Structured Low-Rank Tensors for Generalized Linear Models

• URL: http://arxiv.org/abs/2308.02922v1
• Date: Sat, 5 Aug 2023 17:20:41 GMT
• Title: Structured Low-Rank Tensors for Generalized Linear Models
• Authors: Batoul Taki, Anand D. Sarwate, and Waheed U. Bajwa
• Abstract summary: This work investigates a new low-rank tensor model, called Low Separation Rank (LSR), in Generalized Linear Model (GLM) problems. The LSR model generalizes the well-known Tucker and CANDECOMP/PARAFAC (CP) models. Experiments on synthetic datasets demonstrate the efficacy of the proposed LSR tensor model for three regression types.
• Score: 15.717917936953718
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent works have shown that imposing tensor structures on the coefficient tensor in regression problems can lead to more reliable parameter estimation and lower sample complexity compared to vector-based methods. This work investigates a new low-rank tensor model, called Low Separation Rank (LSR), in Generalized Linear Model (GLM) problems. The LSR model -- which generalizes the well-known Tucker and CANDECOMP/PARAFAC (CP) models, and is a special case of the Block Tensor Decomposition (BTD) model -- is imposed onto the coefficient tensor in the GLM model. This work proposes a block coordinate descent algorithm for parameter estimation in LSR-structured tensor GLMs. Most importantly, it derives a minimax lower bound on the error threshold on estimating the coefficient tensor in LSR tensor GLM problems. The minimax bound is proportional to the intrinsic degrees of freedom in the LSR tensor GLM problem, suggesting that its sample complexity may be significantly lower than that of vectorized GLMs. This result can also be specialised to lower bound the estimation error in CP and Tucker-structured GLMs. The derived bounds are comparable to tight bounds in the literature for Tucker linear regression, and the tightness of the minimax lower bound is further assessed numerically. Finally, numerical experiments on synthetic datasets demonstrate the efficacy of the proposed LSR tensor model for three regression types (linear, logistic and Poisson). Experiments on a collection of medical imaging datasets demonstrate the usefulness of the LSR model over other tensor models (Tucker and CP) on real, imbalanced data with limited available samples.

Related papers

• Computational and Statistical Guarantees for Tensor-on-Tensor Regression with Tensor Train Decomposition [27.29463801531576]
  We study the theoretical and algorithmic aspects of the TT-based ToT regression model. We propose two algorithms to efficiently find solutions to constrained error bounds. We establish the linear convergence rate of both IHT and RGD.
  arXiv  Detail & Related papers  (2024-06-10T03:51:38Z)
• Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms [88.74308282658133]
  Reization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. Recent studies have revealed that, when applied to long-term reinforcement learning problems, model-based RP PGMs may experience chaotic and non-smooth optimization landscapes. We propose a spectral normalization method to mitigate the exploding variance issue caused by long model unrolls.
  arXiv  Detail & Related papers  (2023-10-30T18:43:21Z)
• Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models [69.22568644711113]
  We introduce probabilistic unrolling, a method that combines Monte Carlo sampling with iterative linear solvers to circumvent matrix inversions. Our theoretical analyses reveal that unrolling and backpropagation through the iterations of the solver can accelerate gradient estimation for maximum likelihood estimation. In experiments on simulated and real data, we demonstrate that probabilistic unrolling learns latent Gaussian models up to an order of magnitude faster than gradient EM, with minimal losses in model performance.
  arXiv  Detail & Related papers  (2023-06-05T21:08:34Z)
• Statistical and computational rates in high rank tensor estimation [11.193504036335503]
  Higher-order tensor datasets arise commonly in recommendation systems, neuroimaging, and social networks. We consider a generative latent variable tensor model that incorporates both high rank and low rank models. We show that the statistical-computational gap emerges only for latent variable tensors of order 3 or higher.
  arXiv  Detail & Related papers  (2023-04-08T15:34:26Z)
• Experimental observation on a low-rank tensor model for eigenvalue problems [3.378115152915894]
  We utilize a low-rank tensor model (LTM) as a function approxor, combined with the gradient descent method, to solve evalue problems.
  arXiv  Detail & Related papers  (2023-02-01T16:03:41Z)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal [70.15267479220691]
  We consider and analyze the sample complexity of model reinforcement learning with a generative variance-free model. Our analysis shows that it is nearly minimax-optimal for finding an $varepsilon$-optimal policy when $varepsilon$ is sufficiently small.
  arXiv  Detail & Related papers  (2022-05-27T19:39:24Z)
• Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns [77.34726150561087]
  We introduce four complicated missing patterns, including missing and three fiber-like missing cases according to the mode-drivenn fibers. Despite nonity of the objective function in our model, we derive the optimal solutions by integrating alternating data-mputation method of multipliers.
  arXiv  Detail & Related papers  (2022-05-19T08:37:56Z)
• Scalable Spatiotemporally Varying Coefficient Modelling with Bayesian Kernelized Tensor Regression [17.158289775348063]
  Kernelized tensor Regression (BKTR) can be considered a new and scalable approach to modeling processes with low-rank cotemporal structure. We conduct extensive experiments on both synthetic and real-world data sets, and our results confirm the superior performance and efficiency of BKTR for model estimation and inference.
  arXiv  Detail & Related papers  (2021-08-31T19:22:23Z)
• Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation [105.33409035876691]
  This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. We design a novel structured tensor low-rank norm tailored to MVSC. We show that the proposed method outperforms state-of-the-art methods to a significant extent.
  arXiv  Detail & Related papers  (2020-04-30T11:52:12Z)
• Sparse and Low-Rank High-Order Tensor Regression via Parallel Proximal Method [6.381138694845438]
  We propose the Sparse and Low-rank Regression model for large-scale data with high-order structures. Our model enforces sparsity and low-rankness of the tensor coefficient. Our model's predictions exhibit meaningful interpretations on the video dataset.
  arXiv  Detail & Related papers  (2019-11-29T06:25:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.