Limited-memory quasi-Newton and Hessianfree Newton methods for non-smooth optimization
Multi-Task Learning via Matrix Regularization
Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
Online-Batch Strongly Convex Multi Kernel Learning
Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparse Learning
Fast global convergence rates of gradient methods for high-dimensional statistical recovery
Machine learning and kernel methods for computer vision
Beyond Stochastic Gradient Descent
Survey of Boosting from an Optimization Perspective
Combining Data Sources Nonlinearly for Cell Nucleus Classification of Renal Cell Carcinoma