Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections
This provides a scalable method for handling non-commutative dependencies in sequences like time series and video, which is an incremental improvement over existing approaches.
The paper tackles the challenge of analyzing sequential data with complex dependencies by representing sequences using tensor algebra with low-rank tensor projections, achieving state-of-the-art performance on multivariate time series classification and video generative models.
Sequential data such as time series, video, or text can be challenging to analyse as the ordered structure gives rise to complex dependencies. At the heart of this is non-commutativity, in the sense that reordering the elements of a sequence can completely change its meaning. We use a classical mathematical object -- the tensor algebra -- to capture such dependencies. To address the innate computational complexity of high degree tensors, we use compositions of low-rank tensor projections. This yields modular and scalable building blocks for neural networks that give state-of-the-art performance on standard benchmarks such as multivariate time series classification and generative models for video.