Optimization & Theory

On the Quality of the Initial Basin in Overspecified Neural Networks ICML 2016 On the Role of Nonlinear Transformations in Deep Neural Network Acoustic Models Interspeech 2016 Optimal Architectures in a Solvable Model of Deep Networks NeurIPS 2016 Optimal Black-Box Reductions Between Optimization Objectives NeurIPS 2016 Orthogonal Random Features NeurIPS 2016 Pairwise Matching Through Max-Weight Bipartite Belief Propagation CVPR 2016 Parametric Object Motion From Blur CVPR 2016 Predicting When Saliency Maps Are Accurate and Eye Fixations Consistent CVPR 2016 Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions CVPR 2016 Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent NeurIPS 2016 Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization CVPR 2016 Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization NeurIPS 2016 Quantized Convolutional Neural Networks for Mobile Devices CVPR 2016 Quantized Random Projections and Non-Linear Estimation of Cosine Similarity NeurIPS 2016 Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels JMLR 2016 Random Features for Sparse Signal Classification CVPR 2016 Refining Architectures of Deep Convolutional Neural Networks CVPR 2016 Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning NeurIPS 2016 Residual Networks Behave Like Ensembles of Relatively Shallow Networks NeurIPS 2016 Rethinking the Inception Architecture for Computer Vision CVPR 2016 Scalable Adaptive Stochastic Optimization Using Random Projections NeurIPS 2016 Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters ICML 2016 Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes NeurIPS 2016 SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques NeurIPS 2016 Semantic 3D Reconstruction With Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint CVPR 2016