paper-with-me

홈 › Papers

StrassenNets: Deep Learning with a Multiplication Budget

2017-12-11 · ICML 2018 7 · Michael Tschannen, Aran Khanna, Anima Anandkumar

A large fraction of the arithmetic operations required to evaluate deep neural networks (DNNs) consists of matrix multiplications, in both convolution and fully connected layers. We perform end-to-end learning of low-cost approximations of matrix multiplications in DNN layers by casting matrix multiplications as 2-layer sum-product networks (SPNs) (arithmetic circuits) and learning their (ternary) edge weights from data. The SPNs disentangle multiplication and addition operations and enable us to impose a budget on the number of multiplication operations. Combining our method with knowledge distillation and applying it to image classification DNNs (trained on ImageNet) and language modeling DNNs (using LSTMs), we obtain a first-of-a-kind reduction in number of multiplications (over 99.5%) while maintaining the predictive performance of the full-precision models. Finally, we demonstrate that the proposed framework is able to rediscover Strassen's matrix multiplication algorithm, learning to multiply $2 \times 2$ matrices using only 7 multiplications instead of 8.

📄 PDF Abstract BibTeX arXiv:1712.03942

Code (1)

mitscha/strassennets 공식 구현 mxnet

Tasks

Deep Learningimage-classificationImage ClassificationKnowledge DistillationLanguage ModelingLanguage ModellingModel CompressionNeural Network Compression

Similar Papers 제목 키워드 기반

DeepShift: Towards Multiplication-Less Neural Networks

2019-05-30 · Mostafa Elhoushi, Zihao Chen, Farhan Shafiq, Ye Henry Tian 외

The high computation, memory, and power budgets of inferring convolutional neural networks (CNNs) are major bottlenecks of model deployment to edge computing platforms, e.g., mobile devices and IoT. Moreover, training CN…

Edge-computingGPUQuantization

RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Acceleration

2023-01-10 · Yvan Tortorella, Luca Bertaccini, Luca Benini, Davide Rossi 외

The increasing interest in TinyML, i.e., near-sensor machine learning on power budgets of a few tens of mW, is currently pushing toward enabling TinyML-class training as opposed to inference only. Current training algori…

Efficient Randomized Subspace Embeddings for Distributed Optimization under a Communication Budget

2021-03-13 · Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith

We study first-order optimization algorithms under the constraint that the descent direction is quantized using a pre-specified budget of $R$-bits per dimension, where $R \in (0 ,\infty)$. We propose computationally effi…

Distributed OptimizationQuantization

Holistic Filter Pruning for Efficient Deep Neural Networks

2020-09-17 · Lukas Enderich, Fabian Timm, Wolfram Burgard

Deep neural networks (DNNs) are usually over-parameterized to increase the likelihood of getting adequate initial weights by random initialization. Consequently, trained DNNs have many redundancies which can be pruned fr…

Rewrite the Stars

2024-03-29 · CVPR 2024 1 · Xu Ma, Xiyang Dai, Yue Bai, Yizhou Wang 외

Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound, the foundational rationale behind its applicatio…