nguyen, Lam Si Tung Ho, Vu Dinh
November 23, 2022
November 08, 2022
Ari Morcos, Shashank Shekhar, Surya Ganguli, Ben Sorscher, Robert Geirhos
November 08, 2022
December 06, 2021
Takanori Maehara, Hoang NT
December 06, 2021
Who We Are
Our Actions
Newsletter