mlsanityData to 14 Oct 2026

Automated Evolutionary Optimization for Resource-Efficient Neural Network Training

arXiv 2510.09566 ↗First posted 10 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary optimization to model architecture and training strategy. PETRA includes pruning, quantization, and loss regularization. Experimental studies on real-world data with financial event sequences, as well as image and time-series -- benchmarks, demonstrate PETRA's ability to improve neural model performance and scalability -- namely, a significant decrease in model size (up to 75%) and latency (up to 33%), and an increase in throughput (by 13%) without noticeable degradation in the target metric.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

25 of 40 references.

References · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  6. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 656
  7. 2019Importance Estimation for Neural Network Pruningcited by 541
  8. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  9. 2021UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuningcited by 162
  10. 2020Layer-adaptive sparsity for the Magnitude-based Pruningcited by 126
  11. 2024Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performancecited by 70
  12. 2020AutoML to Date and Beyond: Challenges and Opportunitiescited by 63
13 more
  1. 2020CoLES: Contrastive Learning for Event Sequences with Self-Supervisioncited by 32
  2. 2021LightAutoML: AutoML Solution for a Large Financial Services Ecosystemcited by 32
  3. 2018Latency and Throughput Characterization of Convolutional Neural Networks for Mobile Computer Visioncited by 13
  4. 2021Multi-Objective Evolutionary Design of Composite Data-Driven Modelscited by 4
  5. 2024FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inferencecited by 4
  6. 2024From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformerscited by 4
  7. 2024Model Uncertainty in Evolutionary Optimization and Bayesian Optimization: A Comparative Analysiscited by 4
  8. 2024Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Modelscited by 4
  9. 2021Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networkscited by 3
  10. 2022Regularization-based Pruning of Irrelevant Weights in Deep Neural Architecturescited by 3
  11. 2023Improvement of Computational Performance of Evolutionary AutoML in a Heterogeneous Environmentcited by 1
  12. 2024Lai Loss: A Novel Loss for Gradient Controlcited by 1
  13. 2024Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Integrating Hyperparameter Search into Model-Free AutoML with Context-Free Grammars
  2. 2026Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch
  3. 2024Large Language Model Agent for Hyper-Parameter Optimization
  4. 2025AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms
  5. 2026Constraint-Driven Model Optimization: An Industry Framework for Selecting Compression and Acceleration Techniques in Modern Machine Learning Systems
  6. 2025Evolution Strategies at the Hyperscale
  7. 2024ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling
  8. 2025Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)