# Theano: A Python framework for fast computation of mathematical expressions

arXiv: https://arxiv.org/abs/1605.02688 · HTML: https://mlsanity.com/paper/1605.02688/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2016.

## Built on by (most cited first, 30 of 64)

- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO](https://mlsanity.com/paper/2109.06716/) (2021)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [Scalable Optimization in the Modular Norm](https://mlsanity.com/paper/2405.14813/) (2024)
- [Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact](https://mlsanity.com/paper/2103.16021/) (2021)
- [Universal Approximation Theorems for Differentiable Geometric Deep Learning](https://mlsanity.com/paper/2101.05390/) (2021)
- [Tangent Space Backpropagation for 3D Transformation Groups](https://mlsanity.com/paper/2103.12032/) (2021)
- [Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python](https://mlsanity.com/paper/2112.08429/) (2021)
- [Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference](https://mlsanity.com/paper/2501.14794/) (2025)
- [Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning](https://mlsanity.com/paper/2201.12023/) (2022)
- [SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning](https://mlsanity.com/paper/2111.14693/) (2021)
- [Bugs in Machine Learning-based Systems: A Faultload Benchmark](https://mlsanity.com/paper/2206.12311/) (2022)
- [Automatic Gradient Descent: Deep Learning without Hyperparameters](https://mlsanity.com/paper/2304.05187/) (2023)
- [LazyTensor: combining eager execution with domain-specific compilers](https://mlsanity.com/paper/2102.13267/) (2021)
- [The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment](https://mlsanity.com/paper/2302.06117/) (2023)
- [Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review](https://mlsanity.com/paper/2311.11883/) (2023)
- [SoftMAC: Differentiable Soft Body Simulation with Forecast-based Contact Model and Two-way Coupling with Articulated Rigid Bodies and Clothes](https://mlsanity.com/paper/2312.03297/) (2023)
- [Breiman's two cultures: You don't have to choose sides](https://mlsanity.com/paper/2104.12219/) (2021)
- [Relational Graph Convolutional Networks: A Closer Look](https://mlsanity.com/paper/2107.10015/) (2021)
- [BDNNSurv: Bayesian deep neural networks for survival analysis using pseudo values](https://mlsanity.com/paper/2101.03170/) (2021)
- [Jade: A Differentiable Physics Engine for Articulated Rigid Bodies with Intersection-Free Frictional Contact](https://mlsanity.com/paper/2309.04710/) (2023)
- [Ivy: Templated Deep Learning for Inter-Framework Portability](https://mlsanity.com/paper/2102.02886/) (2021)
- [Investigating White-Box Attacks for On-Device Models](https://mlsanity.com/paper/2402.05493/) (2024)
- [tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds](https://mlsanity.com/paper/2105.13921/) (2021)
- [Speech Enhancement using a Deep Mixture of Experts](https://mlsanity.com/paper/1703.09302/) (2017)
- [A Model-Driven Approach to Machine Learning and Software Modeling for the IoT](https://mlsanity.com/paper/2107.02689/) (2021)
- [Discriminative Multimodal Learning via Conditional Priors in Generative Models](https://mlsanity.com/paper/2110.04616/) (2021)
- [Optimizing Mixture of Experts using Dynamic Recompilations](https://mlsanity.com/paper/2205.01848/) (2022)
- [Differentiable Bilevel Programming for Stackelberg Congestion Games](https://mlsanity.com/paper/2209.07618/) (2022)
- [Differential testing for machine learning: an analysis for classification algorithms beyond deep learning](https://mlsanity.com/paper/2207.11976/) (2022)

## 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.