Optimization

Sparseness Meets Deepness: 3D Human Pose Estimation From Monocular Video CVPR 2016 Staple: Complementary Learners for Real-Time Tracking CVPR 2016 Sublabel-Accurate Relaxation of Nonconvex Energies CVPR 2016 The Sound of APALM Clapping: Faster Nonsmooth Nonconvex Optimization with Stochastic Asynchronous PALM NeurIPS 2016 Tight Complexity Bounds for Optimizing Composite Objectives NeurIPS 2016 Towards More Efficient SPSD Matrix Approximation and CUR Matrix Decomposition JMLR 2016 Train faster, generalize better: Stability of stochastic gradient descent ICML 2016 Trust No One: Low Rank Matrix Factorization Using Hierarchical RANSAC CVPR 2016 Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition Interspeech 2016 Video-Story Composition via Plot Analysis CVPR 2016 A fast, universal algorithm to learn parametric nonlinear embeddings NeurIPS 2015 A Modified Orthant-Wise Limited Memory Quasi-Newton Method with Convergence Analysis ICML 2015 A Multi-Plane Block-Coordinate Frank-Wolfe Algorithm for Training Structural SVMs With a Costly Max-Oracle CVPR 2015 A Projection Free Method for Generalized Eigenvalue Problem With a Nonsmooth Regularizer ICCV 2015 A Stochastic PCA and SVD Algorithm with an Exponential Convergence Rate ICML 2015 Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization NeurIPS 2015 Deep learning with Elastic Averaging SGD NeurIPS 2015 Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets NeurIPS 2015 Equilibrated adaptive learning rates for non-convex optimization NeurIPS 2015 Escaping From Saddle Points — Online Stochastic Gradient for Tensor Decomposition COLT 2015 FaLRR: A Fast Low Rank Representation Solver CVPR 2015 Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization CVPR 2015 Frequency-Based Environment Matting by Compressive Sensing ICCV 2015 Gradient Estimation Using Stochastic Computation Graphs NeurIPS 2015 Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks NeurIPS 2015