Timezone: »
Multiview representation learning is popular for latent factor analysis. Many existing approaches formulate the multiview representation learning as convex optimization problems, where global optima can be obtained by certain algorithms in polynomial time. However, many evidences have corroborated that heuristic nonconvex approaches also have good empirical computational performance and convergence to the global optima, although there is a lack of theoretical justification. Such a gap between theory and practice motivates us to study a nonconvex formulation for multiview representation learning, which can be efficiently solved by a simple stochastic gradient descent method. By analyzing the dynamics of the algorithm based on diffusion processes, we establish a global rate of convergence to the global optima. Numerical experiments are provided to support our theory.
Summary/Notes »Author Information
Zhehui Chen (Georgia Institute of Technology)
Lin Yang (Johns Hopkins)
Chris Junchi Li (Princeton University)
Tuo Zhao (Georgia Institute of Technology)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Talk: Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability »
Mon Aug 7th 01:24 -- 01:42 AM Room C4.4
More from the Same Authors
-
2019 Poster: On Scalable and Efficient Computation of Large Scale Optimal Transport »
Yujia Xie · Minshuo Chen · Haoming Jiang · Tuo Zhao · Hongyuan Zha -
2019 Oral: On Scalable and Efficient Computation of Large Scale Optimal Transport »
Yujia Xie · Minshuo Chen · Haoming Jiang · Tuo Zhao · Hongyuan Zha -
2019 Poster: Toward Understanding the Importance of Noise in Training Neural Networks »
Mo Zhou · Tianyi Liu · Yan Li · Dachao Lin · Enlu Zhou · Tuo Zhao -
2019 Oral: Toward Understanding the Importance of Noise in Training Neural Networks »
Mo Zhou · Tianyi Liu · Yan Li · Dachao Lin · Enlu Zhou · Tuo Zhao -
2017 Poster: Clustering High Dimensional Dynamic Data Streams »
Lin Yang · Harry Lang · Christian Sohler · Vladimir Braverman · Gereon Frahling -
2017 Talk: Clustering High Dimensional Dynamic Data Streams »
Lin Yang · Harry Lang · Christian Sohler · Vladimir Braverman · Gereon Frahling
