Timezone: »
Stagewise training strategy is widely used for learning neural networks, which runs a stochastic algorithm (e.g., SGD) starting with a relatively large step size (aka learning rate) and geometrically decreasing the step size after a number of iterations. It has been observed that the stagewise SGD has much faster convergence than the vanilla SGD with a polynomially decaying step size in terms of both training error and testing error. {\it But how to explain this phenomenon has been largely ignored by existing studies.} This paper provides some theoretical evidence for explaining this faster convergence. In particular, we consider a stagewise training strategy for minimizing empirical risk that satisfies the Polyak-\L ojasiewicz (PL) condition, which has been observed/proved for neural networks and also holds for a broad family of convex functions. For convex loss functions and two classes of ``nice-behaviored" non-convex objectives that are close to a convex function, we establish faster convergence of stagewise training than the vanilla SGD under the PL condition on both training error and testing error. Experiments on stagewise learning of deep residual networks exhibits that it satisfies one type of non-convexity assumption and therefore can be explained by our theory.
Author Information
Zhuoning Yuan (University of Iowa)
Yan Yan (the University of Iowa)
Rong Jin (Alibaba)
Tianbao Yang (The University of Iowa)
More from the Same Authors
-
2020 Poster: Improved Schemes for Episodic Memory-based Lifelong Learning »
Yunhui Guo · Mingrui Liu · Tianbao Yang · Tajana Rosing -
2020 Spotlight: Improved Schemes for Episodic Memory-based Lifelong Learning »
Yunhui Guo · Mingrui Liu · Tianbao Yang · Tajana Rosing -
2020 Poster: A Decentralized Parallel Algorithm for Training Generative Adversarial Nets »
Mingrui Liu · Wei Zhang · Youssef Mroueh · Xiaodong Cui · Jarret Ross · Tianbao Yang · Payel Das -
2020 Poster: Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization »
Yan Yan · Yi Xu · Qihang Lin · Wei Liu · Tianbao Yang -
2019 Poster: XNAS: Neural Architecture Search with Expert Advice »
Niv Nayman · Asaf Noy · Tal Ridnik · Itamar Friedman · Rong Jin · Lihi Zelnik -
2019 Poster: Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems »
Yi Xu · Rong Jin · Tianbao Yang -
2018 Poster: First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time »
Yi Xu · Rong Jin · Tianbao Yang -
2018 Poster: Adaptive Negative Curvature Descent with Applications in Non-convex Optimization »
Mingrui Liu · Zhe Li · Xiaoyu Wang · Jinfeng Yi · Tianbao Yang -
2018 Poster: Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization »
Xiaoxuan Zhang · Mingrui Liu · Xun Zhou · Tianbao Yang -
2018 Poster: Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions »
Mingrui Liu · Xiaoxuan Zhang · Lijun Zhang · Rong Jin · Tianbao Yang -
2017 Poster: ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization »
Yi Xu · Mingrui Liu · Qihang Lin · Tianbao Yang -
2017 Poster: Improved Dynamic Regret for Non-degenerate Functions »
Lijun Zhang · Tianbao Yang · Jinfeng Yi · Rong Jin · Zhi-Hua Zhou -
2017 Poster: Adaptive Accelerated Gradient Converging Method under H\"{o}lderian Error Bound Condition »
Mingrui Liu · Tianbao Yang -
2017 Poster: Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter »
Yi Xu · Qihang Lin · Tianbao Yang -
2016 Poster: Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/\epsilon)$ »
Yi Xu · Yan Yan · Qihang Lin · Tianbao Yang -
2016 Poster: Improved Dropout for Shallow and Deep Learning »
Zhe Li · Boqing Gong · Tianbao Yang