Neural Network Optimization

Deeply Learning the Messages in Message Passing Inference NeurIPS 2015 Deeply-Supervised Nets AISTATS 2015 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification ICCV 2015 Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets NeurIPS 2015 End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture NeurIPS 2015 Equilibrated adaptive learning rates for non-convex optimization NeurIPS 2015 From Averaging to Acceleration, There is Only a Step-size COLT 2015 Global Convergence of Online Limited Memory BFGS JMLR 2015 Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems ICML 2015 Gradient-based Hyperparameter Optimization through Reversible Learning ICML 2015 Gradient Estimation Using Stochastic Computation Graphs NeurIPS 2015 Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks NeurIPS 2015 HONOR: Hybrid Optimization for NOn-convex Regularized problems NeurIPS 2015 Learning with Incremental Iterative Regularization NeurIPS 2015 Local Smoothness in Variance Reduced Optimization NeurIPS 2015 Natural Neural Networks NeurIPS 2015 On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants NeurIPS 2015 Open Problem: The landscape of the loss surfaces of multilayer networks COLT 2015 Optimizing Neural Networks with Kronecker-factored Approximate Curvature ICML 2015 Preconditioned Spectral Descent for Deep Learning NeurIPS 2015 Recurrent Convolutional Neural Network for Object Recognition CVPR 2015 Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix ICML 2015 See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG ICCV 2015 Stochastic Spectral Descent for Restricted Boltzmann Machines AISTATS 2015 StopWasting My Gradients: Practical SVRG NeurIPS 2015