20 results for “tensor completion”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper proposes Robust Iterative t-CUR (R-ItCUR), a tensor-native algorithm for robust recovery of low-rank tensors from partial observations contaminated with sparse outliers using tensor cross-c…
The paper introduces TN-SHAP-G, a novel framework that uses graph-structured tensor networks to efficiently approximate and compute Shapley values and interaction indices for black-box models, overcom…
This paper provides explicit error bounds for the infinite-width Gaussian-process limit of random neural networks using tensor programs and quantitative convergence theory in Wasserstein distance.
The paper studies eigenpair estimation for the tensorized Laplace--Beltrami operator from multi-manifold mixture data.
The paper introduces SLORR, a simple and stateless framework for in-training low-rank regularization of neural networks using two variants based on the Hoyer sparsity metric and the nuclear norm.
This paper improves the foundations of neural likelihood approximation for Bayesian inverse problems by making the learning problem strictly convex and showing convergence to the true likelihood.
Jieke Shi, Junda He, Wenjia Jiang, Weifeng Sun +10 more
Brevis compresses model checkpoints by synthesizing self-contained DSL programs that reconstruct tensors bit-exactly, reducing storage requirements and achieving high compression and decompression spe…
This paper proposes an algorithm called Tensor-based Second-order Causal Discovery (TSCD) to uncover causal dependencies among variables.
The paper studies sampling and recovery for tensor-valued dynamical systems using partial spatial observations over time.
The paper introduces Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) to achieve massive, structured compression of deep neural networks, demonstrating compression ratios up to 77,000x…
VISReg introduces a novel regularization technique that combines variance control with a Sliced-Wasserstein-based sketching objective to stabilize self-supervised learning, achieving state-of-the-art…
This paper constructs a graph-based image restoration system using unrolled networks and shows that the learned steps select an element of a Krylov subspace, constraining the hypothesis space.
The paper analyzes low-degree estimation thresholds for recovering hidden signals in planted hypergraphs and tensor PCA, establishing sharp phase transitions and providing polynomial-time recovery alg…
The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…
This paper presents the first polynomial-time algorithms for two variants of multireference alignment.