NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization
Hajinezhad, Davood, Hong, Mingyi, Zhao, Tuo, Wang, Zhaoran
We study a stochastic and distributed algorithm for nonconvex problems whose objective consists of a sum of $N$ nonconvex $L_i/N$-smooth functions, plus a nonsmooth regularizer. The proposed NonconvEx primal-dual SpliTTing (NESTT) algorithm splits the problem into $N$ subproblems, and utilizes an augmented Lagrangian based primal-dual scheme to solve it in a distributed and stochastic manner. With a special non-uniform sampling, a version of NESTT achieves $\epsilon$-stationary solution using $\mathcal{O}((\sum_{i=1}^N\sqrt{L_i/N})^2/\epsilon)$ gradient evaluations, which can be up to $\mathcal{O}(N)$ times better than the (proximal) gradient descent methods. It also achieves Q-linear convergence rate for nonconvex $\ell_1$ penalized quadratic problems with polyhedral constraints. Further, we reveal a fundamental connection between primal-dual based methods and a few primal only methods such as IAG/SAG/SAGA.
Nov-7-2016
- Country:
- North America > United States
- Iowa (0.04)
- Massachusetts > Middlesex County
- Belmont (0.04)
- North America > United States
- Genre:
- Research Report (0.81)
- Technology: