Entry-Specific Matrix Estimation under Arbitrary Sampling Patterns through the Lens of Network Flows

• URL: http://arxiv.org/abs/2409.03980v1
• Date: Fri, 6 Sep 2024 02:01:03 GMT
• Title: Entry-Specific Matrix Estimation under Arbitrary Sampling Patterns through the Lens of Network Flows
• Authors: Yudong Chen, Xumei Xi, Christina Lee Yu,
• Abstract summary: Matrix completion tackles the task of predicting missing values in a low-rank matrix based on a sparse set of observed entries. We introduce a matrix completion algorithm based on network flows in the bipartite graph induced by the observation pattern. Our results show that the minimax squared error for recovery of a particular entry in the matrix is proportional to the effective resistance of the corresponding edge in the graph.
• Score: 9.631640936820126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Matrix completion tackles the task of predicting missing values in a low-rank matrix based on a sparse set of observed entries. It is often assumed that the observation pattern is generated uniformly at random or has a very specific structure tuned to a given algorithm. There is still a gap in our understanding when it comes to arbitrary sampling patterns. Given an arbitrary sampling pattern, we introduce a matrix completion algorithm based on network flows in the bipartite graph induced by the observation pattern. For additive matrices, the particular flow we used is the electrical flow and we establish error upper bounds customized to each entry as a function of the observation set, along with matching minimax lower bounds. Our results show that the minimax squared error for recovery of a particular entry in the matrix is proportional to the effective resistance of the corresponding edge in the graph. Furthermore, we show that our estimator is equivalent to the least squares estimator. We apply our estimator to the two-way fixed effects model and show that it enables us to accurately infer individual causal effects and the unit-specific and time-specific confounders. For rank-$1$ matrices, we use edge-disjoint paths to form an estimator that achieves minimax optimal estimation when the sampling is sufficiently dense. Our discovery introduces a new family of estimators parametrized by network flows, which provide a fine-grained and intuitive understanding of the impact of the given sampling pattern on the relative difficulty of estimation at an entry-specific level. This graph-based approach allows us to quantify the inherent complexity of matrix completion for individual entries, rather than relying solely on global measures of performance.

Related papers

• Statistical Inference For Noisy Matrix Completion Incorporating Auxiliary Information [3.9748528039819977]
  This paper investigates statistical inference for noisy matrix completion in a semi-supervised model. We apply an iterative least squares (LS) estimation approach in our considered context. We show that our method only needs a few iterations, and the resulting entry-wise estimators of the low-rank matrix and the coefficient matrix are guaranteed to have normal distributions.
  arXiv  Detail & Related papers  (2024-03-22T01:06:36Z)
• Entry-Specific Bounds for Low-Rank Matrix Completion under Highly Non-Uniform Sampling [10.824999179337558]
  We show that it is often better and sometimes optimal to run estimation algorithms on a smaller submatrix rather than the entire matrix. Our bounds characterize the hardness of estimating each entry as a function of the localized sampling probabilities.
  arXiv  Detail & Related papers  (2024-02-29T23:24:43Z)
• On the design-dependent suboptimality of the Lasso [27.970033039287884]
  We show that the Lasso estimator is provably minimax rate-suboptimal when the minimum singular value is small. Our lower bound is strong enough to preclude the sparse statistical optimality of all forms of the Lasso.
  arXiv  Detail & Related papers  (2024-02-01T07:01:54Z)
• Entrywise Inference for Missing Panel Data: A Simple and Instance-Optimal Approach [27.301741710016223]
  We consider inferential questions associated with the missing data version of panel data induced by staggered adoption. We develop and analyze a data-driven procedure for constructing entrywise confidence intervals with pre-specified coverage. We prove non-asymptotic and high-probability bounds on its error in estimating each missing entry.
  arXiv  Detail & Related papers  (2024-01-24T18:58:18Z)
• Matrix Completion from General Deterministic Sampling Patterns [28.116011361245224]
  We establish theoretical guarantee for the exact and approximate low-rank matrix completion problems. We show that the algorithm can be successful as the observation graph is well-connected and has similar node degrees.
  arXiv  Detail & Related papers  (2023-06-04T07:01:31Z)
• Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization [59.87663954467815]
  Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. In this paper, leveraging a recent linear algebraic theorem called Gershgorin disc perfect alignment (GDPA), we unroll a projection-free algorithm for semi-definite programming relaxation (SDR) of a binary graph. Experimental results show that our unrolled network outperformed pure model-based graph classifiers, and achieved comparable performance to pure data-driven networks but using far fewer parameters.
  arXiv  Detail & Related papers  (2021-09-10T07:01:15Z)
• Sparse PCA via $l_{2,p}$-Norm Regularization for Unsupervised Feature Selection [138.97647716793333]
  We propose a simple and efficient unsupervised feature selection method, by combining reconstruction error with $l_2,p$-norm regularization. We present an efficient optimization algorithm to solve the proposed unsupervised model, and analyse the convergence and computational complexity of the algorithm theoretically.
  arXiv  Detail & Related papers  (2020-12-29T04:08:38Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)
• Learning Minimax Estimators via Online Learning [55.92459567732491]
  We consider the problem of designing minimax estimators for estimating parameters of a probability distribution. We construct an algorithm for finding a mixed-case Nash equilibrium.
  arXiv  Detail & Related papers  (2020-06-19T22:49:42Z)
• Asymptotic Analysis of an Ensemble of Randomly Projected Linear Discriminants [94.46276668068327]
  In [1], an ensemble of randomly projected linear discriminants is used to classify datasets. We develop a consistent estimator of the misclassification probability as an alternative to the computationally-costly cross-validation estimator. We also demonstrate the use of our estimator for tuning the projection dimension on both real and synthetic data.
  arXiv  Detail & Related papers  (2020-04-17T12:47:04Z)
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees [106.91654068632882]
  We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
  arXiv  Detail & Related papers  (2020-03-02T16:40:36Z)

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.