mlsanityData to 14 Oct 2026

Optuna: A Next-generation Hyperparameter Optimization Framework

arXiv 1907.10902 ↗First posted 25 Jul 2019cs.LG stat.MLcited by 2,501

Not on the map. Why?

Cited by 87 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to construct the parameter search space dynamically, (2) efficient implementation of both searching and pruning strategies, and (3) easy-to-setup, versatile architecture that can be deployed for various purposes, ranging from scalable distributed computing to light-weight experiment conducted via interactive interface. In order to prove our point, we will introduce Optuna, an optimization software which is a culmination of our effort in the development of a next generation optimization software. As an optimization software designed with define-by-run principle, Optuna is particularly the first of its kind. We will present the design-techniques that became necessary in the development of the software that meets the above criteria, and demonstrate the power of our new design through experimental results and real world applications. Our software is available under the MIT license (https://github.com/pfnet/optuna/).

Key facts. Cited by 2,501 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 152; 2022: 217; 2023: 321; 2024: 476; 2025: 651; 2026: 684.

2,501 papers.

Sort:

By area:

  1. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  2. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  3. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  4. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  5. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  6. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 291
  7. 2022Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfercited by 288
  8. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
  9. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  10. 2023When Do Neural Nets Outperform Boosted Trees on Tabular Data?cited by 223
  11. 2024AI Agents That Mattercited by 219
  12. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
38 more
  1. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 207
  2. 2022On Embeddings for Numerical Features in Tabular Deep Learningcited by 186
  3. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 181
  4. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 172
  5. 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 147
  6. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 145
  7. 2024A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalistcited by 137
  8. 2024Large Language Models to Enhance Bayesian Optimizationcited by 135
  9. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 128
  10. 2024TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensemblingcited by 113
  11. 2021HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPOcited by 112
  12. 2021BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representationcited by 106
  13. 2023Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Taskcited by 88
  14. 2024Better than classical? The subtle art of benchmarking quantum machine learning modelscited by 85
  15. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  16. 2023TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023cited by 74
  17. 2023SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learningcited by 73
  18. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 70
  19. 2023EasyTPP: Towards Open Benchmarking Temporal Point Processescited by 68
  20. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 68
  21. 2023Scalable Membership Inference Attacks via Quantile Regressioncited by 65
  22. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  23. 2021YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimizationcited by 62
  24. 2023Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networkscited by 61
  25. 2021EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTacited by 60
  26. 2023Hyperparameters in Reinforcement Learning and How To Tune Themcited by 59
  27. 2022Concept Activation Regions: A Generalized Framework For Concept-Based Explanationscited by 57
  28. 2024Making Pre-trained Language Models Great on Tabular Predictioncited by 57
  29. 2023Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunitycited by 56
  30. 2023Generative Table Pre-training Empowers Models for Tabular Predictioncited by 55
  31. 2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
  32. 2023Algorithm Evolution Using Large Language Modelcited by 53
  33. 2022Transfer Learning with Deep Tabular Modelscited by 52
  34. 2024TALENT: A Tabular Analytics and Learning Toolboxcited by 52
  35. 2024Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoningcited by 49
  36. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 49
  37. 2024TuneTables: Context Optimization for Scalable Prior-Data Fitted Networkscited by 47
  38. 2022Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discoverycited by 46

50 most cited of 2,501 All 2,501 (JSON)