Error Analysis of Tensor-Train Cross Approximation
Nov 28, 2022
About
Tensor train decomposition is widely used in machine learning and quantum physics due to its concise representation of high-dimensional tensors, overcoming the curse of dimensionality. Cross approximation—originally developed for representing a matrix from a set of selected rows and columns—is an efficient method for constructing a tensor train decomposition of a tensor from few of its entries. While tensor train cross approximation has achieved remarkable performance in practical applications, its theoretical analysis, in particular regarding the error of the approximation, is so far lacking. To our knowledge, existing results only provide element-wise approximation accuracy guarantees, which lead to a very loose bound when extended to the entire tensor. In this paper, we bridge this gap by providing accuracy guarantees in terms of the entire tensor for both exact and noisy measurements. Our results illustrate how the choice of selected subtensors affects the quality of the cross approximation and that the approximation error caused by model error and/or measurement error may not grow exponentially with the order of the tensor. These results are verified by numerical experiments, and may have important implications for the usefulness of cross approximations for high-order tensors, such as those encountered in the description of quantum many-body states.Tensor train decomposition is widely used in machine learning and quantum physics due to its concise representation of high-dimensional tensors, overcoming the curse of dimensionality. Cross approximation—originally developed for representing a matrix from a set of selected rows and columns—is an efficient method for constructing a tensor train decomposition of a tensor from few of its entries. While tensor train cross approximation has achieved remarkable performance in practical applications,…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On Translation and Reconstruction Guarantees of the Cycle-Consistent Generative Adversarial Networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
Watch later
Bencheng Yan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Panel Discussion
Watch later
Cheng Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Closing Remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning about materials by learning to predict images and videos
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Basis Encoded Polynomial Neural Fields for Subband Decomposition
Watch later
Guandao Yang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%