# Any-Precision Deep Neural Networks

arXiv: https://arxiv.org/abs/1911.07346 · HTML: https://mlsanity.com/paper/1911.07346/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2019.

## Built on by (most cited first, 30 of 40)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs](https://mlsanity.com/paper/2402.10517/) (2024)
- [FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos](https://mlsanity.com/paper/2212.12294/) (2022)
- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [Dynamic Network Quantization for Efficient Video Inference](https://mlsanity.com/paper/2108.10394/) (2021)
- [BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer](https://mlsanity.com/paper/2105.08952/) (2021)
- [Progressive Mixed-Precision Decoding for Efficient LLM Inference](https://mlsanity.com/paper/2410.13461/) (2024)
- [DiSparse: Disentangled Sparsification for Multitask Model Compression](https://mlsanity.com/paper/2206.04662/) (2022)
- [Matryoshka Quantization](https://mlsanity.com/paper/2502.06786/) (2025)
- [AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment](https://mlsanity.com/paper/2411.10606/) (2024)
- [EQ-Net: Elastic Quantization Neural Networks](https://mlsanity.com/paper/2308.07650/) (2023)
- [Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach](https://mlsanity.com/paper/2207.10188/) (2022)
- [Class-based Quantization for Neural Networks](https://mlsanity.com/paper/2211.14928/) (2022)
- [AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs](https://mlsanity.com/paper/2510.10467/) (2025)
- [Boosted Dynamic Neural Networks](https://mlsanity.com/paper/2211.16726/) (2022)
- [GradMDM: Adversarial Attack on Dynamic Networks](https://mlsanity.com/paper/2304.06724/) (2023)
- [Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization](https://mlsanity.com/paper/2103.02904/) (2021)
- [Recognition of handwritten MNIST digits on low-memory 2 Kb RAM Arduino board using LogNNet reservoir neural network](https://mlsanity.com/paper/2105.02953/) (2021)
- [BARVINN: Arbitrary Precision DNN Accelerator Controlled by a RISC-V CPU](https://mlsanity.com/paper/2301.00290/) (2022)
- [MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization](https://mlsanity.com/paper/2305.08117/) (2023)
- [Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths](https://mlsanity.com/paper/2103.01435/) (2021)
- [Neural Networks with Quantization Constraints](https://mlsanity.com/paper/2210.15623/) (2022)
- [Low-Precision Mixed-Computation Models for Inference on Edge](https://mlsanity.com/paper/2312.02210/) (2023)
- [NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN](https://mlsanity.com/paper/2506.17870/) (2025)
- [One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment](https://mlsanity.com/paper/2105.01353/) (2021)
- [TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision](https://mlsanity.com/paper/2506.11431/) (2025)
- [Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling](https://mlsanity.com/paper/2510.20673/) (2025)
- [Low-Rank Compression for IMC Arrays](https://mlsanity.com/paper/2502.07820/) (2025)
- [MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models](https://mlsanity.com/paper/2607.23047/) (2026)
- [Computational Complexity Evaluation of Neural Network Applications in Signal Processing](https://mlsanity.com/paper/2206.12191/) (2022)

## Abstract (arXiv)

We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-widths, by truncating the least significant bits, to support dynamic speed and accuracy trade-off. When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision. This nice property facilitates flexible deployment of deep learning models in real-world applications, where in practice trade-offs between model accuracy and runtime efficiency are often sought. Previous literature presents solutions to train models at each individual fixed efficiency/accuracy trade-off point. But how to produce a model flexible in runtime precision is largely unexplored. When the demand of efficiency/accuracy trade-off varies from time to time or even dynamically changes in runtime, it is infeasible to re-train models accordingly, and the storage budget may forbid keeping multiple models. Our proposed framework achieves this flexibility without performance degradation. More importantly, we demonstrate that this achievement is agnostic to model architectures and applicable to multiple vision tasks. Our code is released at https://github.com/SHI-Labs/Any-Precision-DNNs.