Alternating minimization algorithm with initialization analysis for r-local and k-sparse unlabeled sensing

• URL: http://arxiv.org/abs/2211.07621v2
• Date: Thu, 12 Dec 2024 01:34:09 GMT
• Title: Alternating minimization algorithm with initialization analysis for r-local and k-sparse unlabeled sensing
• Authors: Ahmed Abbasi, Shuchin Aeron, Abiy Tasissa,
• Abstract summary: Experimental results show that our algorithm is fast, applicable to both permutation models, and robust to choice of measurement matrix. We also test our algorithm on several real datasets for the linked linear regression problem and show superior performance compared to baseline methods.
• Score: 13.433637831618007
• License:
• Abstract: Unlabeled sensing is a linear inverse problem with permuted measurements. We propose an alternating minimization (AltMin) algorithm with a suitable initialization for two widely considered permutation models: partially shuffled/$k$-sparse permutations and $r$-local/block diagonal permutations. Key to the performance of the AltMin algorithm is the initialization. For the exact unlabeled sensing problem, assuming either a Gaussian measurement matrix or a sub-Gaussian signal, we bound the initialization error in terms of the number of blocks $s$ and the number of shuffles $k$. Experimental results show that our algorithm is fast, applicable to both permutation models, and robust to choice of measurement matrix. We also test our algorithm on several real datasets for the linked linear regression problem and show superior performance compared to baseline methods.

Related papers

• A Sample Efficient Alternating Minimization-based Algorithm For Robust Phase Retrieval [56.67706781191521]
  In this work, we present a robust phase retrieval problem where the task is to recover an unknown signal. Our proposed oracle avoids the need for computationally spectral descent, using a simple gradient step and outliers.
  arXiv  Detail & Related papers  (2024-09-07T06:37:23Z)
• Noise misleads rotation invariant algorithms on sparse targets [0.0]
  We show that the class of rotation invariant algorithms are suboptimal for learning sparse linear problems. We prove this via a lower bound for the Bayes optimal algorithm on a rotationally symmetrized problem. We then prove much lower upper bounds on the same problem for simple non-rotation invariant algorithms.
  arXiv  Detail & Related papers  (2024-03-05T06:25:19Z)
• Learning the Positions in CountSketch [49.57951567374372]
  We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem. In this work, we propose the first learning-based algorithms that also optimize the locations of the non-zero entries.
  arXiv  Detail & Related papers  (2023-06-11T07:28:35Z)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization [5.900674344455754]
  We show a technique for estimating properties of a rank random matrix with i.i.d. We show sharp convergence guarantees exact recovery in a single step. Our analysis also exposes several other properties of this problem.
  arXiv  Detail & Related papers  (2022-07-20T05:31:05Z)
• Randomly Initialized Alternating Least Squares: Fast Convergence for Matrix Sensing [9.264464791978362]
  We show that Alternating Least Squares (ALS) converges to the true solution with $varepsilon$-accuracy in $O(log n + log (1/varepsilon)) $ iterations. Key to our proof is the observation that the trajectory of the ALS iterates only depends very mildly on certain entries of the random measurement matrices.
  arXiv  Detail & Related papers  (2022-04-25T08:55:38Z)
• PROMPT: Parallel Iterative Algorithm for $\ell_{p}$ norm linear regression via Majorization Minimization with an application to semi-supervised graph learning [0.0]
  We consider the problem of $ell_p$ norm linear regression, which has several applications such as in sparse recovery, data clustering, and semi-supervised learning. We propose an iterative algorithm : Parallel IteRative AlgOrithM for $ell_P$ norm regression via MajorizaTion Minimization (PROMPT)
  arXiv  Detail & Related papers  (2021-10-23T10:19:11Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)
• Gradient Free Minimax Optimization: Variance Reduction and Faster Convergence [120.9336529957224]
  In this paper, we denote the non-strongly setting on the magnitude of a gradient-free minimax optimization problem. We show that a novel zeroth-order variance reduced descent algorithm achieves the best known query complexity.
  arXiv  Detail & Related papers  (2020-06-16T17:55:46Z)
• Efficient Algorithms for Multidimensional Segmented Regression [42.046881924063044]
  We study the fundamental problem of fixed design em multidimensional regression. We provide the first sample and computationally efficient algorithm for this problem in any fixed dimension. Our algorithm relies on a simple merging iterative approach, which is novel in the multidimensional setting.
  arXiv  Detail & Related papers  (2020-03-24T19:39:34Z)
• Optimal Randomized First-Order Methods for Least-Squares Problems [56.05635751529922]
  This class of algorithms encompasses several randomized methods among the fastest solvers for least-squares problems. We focus on two classical embeddings, namely, Gaussian projections and subsampled Hadamard transforms. Our resulting algorithm yields the best complexity known for solving least-squares problems with no condition number dependence.
  arXiv  Detail & Related papers  (2020-02-21T17:45:32Z)

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.