Search Results for author: Daniel L. Pimentel-Alarcón

Found 7 papers, 1 papers with code

A Perturbation Bound on the Subspace Estimator from Canonical Projections

1 code implementation28 Jun 2022 Karan Srivastava, Daniel L. Pimentel-Alarcón

This paper derives a perturbation bound on the optimal subspace estimator obtained from a subset of its canonical projections contaminated by noise.

Clustering Matrix Completion

Mixed-Features Vectors and Subspace Splitting

no code implementations ICLR 2021 Alejandro Pimentel-Alarcón, Daniel L. Pimentel-Alarcón

Motivated by metagenomics, recommender systems, dictionary learning, and related problems, this paper introduces subspace splitting(SS): the task of clustering the entries of what we call amixed-features vector, that is, a vector whose subsets of coordinates agree with a collection of subspaces.

Clustering Dictionary Learning +1

Mixture Matrix Completion

no code implementations NeurIPS 2018 Daniel L. Pimentel-Alarcón

A more general model assumes that each column of X corresponds to one of several low-rank matrices.

Clustering Matrix Completion +1

A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion

no code implementations9 Mar 2015 Daniel L. Pimentel-Alarcón, Nigel Boston, Robert D. Nowak

Finite completability is the tipping point in LRMC, as a few additional samples of a finitely completable matrix guarantee its unique completability.

Low-Rank Matrix Completion

Deterministic Conditions for Subspace Identifiability from Incomplete Sampling

no code implementations2 Oct 2014 Daniel L. Pimentel-Alarcón, Robert D. Nowak, Nigel Boston

Consider a generic $r$-dimensional subspace of $\mathbb{R}^d$, $r<d$, and suppose that we are only given projections of this subspace onto small subsets of the canonical coordinates.

To lie or not to lie in a subspace

no code implementations24 Aug 2014 Daniel L. Pimentel-Alarcón

Give deterministic necessary and sufficient conditions to guarantee that if a subspace fits certain partially observed data from a union of subspaces, it is because such data really lies in a subspace.

Cannot find the paper you are looking for? You can Submit a new open access paper.