Optimization & Theory

SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization CVPR 2019 Self-Supervised 3D Hand Pose Estimation Through Training by Fitting CVPR 2019 Semi-flat minima and saddle points by embedding neural networks to overparameterization NeurIPS 2019 Sensitive-Sample Fingerprinting of Deep Neural Networks CVPR 2019 Sensitivity Analysis of Deep Neural Networks AAAI 2019 Separate Loss for Basic and Compound Facial Expression Recognition in the Wild ACML 2019 Sharp Restricted Isometry Bounds for the Inexistence of Spurious Local Minima in Nonconvex Matrix Recovery JMLR 2019 Similarity Preserving Deep Asymmetric Quantization for Image Retrieval AAAI 2019 Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation CVPR 2019 Small and Practical BERT Models for Sequence Labeling EMNLP 2019 Snapshot Distillation: Teacher-Student Optimization in One Generation CVPR 2019 SNR: Sub-Network Routing for Flexible Parameter Sharing in Multi-Task Learning AAAI 2019 Sobolev Independence Criterion NeurIPS 2019 Sparse Adversarial Perturbations for Videos AAAI 2019 SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers NeurIPS 2019 Spectral Metric for Dataset Complexity Assessment CVPR 2019 Spectral Reconstruction From Dispersive Blur: A Novel Light Efficient Spectral Imager CVPR 2019 Speculative Beam Search for Simultaneous Translation EMNLP 2019 Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-Spheres CVPR 2019 SpiderBoost and Momentum: Faster Variance Reduction Algorithms NeurIPS 2019 Spurious Valleys in One-hidden-layer Neural Network Optimization Landscapes JMLR 2019 SSN: Learning Sparse Switchable Normalization via SparsestMax CVPR 2019 SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points NeurIPS 2019 Stagewise Training Accelerates Convergence of Testing Error Over SGD NeurIPS 2019 Stochastic Gradient Descent Learns State Equations with Nonlinear Activations COLT 2019