paper-with-me

홈 › Papers

Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks

2018-09-01 · ECCV 2018 9 · Chong Li, C. J. Richard Shi

We present COBLA---Constrained Optimization Based Low-rank Approximation---a systematic method of finding an optimal low-rank approximation of a trained convolutional neural network, subject to constraints in the number of multiply-accumulate (MAC) operations and the memory footprint. COBLA optimally allocates the constrained computation resource into each layer of the approximated network. The singular value decomposition of the network weight is computed, then a binary masking variable is introduced to denote whether a particular singular value and the corresponding singular vectors are used in low-rank approximation. With this formulation, the number of the MAC operations and the memory footprint are represented as linear constraints in terms of the binary masking variables. The resulted 0-1 integer programming problem is approximately solved by sequential quadratic programming. COBLA does not introduce any hyperparameter. We empirically demonstrate that COBLA outperforms prior art using the SqueezeNet and VGG-16 architecture on the ImageNet dataset.

📄 PDF Abstract BibTeX

Code (1)

chongli-uw/cobla 공식 구현 tf

Methods 이 논문이 사용한 방법론

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…
Residual Connection 설명 없음
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…
Average Pooling 설명 없음
Fire Module 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
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…

Similar Papers 제목 키워드 기반

Dictionary-based Low-Rank Approximations and the Mixed Sparse Coding problem

2021-11-24 · Jeremy E. Cohen

Constrained tensor and matrix factorization models allow to extract interpretable patterns from multiway data. Therefore identifiability properties and efficient algorithms for constrained low-rank approximations are now…

Data-driven satisficing measure and ranking

2018-07-01 · Wenjie Huang

We propose an computational framework for real-time risk assessment and prioritizing for random outcomes without prior information on probability distributions. The basic model is built based on satisficing measure (SM) …

Stochastic Optimization

1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models

2025-10-30 · Zeliang Zong, Kai Zhang, Zheyang Li, Wenming Tan 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While …

MLoRQ: Bridging Low-Rank and Quantization for Transformer Compression

2025-07-13 · Ofir Gordon, Ariel Lapid, Elad Cohen, Yarden Yagil 외 arxiv

Deploying transformer-based neural networks on resource-constrained edge devices presents a significant challenge. This challenge is often addressed through various techniques, such as low-rank approximation and mixed-pr…

Instance SegmentationImage ClassificationObject Detection

Improved Approximation Algorithms for Low-Rank Problems Using Semidefinite Optimization

2025-01-06 · Ryan Cory-Wright, Jean Pauphilet

Inspired by the impact of the Goemans-Williamson algorithm on combinatorial optimization, we construct an analogous relax-then-sample strategy for low-rank optimization problems. First, for orthogonally constrained quadr…

Combinatorial OptimizationMatrix Completion