Abstract
In this work, we establish an asymptotic limit of almost-lossless compression of a random, finite alphabet tensor which admits a low-rank canonical polyadic decomposition.
Almost-lossless compression of a low-rank random tensor
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- Solving Tensor Low Cycle Rank Approximation (2023)61% match
- Hotelling Deflation on Large Symmetric Spiked Tensors (2023)60% match
- Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent (2024)59% match
- Cannikin's Law in Tensor Modeling: A Rank Study for Entanglement and Separability in Tensor Complexity and Model Capacity (2022)59% match
- On Estimating Rank-One Spiked Tensors in the Presence of Heavy Tailed Errors (2021)59% match
- A Tighter Complexity Analysis of SparseGPT (2024)58% match
- Low-Rank Tensor Approximation of Weights in Large Language Models via Cosine Lanczos Bidiagonalization (2026)57% match
- Low-Rank Compression of Language Models via Differentiable Rank Selection (2025)57% match