Timezone: »

Delay-agnostic Asynchronous Coordinate Update Algorithm
Xuyang Wu · Changxin Liu · Sindri Magnússon · Mikael Johansson

Wed Jul 26 02:00 PM -- 03:30 PM (PDT) @ Exhibit Hall 1 #513

We propose a delay-agnostic asynchronous coordinate update algorithm (DEGAS) for computing operator fixed points, with applications to asynchronous optimization. DEGAS includes novel asynchronous variants of ADMM and block-coordinate descent as special cases. We prove that DEGAS converges with both bounded and unbounded delays under delay-free parameter conditions. We also validate by theory and experiments that DEGAS adapts well to the actual delays. The effectiveness of DEGAS is demonstrated by numerical experiments on classification problems.

Author Information

Xuyang Wu (KTH Royal Institute of Technology)
Changxin Liu (KTH Royal Institute of Technology)
Sindri Magnússon (Stockholm University)
Mikael Johansson (KTH Royal Institute of Technology)

More from the Same Authors