TensorLy: Tensor Learning in Python
arXiv:1610.09555
Abstract
Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of machine learning and data analysis, tensor methods have been gaining increasing traction. However, software support for tensor operations is not on the same footing. In order to bridge this gap, we have developed \emph{TensorLy}, a high-level API for tensor methods and deep tensorized neural networks in Python. TensorLy aims to follow the same standards adopted by the main projects of the Python scientific community, and seamlessly integrates with them. Its BSD license makes it suitable for both academic and commercial applications. TensorLy's backend system allows users to perform computations with NumPy, MXNet, PyTorch, TensorFlow and CuPy. They can be scaled on multiple CPU or GPU machines. In addition, using the deep-learning frameworks as backend allows users to easily design and train deep tensorized neural networks. TensorLy is available at https://github.com/tensorly/tensorly
References in corpus (4)
Cited by in corpus (38)
- Tensor Methods in Computer Vision and Deep Learning
- Tensor Regression Networks
- Multi-Head Attention: Collaborate Instead of Concatenate
- Tensor Train decomposition on TensorFlow (T3F)
- DisCoPy: Monoidal Categories in Python
- Data-driven emergence of convolutional structure in neural networks
- Spectral Learning on Matrices and Tensors
- Point Spread Function Modelling for Wide Field Small Aperture Telescopes with a Denoising Autoencoder
- Higher-Order Networks Representation and Learning: A Survey
- Learning Low-Rank Approximation for CNNs
- TedNet: A Pytorch Toolkit for Tensor Decomposition Networks
- Understanding Generalization in Deep Learning via Tensor Methods
- Low-Rank Tucker Approximation of a Tensor From Streaming Data
- Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis
- Adaptive Learning of Tensor Network Structures
- Ivy: Templated Deep Learning for Inter-Framework Portability
- Tensor Decompositions in Deep Learning
- Deep Tensor CCA for Multi-view Learning
- The landscape of software for tensor computations
- The Tensor Track VII: From Quantum Gravity to Artificial Intelligence
- Applying Tensor Decomposition to image for Robustness against Adversarial Attack
- Biologically inspired architectures for sample-efficient deep reinforcement learning
- Disentangling Observed Causal Effects from Latent Confounders using Method of Moments
- Fast Low-Rank Tensor Decomposition by Ridge Leverage Score Sampling
- A Time-aware tensor decomposition for tracking evolving patterns
- AutoHOOT: Automatic High-Order Optimization for Tensors
- Weighted Tensor Completion for Time-Series Causal Inference
- HOTTBOX: Higher Order Tensor ToolBOX
- Tucker Tensor Decomposition on FPGA
- Ricci-Notation Tensor Framework for Model-based Approaches to Imaging
- PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
- Low-Rank+Sparse Tensor Compression for Neural Networks
- Multivariate Convolutional Sparse Coding with Low Rank Tensor
- A novel fusion Python application of data mining techniques to evaluate airborne magnetic datasets
- Tensor Convolutional Sparse Coding with Low-Rank activations, an application to EEG analysis
- Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation
- High Order Singular Value Decomposition for Plant Biodiversity Estimation
- Modulating Regularization Frequency for Efficient Compression-Aware Model Training