DP-Net: Dynamic Programming Guided Deep Neural Network Compression
In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an optimization process to train a clustering-friendly DNN. Experiments showed that the DP-Net allows larger compression than the state-of-the-art counterparts while preserving accuracy. The largest 77X compression ratio on Wide ResNet is achieved by combining DP-Net with other compression techniques. Furthermore, the DP-Net is extended for compressing a robust DNN model with negligible accuracy loss. At last, a custom accelerator is designed on FPGA to speed up the inference computation with DP-Net.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringNeural Network CompressionQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis
Despite extensive usage in high-performance, low-level systems programming applications, C is susceptible to vulnerabilities due to manual memory management and unsafe pointer operations. Rust, a modern systems programmi…
Code GenerationCode TranslationTranslationAdaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning
Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, d…
Federated LearningBounded Approximate Symbolic Dynamic Programming for Hybrid MDPs
Recent advances in symbolic dynamic programming (SDP) combined with the extended algebraic decision diagram (XADD) data structure have provided exact solutions for mixed discrete and continuous (hybrid) MDPs with piecewi…
Tree Quantization for Large-Scale Similarity Search and Classification
We propose a new vector encoding scheme (tree quantization) that obtains lossy compact codes for high-dimensional vectors via tree-based dynamic programming. Similarly to several previous schemes such as product quantiza…
ClassificationGeneral Classificationimage-classificationImage Classification+2An Algorithm for Cellular Reprogramming
The day we understand the time evolution of subcellular elements at a level of detail comparable to physical systems governed by Newton's laws of motion seems far away. Even so, quantitative approaches to cellular dynami…