Search Results for author: Abiy Tasissa

Found 16 papers, 5 papers with code

Clustering Inductive Biases with Unrolled Networks

no code implementations30 Nov 2023 Jonathan Huml, Abiy Tasissa, Demba Ba

We propose an autoencoder architecture (WLSC) whose latent representations are implicitly, locally organized for spectral clustering through a Laplacian quadratic form of a bipartite graph, which generates a diverse set of artificial receptive fields that match primate data in V1 as faithfully as recent contrastive frameworks like Local Low Dimensionality, or LLD \citep{lld} that discard sparse dictionary learning.

Clustering Dictionary Learning +1

A Nyström method with missing distances

no code implementations29 Nov 2023 Samuel Lichtenberg, Abiy Tasissa

First, we establish a relationship between the columns of the anchor-mobile block in the distance matrix and the columns of the corresponding block in the Gram matrix via a graph Laplacian.

RACH-Space: Reconstructing Adaptive Convex Hull Space with Applications in Weak Supervision

no code implementations10 Jul 2023 Woojoo Na, Abiy Tasissa

We introduce RACH-Space, an algorithm for labelling unlabelled data in weakly supervised learning, given incomplete, noisy information about the labels.

Ensemble Learning Weakly-supervised Learning

A dual basis approach to multidimensional scaling: spectral analysis and graph regularity

no code implementations10 Mar 2023 Samuel Lichtenberg, Abiy Tasissa

A central result in CMDS connects the squared Euclidean matrix to a Gram matrix derived from the set of points.

Sparse, Geometric Autoencoder Models of V1

no code implementations22 Feb 2023 Jonathan Huml, Abiy Tasissa, Demba Ba

The classical sparse coding model represents visual stimuli as a linear combination of a handful of learned basis functions that are Gabor-like when trained on natural image data.

Dictionary Learning

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

no code implementations14 Nov 2022 Ahmed Abbasi, Abiy Tasissa, Shuchin Aeron

The unlabeled sensing problem is to recover an unknown signal from permuted linear measurements.

Geometric Sparse Coding in Wasserstein Space

no code implementations21 Oct 2022 Marshall Mueller, Shuchin Aeron, James M. Murphy, Abiy Tasissa

We show this approach leads to sparse representations in Wasserstein space and addresses the problem of non-uniqueness of barycentric representation.

Dictionary Learning

Measure Estimation in the Barycentric Coding Model

1 code implementation28 Jan 2022 Matthew Werenski, Ruijie Jiang, Abiy Tasissa, Shuchin Aeron, James M. Murphy

Our first main result leverages the Riemannian geometry of Wasserstein-2 space to provide a procedure for recovering the barycentric coordinates as the solution to a quadratic optimization problem assuming access to the true reference measures.

r-local sensing: Improved algorithm and applications

2 code implementations26 Oct 2021 Ahmed Ali Abbasi, Abiy Tasissa, Shuchin Aeron

The unlabeled sensing problem is to solve a noisy linear system of equations under unknown permutation of the measurements.

Weighed $\ell_1$ on the simplex: Compressive sensing meets locality

no code implementations28 Apr 2021 Abiy Tasissa, Pranay Tankala, Demba Ba

Sparse manifold learning algorithms combine techniques in manifold learning and sparse optimization to learn features that could be utilized for downstream tasks.

Compressive Sensing

On the convergence of group-sparse autoencoders

no code implementations13 Feb 2021 Emmanouil Theodosis, Bahareh Tolooshams, Pranay Tankala, Abiy Tasissa, Demba Ba

Recent approaches in the theoretical analysis of model-based deep learning architectures have studied the convergence of gradient descent in shallow ReLU networks that arise from generative models whose hidden layers are sparse.

Clustering

Deep Diffusion Processes for Active Learning of Hyperspectral Images

1 code implementation8 Jan 2021 Abiy Tasissa, Duc Nguyen, James Murphy

A method for active learning of hyperspectral images (HSI) is proposed, which combines deep learning with diffusion processes on graphs.

Active Learning

K-Deep Simplex: Deep Manifold Learning via Local Dictionaries

1 code implementation3 Dec 2020 Pranay Tankala, Abiy Tasissa, James M. Murphy, Demba Ba

We theoretically analyze the proposed program by relating the weighted $\ell_1$ penalty in KDS to a weighted $\ell_0$ program.

Clustering Deep Clustering +2

Towards improving discriminative reconstruction via simultaneous dense and sparse coding

no code implementations16 Jun 2020 Abiy Tasissa, Emmanouil Theodosis, Bahareh Tolooshams, Demba Ba

We propose a novel dense and sparse coding model that integrates both representation capability and discriminative features.

Compressive Sensing Dictionary Learning

R-local unlabeled sensing: A novel graph matching approach for multiview unlabeled sensing under local permutations

1 code implementation14 Nov 2019 Ahmed Abbasi, Abiy Tasissa, Shuchin Aeron

Unlabeled sensing is a linear inverse problem where the measurements are scrambled under an unknown permutation leading to loss of correspondence between the measurements and the rows of the sensing matrix.

Graph Matching

Exact Reconstruction of Euclidean Distance Geometry Problem Using Low-rank Matrix Completion

no code implementations12 Apr 2018 Abiy Tasissa, Rongjie Lai

In this paper, this minimization program is recast as a matrix completion problem of a low-rank $r$ Gram matrix with respect to a suitable basis.

Low-Rank Matrix Completion

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