mlsanityData to 14 Oct 2026

Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization

arXiv 2106.07611 ↗First posted 14 Jun 2021cs.NE cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Mixed-precision quantization is a powerful tool to enable memory and compute savings of neural network workloads by deploying different sets of bit-width precisions on separate compute operations. In this work, we present a flexible and scalable framework for automated mixed-precision quantization that concurrently optimizes task performance, memory compression, and compute savings through multi-objective evolutionary computing. Our framework centers on Neuroevolution-Enhanced Multi-Objective Optimization (NEMO), a novel search method, which combines established search methods with the representational power of neural networks. Within NEMO, the population is divided into structurally distinct sub-populations, or species, which jointly create the Pareto frontier of solutions for the multi-objective problem. At each generation, species perform separate mutation and crossover operations, and are re-sized in proportion to the goodness of their contribution to the Pareto frontier. In our experiments, we define a graph-based representation to describe the underlying workload, enabling us to deploy graph neural networks trained by NEMO via neuroevolution, to find Pareto optimal configurations for MobileNet-V2, ResNet50 and ResNeXt-101-32x8d. Compared to the state-of-the-art, we achieve competitive results on memory compression and superior results for compute compression. Further analysis reveals that the graph representation and the species-based approach employed by NEMO are critical to finding optimal solutions.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 25 of its 56 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

25 of 56 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  8. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  9. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  10. 2019Learned Step Size Quantizationcited by 628
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  12. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
13 more
  1. 2019Graph U-Netscited by 492
  2. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  3. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  4. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
  5. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  6. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  7. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 125
  8. 2020HAWQV3: Dyadic Neural Network Quantizationcited by 60
  9. 2019The Knowledge Within: Methods for Data-Free Model Compressioncited by 54
  10. 2020HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNscited by 43
  11. 2019Collaborative Evolutionary Reinforcement Learningcited by 37
  12. 2020Neural Network Compression Framework for fast model inferencecited by 18
  13. 2020Optimizing Memory Placement using Evolutionary Graph Reinforcement Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 1.

6 papers.

  1. 2022Multi-Objective GFlowNetscited by 101
  2. 2023Searching for High-Value Molecules Using Reinforcement Learning and Transformerscited by 18
  3. 2023Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Searchcited by 3
  4. 2024CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloadscited by 1
  5. 2024Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimizationcited by 0
  6. 2025Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Questioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
  2. 2023A Practical Mixed Precision Algorithm for Post-Training Quantization
  3. 2026Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training
  4. 2022QFT: Post-training quantization via fast joint finetuning of all degrees of freedom
  5. 2026Task-Aware QUBO Allocation for Mixed-Precision Quantization
  6. 2022AMED: Automatic Mixed-Precision Quantization for Edge Devices
  7. 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge
  8. 2026Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost