On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Device-edge co-inference”

Communication-Computation Efficient Device-Edge Co-Inference via AutoMLcs.LG

Paper proposes an AutoML framework for efficient device-edge co-inference.

problem Finding optimal hyper-parameters for model sparsity and feature compression.

method Sequential decision problem solved using deep reinforcement learning (DRL).

result Achieves better communication-computation trade-off and significant speedup.

AutoML Device-edge co-inference Deep reinforcement learning Hyper-parameter optimization Inference efficiency

2021-08-30abs ↗pdf ↗

BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systemscs.LG

BottleNet++ compresses deep learning features for efficient mobile inference.

problem Balancing computation and communication in mobile devices with deep learning models.

method End-to-end architecture with encoder, non-trainable channel layer, and decoder.

result Achieves high compression ratio and bandwidth reduction with minimal accuracy loss.

feature compression deep learning mobile inference channel coding sparsity

2019-10-31abs ↗pdf ↗

Communication-Computation Trade-Off in Resource-Constrained Edge Inferencecs.LG

This paper optimizes AI inference on edge devices with reduced communication and computation costs.

problem Efficiently performing AI inference on resource-constrained edge devices with reduced communication and computation costs.

method A three-step framework for effective inference: model split point selection, communication-aware model compression, and task-oriented encoding of intermediate features.

result Our proposed framework achieves a better trade-off and significantly reduces inference latency compared to baseline methods.

AI inference Edge computing Resource-constrained devices Communication-computation trade-off Model compression

2020-06-03abs ↗pdf ↗

NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usagecs.CV

Much of the focus in the design of deep neural networks has been on improving accuracy, leading to more powerful yet highly complex network architectures that are difficult to deploy in practical scenarios, particularly on edge devices such as mobile and other consumer devices given their high computational and memory …

2018-06-14abs ↗pdf ↗

EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edgeeess.AS

Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices. Recently, there have been greater efforts in the design of small, low-footprint deep neural networks (DNNs) that are more appropriate fo…

2018-10-18abs ↗pdf ↗

Adaptive Anomaly Detection for IoT Data in Hierarchical Edge Computingcs.LG

Adaptive anomaly detection for IoT data reduces delay by 84%.

problem Real-time anomaly detection for IoT devices with limited resources.

method Hierarchical edge computing with adaptive anomaly detection models.

result Reduces detection delay by 84% while maintaining accuracy.

IoT Anomaly Detection Hierarchical Edge Computing Deep Neural Networks Contextual Bandit

2020-01-10abs ↗pdf ↗