Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima

Keyphrases

• Local Minima 100%
• Non-convexity 100%
• Gradient Descent 100%
• Stochastic Gradient Descent 100%
• Non-smoothness 100%
• Loss Function 50%
• Nonsmooth 50%
• Distributed Algorithms 25%
• Network Applications 25%
• Stochastic Approximation 25%
• Gradient Flow 25%
• Deep Learning 25%
• Internet of Things 25%
• Machine Learning Models 25%
• Machine Learning Problems 25%
• Non-smooth Loss Function 25%
• Large-scale Machine Learning 25%
• Ordinary Differential Equation Method 25%

Mathematics

• Stochastics 100%
• Local Minimum 100%
• Saddle Point 66%
• Loss Function 50%
• Critical Point 33%
• Probability 33%
• Ordinary Differential Equation 16%
• Gradient Flow 16%
• Analogous Result 16%
• Deep Learning Method 16%
• Internet-Of-Things 16%