# PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization

arXiv: https://arxiv.org/abs/2307.09488 · HTML: https://mlsanity.com/paper/2307.09488/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 18 Jul 2023.

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [SNAS: Stochastic Neural Architecture Search](https://mlsanity.com/paper/1812.09926/) (2018)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [Rethinking Differentiable Search for Mixed-Precision Neural Networks](https://mlsanity.com/paper/2004.05795/) (2020)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [Bringing AI To Edge: From Deep Learning's Perspective](https://mlsanity.com/paper/2011.14808/) (2020)
- [A Practical Mixed Precision Algorithm for Post-Training Quantization](https://mlsanity.com/paper/2302.05397/) (2023)
- [HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search](https://mlsanity.com/paper/2102.11646/) (2021)
- [Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge](https://mlsanity.com/paper/2301.10281/) (2023)
- [Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition](https://mlsanity.com/paper/2203.12932/) (2022)
- [Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes](https://mlsanity.com/paper/2206.08852/) (2022)
- [VEGA: Towards an End-to-End Configurable AutoML Pipeline](https://mlsanity.com/paper/2011.01507/) (2020)
- [Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference](https://mlsanity.com/paper/2306.05060/) (2023)
- [Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks](https://mlsanity.com/paper/2206.00302/) (2022)

## Built on by (most cited first, 9 of 9)

- [Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks](https://mlsanity.com/paper/2407.01054/) (2024)
- [Adaptive Deep Learning for Efficient Visual Pose Estimation aboard Ultra-low-power Nano-drones](https://mlsanity.com/paper/2401.15236/) (2024)
- [Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables](https://mlsanity.com/paper/2409.07485/) (2024)
- [HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays](https://mlsanity.com/paper/2402.01226/) (2024)
- [Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones](https://mlsanity.com/paper/2402.15273/) (2024)
- [Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time](https://mlsanity.com/paper/2409.18566/) (2024)
- [BlankSkip: Early-exit Object Detection onboard Nano-drones](https://mlsanity.com/paper/2603.28149/) (2026)
- [End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables](https://mlsanity.com/paper/2604.10117/) (2026)
- [MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor](https://mlsanity.com/paper/2608.07192/) (2026)

## Abstract (arXiv)

Accurate yet efficient Deep Neural Networks (DNNs) are in high demand, especially for applications that require their execution on constrained edge devices. Finding such DNNs in a reasonable time for new applications requires automated optimization pipelines since the huge space of hyper-parameter combinations is impossible to explore extensively by hand. In this work, we propose PLiNIO, an open-source library implementing a comprehensive set of state-of-the-art DNN design automation techniques, all based on lightweight gradient-based optimization, under a unified and user-friendly interface. With experiments on several edge-relevant tasks, we show that combining the various optimizations available in PLiNIO leads to rich sets of solutions that Pareto-dominate the considered baselines in terms of accuracy vs model size. Noteworthy, PLiNIO achieves up to 94.34% memory reduction for a <1% accuracy drop compared to a baseline architecture.