Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning

• URL: http://arxiv.org/abs/1910.10453v7
• Date: Sun, 19 Jan 2025 01:27:23 GMT
• Title: Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
• Authors: Anis Elgabli, Jihong Park, Amrit S. Bedi, Chaouki Ben Issaid, Mehdi Bennis, Vaneet Aggarwal,
• Abstract summary: We propose a communication-efficient decentralized machine learning (ML) algorithm, coined QGADMM (QGADMM) We develop a novel quantization method to adaptively adjust modelization levels and their probabilities, while proving the convergence of QGADMM for convex functions.
• Score: 66.18202188565922
• License:
• Abstract: In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, while updating its model via the group alternating direction method of multipliers (GADMM). Moreover, each worker transmits the quantized difference between its current model and its previously quantized model, thereby decreasing the communication payload size. However, due to the lack of centralized entity in decentralized ML, the spatial sparsity and payload compression may incur error propagation, hindering model training convergence. To overcome this, we develop a novel stochastic quantization method to adaptively adjust model quantization levels and their probabilities, while proving the convergence of Q-GADMM for convex objective functions. Furthermore, to demonstrate the feasibility of Q-GADMM for non-convex and stochastic problems, we propose quantized stochastic GADMM (Q-SGADMM) that incorporates deep neural network architectures and stochastic sampling. Simulation results corroborate that Q-GADMM significantly outperforms GADMM in terms of communication efficiency while achieving the same accuracy and convergence speed for a linear regression task. Similarly, for an image classification task using DNN, Q-SGADMM achieves significantly less total communication cost with identical accuracy and convergence speed compared to its counterpart without quantization, i.e., stochastic GADMM (SGADMM).

Related papers

• Approximately Equivariant Quantum Neural Network for $p4m$ Group Symmetries in Images [30.01160824817612]
  This work proposes equivariant Quantum Convolutional Neural Networks (EquivQCNNs) for image classification under planar $p4m$ symmetry. We present the results tested in different use cases, such as phase detection of the 2D Ising model and classification of the extended MNIST dataset.
  arXiv  Detail & Related papers  (2023-10-03T18:01:02Z)
• Quantum Multi-Agent Reinforcement Learning for Autonomous Mobility Cooperation [14.606459096293088]
  We propose a quantum MARL (QMARL) algorithm based on the concept of actor-critic network. Our QMARL is beneficial in terms of efficient parameter utilization and fast convergence due to quantum supremacy. An additional technique for scalability is proposed, which is called projection value measure (PVM)
  arXiv  Detail & Related papers  (2023-08-03T03:29:25Z)
• Quantized Adaptive Subgradient Algorithms and Their Applications [39.103587572626026]
  We propose quantized composite mirror descent adaptive subgradient (QCMD adagrad) and quantized regularized dual average adaptive subgradient (QRDA adagrad) for distributed training. A quantized gradient-based adaptive learning rate matrix is constructed to achieve a balance between communication costs, accuracy, and model sparsity.
  arXiv  Detail & Related papers  (2022-08-11T04:04:03Z)
• ClusterQ: Semantic Feature Distribution Alignment for Data-Free Quantization [111.12063632743013]
  We propose a new and effective data-free quantization method termed ClusterQ. To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics. We also incorporate the intra-class variance to solve class-wise mode collapse.
  arXiv  Detail & Related papers  (2022-04-30T06:58:56Z)
• A new perspective on probabilistic image modeling [92.89846887298852]
  We present a new probabilistic approach for image modeling capable of density estimation, sampling and tractable inference. DCGMMs can be trained end-to-end by SGD from random initial conditions, much like CNNs. We show that DCGMMs compare favorably to several recent PC and SPN models in terms of inference, classification and sampling.
  arXiv  Detail & Related papers  (2022-03-21T14:53:57Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge Computing [113.52575069030192]
  Big data, including applications with high security requirements, are often collected and stored on multiple heterogeneous devices, such as mobile devices, drones and vehicles. Due to the limitations of communication costs and security requirements, it is of paramount importance to extract information in a decentralized manner instead of aggregating data to a fusion center. We consider the problem of learning model parameters in a multi-agent system with data locally processed via distributed edge nodes. A class of mini-batch alternating direction method of multipliers (ADMM) algorithms is explored to develop the distributed learning model.
  arXiv  Detail & Related papers  (2020-10-02T10:41:59Z)
• Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM [52.12831959365598]
  We propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers. The proposed algorithm, Censored and Quantized Generalized GADMM, leverages the worker grouping and decentralized learning ideas of Group Alternating Direction Method of Multipliers (GADMM) Numerical simulations corroborate that CQ-GGADMM exhibits higher communication efficiency in terms of the number of communication rounds and transmit energy consumption without compromising the accuracy and convergence speed.
  arXiv  Detail & Related papers  (2020-09-14T14:18:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.