Timezone: »

SpiderBoost and Momentum: Faster Variance Reduction Algorithms
Zhe Wang · Kaiyi Ji · Yi Zhou · Yingbin Liang · Vahid Tarokh

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #124

SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization. However, SPIDER uses an accuracy-dependent stepsize that slows down the convergence in practice, and cannot handle objective functions that involve nonsmooth regularizers. In this paper, we propose SpiderBoost as an improved scheme, which allows to use a much larger constant-level stepsize while maintaining the same near-optimal oracle complexity, and can be extended with proximal mapping to handle composite optimization (which is nonsmooth and nonconvex) with provable convergence guarantee. In particular, we show that proximal SpiderBoost achieves an oracle complexity of O(min{n^{1/2}\epsilon^{-2},\epsilon^{-3}}) in composite nonconvex optimization, improving the state-of-the-art result by a factor of O(min{n^{1/6},\epsilon^{-1/3}}). We further develop a novel momentum scheme to accelerate SpiderBoost for composite optimization, which achieves the near-optimal oracle complexity in theory and substantial improvement in experiments.

Author Information

Zhe Wang (Ohio State University)
Kaiyi Ji (The Ohio State University)
Yi Zhou (University of Utah)
Yingbin Liang (The Ohio State University)
Vahid Tarokh (Duke University)

More from the Same Authors