analiza aiqbench
This paper introduces MINT, a novel method using tensor decomposition on stacked recurrence matrices to efficiently mine co-clustered patterns in large-scale time series data across domains like energy and transportation. By transforming self-similarity plots into tensors, the approach enables scalable analysis of multivariate datasets containing regular motifs without relying on standard deep learning architectures. The work represents a significant contribution to machine learning theory for handling high-dimensional temporal sequences through linear algebraic primitives rather than end-to-end neural networks.
MINT: Tensor Decomposition on Stacked Recurrence Matrices for Time Series Data Mining
arXiv:2608.04157v1 Announce Type: new Abstract: Recurrence plots are a time series data mining primitive applied to a variety of domains (e.g. star light curves, sound waveforms, CCT telemetry). This work proposes tensorized self-similarity matrices as a primitive for univariate time series datasets ($N\times n$) of $N$ time series of length $n$ with a subsequence window of length $m$, and whose tensor-based nature is naturally extensible to multivariate datasets. The proposed method to compute this primitive computes dot plots of size $N \times (n-m+1) \times (n-m+ 1)$ from these datasets, where the subsequent tensor is mined using tensor decomposition methods to mine for co-clustered patterns. We demonstrate our results in mass rapid transit, electricity demand, wind turbine, and car traffic data, finding the MINT pipeline effectively co-clusters cross-sensor patterns in highly regular datasets containing motifs at regular intervals.
Abstract:Recurrence plots are a time series data mining primitive applied to a variety of domains (e.g. star light curves, sound waveforms, CCT telemetry). This work proposes tensorized self-similarity matrices as a primitive for univariate time series datasets ($N\times n$) of $N$ time series of length $n$ with a subsequence window of length $m$, and whose tensor-based nature is naturally extensible to multivariate datasets. The proposed method to compute this primitive computes dot plots of size $N \times (n-m+1) \times (n-m+ 1)$ from these datasets, where the subsequent tensor is mined using tensor decomposition methods to mine for co-clustered patterns. We demonstrate our results in mass rapid transit, electricity demand, wind turbine, and car traffic data, finding the MINT pipeline effectively co-clusters cross-sensor patterns in highly regular datasets containing motifs at regular intervals.
Machine Learning (cs.LG)
arXiv:2608.04157 [cs.LG]
(or arXiv:2608.04157v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.04157 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 226 cuvinte
Subiecte conexe
DI Series: Serving Kimi-K3 MXFP4 Wide-EP Disaggregated on AMD Instinct MI300X and MI325X
AMD · 8 oct. 2026
Profiling in PyTorch (Part 3): Attention is all you profile
Hugging Face · 10 iul. 2026
LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights
arXiv · 19 aug. 2026
News
Quantum Computing Report · 7 iun. 2026