mlsanityData to 7 Oct 2026

Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

arXiv 2106.11890 ↗First posted 22 Jun 2021cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

When tuning the architecture and hyperparameters of large machine learning models for on-device deployment, it is desirable to understand the optimal trade-offs between on-device latency and model accuracy. In this work, we leverage recent methodological advances in Bayesian optimization over high-dimensional search spaces and multi-objective Bayesian optimization to efficiently explore these trade-offs for a production-scale on-device natural language understanding model at Facebook.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

23 of 30 references.

References · 23

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  2. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  3. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  4. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  5. 2018A Tutorial on Bayesian Optimizationcited by 734
  6. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  7. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  8. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 253
  9. 2018Neural Architecture Search with Bayesian Optimisation and Optimal Transportcited by 192
  10. 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
  11. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 187
  12. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
11 more
  1. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 175
  2. 2021Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020cited by 146
  3. 2021High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspacescited by 139
  4. 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
  5. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 65
  6. 2019Multi-objective Bayesian Optimization using Pareto-frontier Entropycited by 57
  7. 2019AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Searchcited by 33
  8. 2016Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraintscited by 27
  9. 2021Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsingcited by 18
  10. 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
  11. 2019Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAScited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 3; 2024: 1; 2025: 2; 2026: 2.

15 papers.

Sort:

By area:

  1. 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
  2. 2021Multi-Objective Bayesian Optimization over High-Dimensional Search Spacescited by 87
  3. 2022Pareto Set Learning for Expensive Multi-Objective Optimizationcited by 51
  4. 2023AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuningcited by 49
  5. 2022Robust Multi-Objective Bayesian Optimization Under Input Noisecited by 36
  6. 2025Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edgecited by 5
  7. 2022Supernet Training for Federated Image Classification under System Heterogeneitycited by 4
  8. 2022Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Searchcited by 2
  9. 2025Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communicationcited by 2
  10. 2022Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Surveycited by 1
  11. 2023Subgraph Stationary Hardware-Software Inference Co-Designcited by 1
  12. 2026MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deploymentcited by 1
3 more
  1. 2023Dynamical Isometry based Rigorous Fair Neural Architecture Searchcited by 0
  2. 2024Dense Optimizer : An Information Entropy-Guided Structural Search Method for Dense-like Neural Network Designcited by 0
  3. 2026Optimising for Energy Efficiency and Performance in Machine Learningcited by 0