← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization ICML 2017
Efficient Knowledge Distillation from an Ensemble of Teachers INTERSPEECH 2017
On Compressing Deep Models by Low Rank and Sparse Decomposition CVPR 2017
Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee NIPS 2017
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices ICML 2017
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting ICML 2017
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations NIPS 2017
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning NIPS 2017
On the Efficient Representation and Execution of Deep Acoustic Models INTERSPEECH 2016
Fast ConvNets Using Group-Wise Brain Damage CVPR 2016
Model Compression Applied to Small-Footprint Keyword Spotting INTERSPEECH 2016
Sparse Convolutional Neural Networks CVPR 2015
Structured Transforms for Small-Footprint Deep Learning NIPS 2015
Tensorizing Neural Networks NIPS 2015
Is Feature Selection Secure against Training Data Poisoning? ICML 2015
Stochastic Neighbor Compression ICML 2014
Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Matrix Decomposition NIPS 2014
Do Deep Nets Really Need to be Deep? NIPS 2014
Safe Screening of Non-Support Vectors in Pathwise SVM Computation ICML 2013
Offline Mobile Instance Retrieval with a Small Memory Footprint ICCV 2013
Learning Adaptive Value of Information for Structured Prediction NIPS 2013
Decision Jungles: Compact and Rich Models for Classification NIPS 2013
Predicting Parameters in Deep Learning NIPS 2013
PiCoDes: Learning a Compact Code for Novel-Category Recognition NIPS 2011
Collaborative Filtering on a Budget AISTATS 2010