Optimization & Theory

HydraNets: Specialized Dynamic Architectures for Efficient Inference CVPR 2018 Hypernetwork-based Implicit Posterior Estimation and Model Averaging of CNN ACML 2018 Implicit Bias of Gradient Descent on Linear Convolutional Networks NeurIPS 2018 Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation ACL 2018 Improving Neural Language Models with Weight Norm Initialization and Regularization EMNLP 2018 Improving Optimization for Models With Continuous Symmetry Breaking ICML 2018 Inference-Invariant Transformation of Batch Normalization for Domain Adaptation of Acoustic Models Interspeech 2018 Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces NeurIPS 2018 Interleaved Structured Sparse Convolutional Neural Networks CVPR 2018 Interpretable Neural Architectures for Attributing an Ad’s Performance to its Writing Style EMNLP 2018 Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections NeurIPS 2018 Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models EMNLP 2018 ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing CVPR 2018 Joint Patch-Group Based Sparse Representation for Image Inpainting ACML 2018 Kalman Normalization: Normalizing Internal Representations Across Network Layers NeurIPS 2018 Knowledge Distillation by On-the-Fly Native Ensemble NeurIPS 2018 Kronecker-factored Curvature Approximations for Recurrent Neural Networks ICLR 2018 L4: Practical loss-based stepsize adaptation for deep learning NeurIPS 2018 LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning NeurIPS 2018 LDMNet: Low Dimensional Manifold Regularized Neural Networks CVPR 2018 Learning Compact Neural Networks with Regularization ICML 2018 Learning Compact Recurrent Neural Networks With Block-Term Tensor Decomposition CVPR 2018 Learning Compressed Transforms with Low Displacement Rank NeurIPS 2018 Learning Compressible 360° Video Isomers CVPR 2018 “Learning-Compression” Algorithms for Neural Net Pruning CVPR 2018