[ICML 2020] Model Compression Paper List

Adversarial Neural Pruning with Latent Vulnerability Supperession (KAIST)

Operate-Aware Soft Channel Pruning using Differentiable Masks (SNU)

Network Pruning by Greedy Subnetwork Selection

DropNet: Reducing Neural Network Complexity via Iterative Pruning

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

Towards Accuarte Post-traing Network Quantization via Bit-Split and Stitching

Online Learned Continual Compression with Adaptive Quantization Modules

Differentiable Product Quantization for Learning Compact Embedding Layers

Up or Down? Adaptive Rounding for Post-Training Quantization

Feature Quantization Improves GAN Trainig

Accelerating Large-Scale Inference with Anisotropic Vector Quantization

Evaluating Lossy Compression Rates of Deep Generative Models

Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding