paper-with-me

Papers

Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey

2022-05-17 · Paul Wimmer, Jens Mehnert, Alexandru Paul Condurache

State-of-the-art deep learning models have a parameter count that reaches into the billions. Training, storing and transferring such models is energy and time consuming, thus costly. A big part of these costs is caused by training the network. Model compression lowers storage and transfer costs, and can further make training more efficient by decreasing the number of computations in the forward and/or backward pass. Thus, compressing networks also at training time while maintaining a high performance is an important research topic. This work is a survey on methods which reduce the number of trained weights in deep learning models throughout the training. Most of the introduced methods set network parameters to zero which is called pruning. The presented pruning approaches are categorized into pruning at initialization, lottery tickets and dynamic sparse training. Moreover, we discuss methods that freeze parts of a network at its random initialization. By freezing weights, the number of trainable parameters is shrunken which reduces gradient computations and the dimensionality of the model's optimization space. In this survey we first propose dimensionality reduced training as an underlying mathematical model that covers pruning and freezing during training. Afterwards, we present and discuss different dimensionality reduced training methods.

📄 PDF Abstract BibTeX arXiv:2205.08099

Code (0)

등록된 구현이 없습니다.

Tasks

Model CompressionSurvey

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

FreezeNet: Full Performance by Reduced Storage Costs

2020-11-28 · Paul Wimmer, Jens Mehnert, Alexandru Condurache

Pruning generates sparse networks by setting parameters to zero. In this work we improve one-shot pruning methods, applied before training, without adding any additional storage costs while preserving the sparse gradient…

Differential Privacy Meets Neural Network Pruning

2023-03-08 · Kamil Adamczewski, Mijung Park

A major challenge in applying differential privacy to training deep neural network models is scalability.The widely-used training algorithm, differentially private stochastic gradient descent (DP-SGD), struggles with tra…

Dimensionality ReductionNetwork Pruning

WSBD: Freezing-Based Optimizer for Quantum Neural Networks

2026-02-11 · Christopher Kverne, Mayur Akewar, Yuqian Huo, Tirthak Patel 외 arxiv

The training of Quantum Neural Networks (QNNs) is hindered by the high computational cost of gradient estimation and the barren plateau problem, where optimization landscapes become intractably flat. To address these cha…

Balanced and Elastic End-to-end Training of Dynamic LLMs

2025-05-20 · Mohamed Wahib, Muhammed Abdullah Soyturk, Didem Unat

To reduce computational and memory costs in Large Language Models (LLMs), dynamic workload reduction schemes like Mixture of Experts (MoEs), parameter pruning, layer freezing, sparse attention, early token exit, and Mixt…

GPUMixture-of-Experts

ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks

2025-05-12 · Wenhao Hu, Paul Henderson, José Cano

Pruning is a widely used method for compressing Deep Neural Networks (DNNs), where less relevant parameters are removed from a DNN model to reduce its size. However, removing parameters reduces model accuracy, so pruning…