mlsanityData to 7 Oct 2026

Theano: A Python framework for fast computation of mathematical expressions

arXiv 1605.02688 ↗First posted 9 May 2016cs.SC cs.LG cs.MScited by 64

Not on the map. Why?

Abstract (arXiv)

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. The present article is structured as follows. Section I provides an overview of the Theano software and its community. Section II presents the principal features of Theano and how to use them, and compares them with other similar projects. Section III focuses on recently-introduced functionalities and improvements. Section IV compares the performance of Theano against Torch7 and TensorFlow on several machine learning models. Section V discusses current limitations of Theano and potential ways of improving it.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2017: 1; 2018: 0; 2019: 0; 2020: 0; 2021: 24; 2022: 18; 2023: 14; 2024: 4; 2025: 2; 2026: 1.

64 papers.

Sort:

By area:

  1. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  2. 2021HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPOcited by 111
  3. 2022Tutorial on amortized optimizationcited by 83
  4. 2024Scalable Optimization in the Modular Normcited by 64
  5. 2021Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contactcited by 50
  6. 2021Universal Approximation Theorems for Differentiable Geometric Deep Learningcited by 41
  7. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  8. 2021Torch.fx: Practical Program Capture and Transformation for Deep Learning in Pythoncited by 38
  9. 2022Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learningcited by 20
  10. 2025Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inferencecited by 20
  11. 2021SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learningcited by 16
  12. 2022Bugs in Machine Learning-based Systems: A Faultload Benchmarkcited by 15
38 more
  1. 2023Automatic Gradient Descent: Deep Learning without Hyperparameterscited by 14
  2. 2021LazyTensor: combining eager execution with domain-specific compilerscited by 11
  3. 2023The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deploymentcited by 11
  4. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  5. 2023SoftMAC: Differentiable Soft Body Simulation with Forecast-based Contact Model and Two-way Coupling with Articulated Rigid Bodies and Clothescited by 9
  6. 2021Breiman's two cultures: You don't have to choose sidescited by 8
  7. 2021Relational Graph Convolutional Networks: A Closer Lookcited by 8
  8. 2021BDNNSurv: Bayesian deep neural networks for survival analysis using pseudo valuescited by 7
  9. 2023Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contactcited by 7
  10. 2021Ivy: Templated Deep Learning for Inter-Framework Portabilitycited by 6
  11. 2024Investigating White-Box Attacks for On-Device Modelscited by 6
  12. 2021tensorflow-riemopt: A Library for Optimization on Riemannian Manifoldscited by 5
  13. 2017Speech Enhancement using a Deep Mixture of Expertscited by 4
  14. 2021A Model-Driven Approach to Machine Learning and Software Modeling for the IoTcited by 4
  15. 2021Discriminative Multimodal Learning via Conditional Priors in Generative Modelscited by 4
  16. 2022Optimizing Mixture of Experts using Dynamic Recompilationscited by 4
  17. 2022Differentiable Bilevel Programming for Stackelberg Congestion Gamescited by 4
  18. 2022Differential testing for machine learning: an analysis for classification algorithms beyond deep learningcited by 3
  19. 2023Software-based Automatic Differentiation is Flawedcited by 3
  20. 2023The Grand Illusion: The Myth of Software Portability and Implications for ML Progresscited by 3
  21. 2021D3p -- A Python Package for Differentially-Private Probabilistic Programmingcited by 2
  22. 2021An automatic differentiation system for the age of differential privacycited by 2
  23. 2021Implicit SVD for Graph Representation Learningcited by 2
  24. 2022Deep Sequence Modeling for Anomalous ISP Traffic Predictioncited by 2
  25. 2022An Empirical Study of Library Usage and Dependency in Deep Learning Frameworkscited by 2
  26. 2022DeeProb-kit: a Python Library for Deep Probabilistic Modellingcited by 2
  27. 2022State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictionscited by 2
  28. 2023Baechi: Fast Device Placement of Machine Learning Graphscited by 2
  29. 2023Design and Implementation of A Soccer Ball Detection System with Multiple Camerascited by 2
  30. 2021Adaptive Latent Space Tuning for Non-Stationary Distributionscited by 1
  31. 2022Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programscited by 1
  32. 2022SOL: Reducing the Maintenance Overhead for Integrating Hardware Support into AI Frameworkscited by 1
  33. 2022Go Beyond Multiple Instance Neural Networks: Deep-learning Models based on Local Pattern Aggregationcited by 1
  34. 2022EdnaML: A Declarative API and Framework for Reproducible Deep Learningcited by 1
  35. 2023Diff-Transfer: Model-based Robotic Manipulation Skill Transfer via Differentiable Physics Simulationcited by 1
  36. 2025A projection-based framework for gradient-free and parallel learningcited by 1
  37. 2021Data Analytics and Machine Learning Methods, Techniques and Tool for Model-Driven Engineering of Smart IoT Servicescited by 0
  38. 2021Tensors Fitting Perfectlycited by 0

50 most cited of 64 All 64 (JSON)