← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Winning the Lottery Ahead of Time: Efficient Early Network Pruning ICML 2022
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging ICML 2022
Overcoming Oscillations in Quantization-Aware Training ICML 2022
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning ICML 2022
SDQ: Stochastic Differentiable Quantization with Mixed Precision ICML 2022
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning ICML 2022
Sparse Double Descent: Where Network Pruning Aggravates Overfitting ICML 2022
The State of Sparse Training in Deep Reinforcement Learning ICML 2022
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training NAACL 2022
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval NAACL 2022
Adaptable Adapters NAACL 2022
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline NAACL 2022
KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation NAACL 2022
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation NAACL 2022
GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering NAACL 2022
Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher COLING 2022
Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting COLING 2022
Token and Head Adaptive Transformers for Efficient Natural Language Processing COLING 2022
Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models COLING 2022
Implicit Feature Decoupling With Depthwise Quantization CVPR 2022
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation CVPR 2022
Focal and Global Knowledge Distillation for Detectors CVPR 2022
Dataset Distillation by Matching Training Trajectories CVPR 2022
DyRep: Bootstrapping Training With Dynamic Re-Parameterization CVPR 2022
Knowledge Distillation With the Reused Teacher Classifier CVPR 2022