paper-with-me

Papers

DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization

2020-12-07 · Yaniv Shulman

Modern neural network architectures typically have many millions of parameters and can be pruned significantly without substantial loss in effectiveness which demonstrates they are over-parameterized. The contribution of this work is two-fold. The first is a method for approximating a multivariate Bernoulli random variable by means of a deterministic and differentiable transformation of any real-valued multivariate random variable. The second is a method for model selection by element-wise multiplication of parameters with approximate binary gates that may be computed deterministically or stochastically and take on exact zero values. Sparsity is encouraged by the inclusion of a surrogate regularization to the $L_0$ loss. Since the method is differentiable it enables straightforward and efficient learning of model architectures by an empirical risk minimization procedure with stochastic gradient descent and theoretically enables conditional computation during training. The method also supports any arbitrary group sparsity over parameters or activations and therefore offers a framework for unstructured or flexible structured model pruning. To conclude experiments are performed to demonstrate the effectiveness of the proposed approach.

📄 PDF Abstract BibTeX arXiv:2012.03653

Code (1)

https://bitbucket.org/YanivShu/diffprune_public 공식 구현 tf

Tasks

Image ClassificationModel SelectionNetwork PruningNeural Architecture Search

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Wide Residual Block 설명 없음
WideResNet 설명 없음

Similar Papers 제목 키워드 기반

Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models

2026-05-27 · Landi He, Mingde Yao, Shawn Young, Lijian Xu arxiv

Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rely on Gumbel-Softmax to approximate discrete selection during trainin…

Continuous Control

Weight-dependent Gates for Network Pruning

2020-07-04 · Yun Li, Zechun Liu, Weiqun Wu, Haotian Yao 외

In this paper, a simple yet effective network pruning framework is proposed to simultaneously address the problems of pruning indicator, pruning ratio, and efficiency constraint. This paper argues that the pruning decisi…

Network Pruning

When Does Low-Bit Quantization Preserve the Decisions of Vector Search?

2026-09-09 · Wenxuan Xiao, Xu Cao arxiv

Low-bit quantization can achieve high recall on some vector representations and fail sharply on others, while average distortion and global rank correlation do not explain the difference. We study quantized vector search…

Deterministic Differentiable Structured Pruning for Large Language Models

2026-03-09 · Weiyu Huang, Pengle Zhang, Xiaolu Zhang, Jun Zhou 외 arxiv

Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplicative gate for each component under an l0 sparsity constraint. Due to the discr…

Single-path Bit Sharing for Automatic Loss-aware Model Compression

2021-01-13 · Jing Liu, Bohan Zhuang, Peng Chen, Chunhua Shen 외

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct network quantization based on the…

Model CompressionNetwork PruningQuantization