paper-with-me

홈 › Papers

SPDY: Accurate Pruning with Speedup Guarantees

2022-01-31 · Elias Frantar, Dan Alistarh

The recent focus on the efficiency of deep neural networks (DNNs) has led to significant work on model compression approaches, of which weight pruning is one of the most popular. At the same time, there is rapidly-growing computational support for efficiently executing the unstructured-sparse models obtained via pruning. Yet, most existing pruning methods minimize just the number of remaining weights, i.e. the size of the model, rather than optimizing for inference time. We address this gap by introducing SPDY, a new compression method which automatically determines layer-wise sparsity targets achieving a desired inference speedup on a given system, while minimizing accuracy loss. SPDY is composed of two new techniques: the first is an efficient dynamic programming algorithm for solving the speedup-constrained layer-wise compression problem assuming a set of given layer-wise sensitivity scores; the second is a local search procedure for determining accurate layer-wise sensitivity scores. Experiments across popular vision and language models show that SPDY guarantees speedups while recovering higher accuracy relative to existing strategies, both for one-shot and gradual pruning scenarios, and is compatible with most existing pruning approaches. We also extend our approach to the recently-proposed task of pruning with very little data, where we achieve the best known accuracy recovery when pruning to the GPU-supported 2:4 sparsity pattern.

📄 PDF Abstract BibTeX arXiv:2201.13096

Code (1)

ist-daslab/spdy 공식 구현 pytorch

Tasks

GPUModel CompressionSensitivity

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

2022-03-14 · Eldar Kurtic, Daniel Campos, Tuan Nguyen, Elias Frantar 외

Transformer-based language models have become a key building block for natural language processing. While these models are extremely accurate, they can be too large and computationally intensive to run on standard deploy…

CPUQuantization

Performance optimizations on deep noise suppression models

2021-10-08 · Jerry Chee, Sebastian Braun, Vishak Gopal, Ross Cutler

We study the role of magnitude structured pruning as an architecture search to speed up the inference time of a deep noise suppression (DNS) model. While deep learning approaches have been remarkably successful in enhanc…

Structured Pruning Learns Compact and Accurate Models

2022-04-01 · ACL 2022 5 · Mengzhou Xia, Zexuan Zhong, Danqi Chen

The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, whic…

Model Compression

Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference

2023-06-26 · Junyan Li, Li Lyna Zhang, Jiahang Xu, Yujing Wang 외

Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length. In this work, we p…

CPUModel Compression

Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective

2026-07-04 · Zhenfeng Su, Kang Zhao, Han Bao, Tao Yuan 외 arxiv

While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width pruning to achieve significant reductions in model size. Depth pruning, whic…