mlsanityData to 14 Oct 2026

Predicting the Computational Cost of Deep Learning Models

arXiv 1811.11880 ↗First posted 28 Nov 2018cs.LG cs.AI stat.MLcited by 49

Not on the map. Why?

Abstract (arXiv)

Deep learning is rapidly becoming a go-to tool for many artificial intelligence problems due to its ability to outperform other approaches and even humans at many problems. Despite its popularity we are still unable to accurately predict the time it will take to train a deep learning network to solve a given problem. This training time can be seen as the product of the training time per epoch and the number of epochs which need to be performed to reach the desired level of accuracy. Some work has been carried out to predict the training time for an epoch -- most have been based around the assumption that the training time is linearly related to the number of floating point operations required. However, this relationship is not true and becomes exacerbated in cases where other activities start to dominate the execution time. Such as the time to load data from memory or loss of performance due to non-optimal parallel execution. In this work we propose an alternative approach in which we train a deep learning network to predict the execution time for parts of a deep learning network. Timings for these individual parts can then be combined to provide a prediction for the whole execution time. This has advantages over linear approaches as it can model more complex scenarios. But, also, it has the ability to predict execution times for scenarios unseen in the training data. Therefore, our approach can be used not only to infer the execution time for a batch, or entire epoch, but it can also support making a well-informed choice for the appropriate hardware and model.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 10; 2023: 11; 2024: 11; 2025: 5; 2026: 5.

49 papers.

Sort:

By area:

  1. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 450
  2. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  3. 2024Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learningcited by 53
  4. 2021A Runtime-Based Computational Performance Predictor for Deep Neural Network Trainingcited by 29
  5. 2023Green Edge AI: A Contemporary Surveycited by 25
  6. 2021Regular Polytope Networkscited by 24
  7. 2023FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUscited by 20
  8. 2024LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Servicescited by 14
  9. 2022Building a Performance Model for Deep Learning Recommendation Model Training on GPUscited by 10
  10. 2024Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learningcited by 10
  11. 2023Lie-Poisson Neural Networks (LPNets): Data-Based Computing of Hamiltonian Systems with Symmetriescited by 9
  12. 2022Benchmarking Resource Usage for Efficient Distributed Deep Learningcited by 7
37 more
  1. 2023Continual Adaptation of Vision Transformers for Federated Learningcited by 6
  2. 2023All-optical image denoising using a diffractive visual processorcited by 6
  3. 2021Multirate Training of Neural Networkscited by 5
  4. 2021Quantitative reconstruction of defects in multi-layered bonded composites using fully convolutional network-based ultrasonic inversioncited by 5
  5. 2022Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarkscited by 5
  6. 2023MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devicescited by 5
  7. 2025Targeted Adversarial Denoising Autoencoders (TADA) for Neural Time Series Filtrationcited by 5
  8. 2022DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networkscited by 4
  9. 2025Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLMcited by 4
  10. 2023Predicting the Performance of a Computing System with Deep Networkscited by 3
  11. 2023PruMUX: Augmenting Data Multiplexing with Model Compressioncited by 3
  12. 2024Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Modelscited by 3
  13. 2024MicroFlow: An Efficient Rust-Based Inference Engine for TinyMLcited by 3
  14. 2021A Neophyte With AutoML: Evaluating the Promises of Automatic Machine Learning Toolscited by 2
  15. 2022Perception Over Time: Temporal Dynamics for Robust Image Understandingcited by 2
  16. 2022Towards Optimal VPU Compiler Cost Modeling by using Neural Networks to Infer Hardware Performancescited by 2
  17. 2026Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalizationcited by 2
  18. 2022Inference Latency Prediction at the Edgecited by 1
  19. 2023DIPPM: a Deep Learning Inference Performance Predictive Model using Graph Neural Networkscited by 1
  20. 2023InvKA: Gait Recognition via Invertible Koopman Autoencodercited by 1
  21. 2023Using Cooperative Game Theory to Prune Neural Networkscited by 1
  22. 2024Cloud-based XAI Services for Assessing Open Repository Models Under Adversarial Attackscited by 1
  23. 2024Towards Universal Performance Modeling for Machine Learning Training on Multi-GPU Platformscited by 1
  24. 2024PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Timecited by 1
  25. 2026Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systemscited by 1
  26. 2021Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospectscited by 0
  27. 2021A Clustering-aided Ensemble Method for Predicting Ridesourcing Demand in Chicagocited by 0
  28. 2022AI Model Utilization Measurements For Finding Class Encoding Patternscited by 0
  29. 2024Off-the-Shelf Neural Network Architectures for Forex Time Series Prediction come at a Costcited by 0
  30. 2024A Model Generalization Study in Localizing Indoor Cows with COw LOcalization (COLO) datasetcited by 0
  31. 2024Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networkscited by 0
  32. 2025Duo Streamers: A Streaming Gesture Recognition Frameworkcited by 0
  33. 2025Language modelling techniques for analysing the impact of human genetic variationcited by 0
  34. 2025ScaleDL: Towards Scalable and Efficient Runtime Prediction for Distributed Deep Learning Workloadscited by 0
  35. 2026Data Complexity-aware Deep Model Performance Forecastingcited by 0
  36. 2026LLM-Powered Predictive Decision-Making for Sustainable Data Center Operationscited by 0
  37. 2026ShardMeter: Sharded and Geo-Distributed Training Without the Guessworkcited by 0