M. Pawan Kumar |
LECTURES
Lecture 5, Part 1: Empirical risk minimization
Lecture 5, Part 2: Optimization for deep learning LINKS FOR EMPIRICAL RISK MINIMIZATION
Max-Margin Markov Networks
Support Vector Machine Learning for Interdependent and Structured Output Spaces LINKS FOR CONVEX OPTIMIZATION OVERVIEW
Convex Optimization, Stephen Boyd and Lieven Vandenberghe.
Convex Optimization: Algorithms and Complexity LINKS FOR MOMENTUM
A Method for Solving a Convex Programming Problem with Convergence Rate O(1/k2)
On the Importance of Initialization and Momentum in Deep Learning LINKS FOR SMOOTHING
Smooth Minimization of Non-Smooth Functions
Smoothing and First Order Methods: A Unified Framework
Smooth Loss Functions for Deep Top-k Classification LINKS FOR ADAPTIVE GRADIENTS
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
AdaDelta: An Adaptive Learning Rate Method
Adam: A Method for Stochastic Optimization
On the Convergence of Adam and Beyond
The Marginal Value of Adaptive Gradient Methods in Machine Learning LINKS FOR DIFFERENCE-OF-CONVEX OPTIMIZATION
Variations and Extensions of the Concave-Convex Procedure
Trusting SVM for Piecewise Linear CNNs |