Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization
Dubois-Taine, Benjamin, Bach, Francis, Berthet, Quentin, Taylor, Adrien
–arXiv.org Artificial Intelligence
We consider the problem of minimizing the sum of two convex functions. One of those functions has Lipschitz-continuous gradients, and can be accessed via stochastic oracles, whereas the other is "simple". We provide a Bregman-type algorithm with accelerated convergence in function values to a ball containing the minimum. The radius of this ball depends on problem-dependent constants, including the variance of the stochastic oracle. We further show that this algorithmic setup naturally leads to a variant of Frank-Wolfe achieving acceleration under parallelization. More precisely, when minimizing a smooth convex function on a bounded domain, we show that one can achieve an $\epsilon$ primal-dual gap (in expectation) in $\tilde{O}(1/ \sqrt{\epsilon})$ iterations, by only accessing gradients of the original function and a linear maximization oracle with $O(1/\sqrt{\epsilon})$ computing units in parallel. We illustrate this fast convergence on synthetic numerical experiments.
arXiv.org Artificial Intelligence
Oct-12-2022
- Country:
- North America > United States (0.14)
- Asia > Russia (0.04)
- Europe
- Russia (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- France > Île-de-France
- Genre:
- Research Report (1.00)
- Industry:
- Government (0.67)
- Technology: