ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings

[2509.00280] ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2509.00280 (cs) [Submitted on 29 Aug 2025 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings Authors: Ahmed E. Helal , Fabio Checconi , Jan Laukemann , Yongseok Soh , Jesmin Jahan Tithi , Fabrizio Petrini , Jee Choi View PDF HTML (experimental) Abstract: Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose major performance challenges on modern parallel processors. Prior works rely on expert-designed sparse tensor formats that fail to adapt to irregular tensor shapes and data distributions. We present the reinforcement-learned adaptive tensor encoding (ReLATE) framework, a learning-augmented method that discovers safe and efficient sparse encodings, without labeled examples, via a hybrid model-free and model-based algorithm that learns from both real and imagined actions. Moreover, ReLATE introduces elastic training, rule-driven action masking, and dynamics-informed action filtering to ensure correct encoding with bounded execution time, even during early learning. After offline training, with geometric-mean overhead of only 5.82% relative to TD workflow time, ReLATE deploys the best encoding with zero inference overhead. Across diverse real-world sparse tensors, ReLATE consistently outperforms the best expert-designed format by up to 2x, with a geometric-mean speedup of 1.38-1.41x. Comments: Accepted to SC 2026 Subjects: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC); Performance (cs.PF) Cite as: arXiv:2509.00280 [cs.LG] (or arXiv:2509.00280v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2509.00280 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ahmed E. Helal [ view email ] [v1] Fri, 29 Aug 2025 23:45:09 UTC (596 KB) [v2] Thu, 27 Aug 2026 05:00:24 UTC (593 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2025-09 Change to browse by: cs cs.DC cs.PF References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings#677415
• Identifiability of Nonnegative Tensor Decompositions via Positive Scattering#999123
• Low-Rank Tensor Decompositions for the Theory of Neural Networks: Understanding deep learning through the lens of tensor formats [Special Issue on the Mathematics of Deep Learning].#489682
• Multivariate quantum state preparation with optimized tensor networks#987066
• Lindblad Multiproduct Formulas#971979