Timezone: »

 
Poster
GIANT: Globally Improved Approximate Newton Method for Distributed Optimization
Shusen Wang · Fred Roosta · Peng Xu · Michael Mahoney

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 210 #44
in Thu Poster Session B »

For distributed computing environment, we consider the empirical risk minimization problem and propose a distributed and communication-efficient Newton-type optimization method. At every iteration, each worker locally finds an Approximate NewTon (ANT) direction, which is sent to the main driver. The main driver, then, averages all the ANT directions received from workers to form a Globally Improved ANT (GIANT) direction. GIANT is highly communication efficient and naturally exploits the trade-offs between local computations and global communications in that more local computations result in fewer overall rounds of communications. Theoretically, we show that GIANT enjoys an improved convergence rate as compared with first-order methods and existing distributed Newton-type methods. Further, and in sharp contrast with many existing distributed Newton-type methods, as well as popular first-order methods, a highly advantageous practical feature of GIANT is that it only involves one tuning parameter. We conduct large-scale experiments on a computer cluster and, empirically, demonstrate the superior performance of GIANT.

Keywords: Convex Optimization · Stochastic Methods · Classification · Regression · Algorithms
[ Paper] 

Author Information

Shusen Wang (UC Berkeley)
Fred Roosta (University of Queensland)
Peng Xu (Stanford University)
Michael Mahoney (UC Berkeley)

More from the Same Authors