Optimization & Theory

Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation CVPR 2017 Population Matching Discrepancy and Applications in Deep Learning NeurIPS 2017 Preventing Gradient Explosions in Gated Recurrent Units NeurIPS 2017 Principles of Riemannian Geometry in Neural Networks NeurIPS 2017 QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding NeurIPS 2017 Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation CVPR 2017 Reducing Reparameterization Gradient Variance NeurIPS 2017 Reducing the Computational Complexity of Two-Dimensional LSTMs Interspeech 2017 Regularization techniques for fine-tuning in neural machine translation EMNLP 2017 Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice NeurIPS 2017 Riemannian approach to batch normalization NeurIPS 2017 Runtime Neural Pruning NeurIPS 2017 S3Pool: Pooling With Stochastic Spatial Sampling CVPR 2017 SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud NeurIPS 2017 Scalable Planning with Tensorflow for Hybrid Nonlinear Domains NeurIPS 2017 SchNet: A continuous-filter convolutional neural network for modeling quantum interactions NeurIPS 2017 Seeing Into Darkness: Scotopic Visual Recognition CVPR 2017 Selective Classification for Deep Neural Networks NeurIPS 2017 SGD Learns the Conjugate Kernel Class of the Network NeurIPS 2017 SGM-Nets: Semi-Global Matching With Neural Networks CVPR 2017 Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU EMNLP 2017 Simultaneous Visual Data Completion and Denoising Based on Tensor Rank and Total Variation Minimization and Its Primal-Dual Splitting Algorithm CVPR 2017 Single Image Reflection Suppression CVPR 2017 Sobolev Training for Neural Networks NeurIPS 2017 Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes CVPR 2017