Timezone: »

 
Spotlight
Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
Trang Tran · Katya Scheinberg · Lam Nguyen

Thu Jul 21 11:00 AM -- 11:05 AM (PDT) @ Room 318 - 320
in Optimization/Reinforcement Learning »
In this paper, we propose Nesterov Accelerated Shuffling Gradient (NASG), a new algorithm for the convex finite-sum minimization problems. Our method integrates the traditional Nesterov's acceleration momentum with different shuffling sampling schemes. We show that our algorithm has an improved rate of $\Ocal(1/T)$ using unified shuffling schemes, where $T$ is the number of epochs. This rate is better than that of any other shuffling gradient methods in convex regime. Our convergence analysis does not require an assumption on bounded domain or a bounded gradient condition. For randomized shuffling schemes, we improve the convergence bound further. When employing some initial condition, we show that our method converges faster near the small neighborhood of the solution. Numerical simulations demonstrate the efficiency of our algorithm.
Keywords: OPT: Convex · OPT: First-order

Author Information

Trang Tran (Cornell University)
Katya Scheinberg (Cornell University)
Lam Nguyen (IBM Research, Thomas J. Watson Research Center)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors