Optimization & Theory

Calibrated Elastic Regularization in Matrix Completion NeurIPS 2012 Deep Learning Made Easier by Linear Transformations in Perceptrons AISTATS 2012 Exact and Stable Recovery of Sequences of Signals with Sparse Increments via Differential _1-Minimization NeurIPS 2012 Feature Clustering for Accelerating Parallel Coordinate Descent NeurIPS 2012 Krylov Subspace Descent for Deep Learning AISTATS 2012 Large Scale Distributed Deep Networks NeurIPS 2012 Learning optimal spike-based representations NeurIPS 2012 Matrix reconstruction with the local max norm NeurIPS 2012 Nyström Method vs Random Fourier Features: A Theoretical and Empirical Comparison NeurIPS 2012 On Sparse, Spectral and Other Parameterizations of Binary Probabilistic Models AISTATS 2012 Parametric Local Metric Learning for Nearest Neighbor Classification NeurIPS 2012 Proximal Newton-type methods for convex optimization NeurIPS 2012 Scaled Gradients on Grassmann Manifolds for Matrix Completion NeurIPS 2012 Scaling up Kernel SVM on Limited Resources: A Low-rank Linearization Approach AISTATS 2012 Sketch-Based Linear Value Function Approximation NeurIPS 2012 Sparse Prediction with the k-Support Norm NeurIPS 2012 Stochastic Gradient Descent with Only One Projection NeurIPS 2012 Synchronization can Control Regularization in Neural Systems via Correlated Noise Processes NeurIPS 2012 The representer theorem for Hilbert spaces: a necessary and sufficient condition NeurIPS 2012 Transelliptical Graphical Models NeurIPS 2012 Volume Regularization for Binary Classification NeurIPS 2012 A blind sparse deconvolution method for neural spike identification NeurIPS 2011 Algorithms for Hyper-Parameter Optimization NeurIPS 2011 Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization NeurIPS 2011 Expressive Power and Approximation Errors of Restricted Boltzmann Machines NeurIPS 2011