35 citations · 53 across the 14 of their papers we have counts for
17 papers
Interference Beyond Geometry in Concept Extraction
Valérie Costa, Bahareh Tolooshams
Interference is commonly treated as geometric overlap between learned features. We introduce effective interference, which combines feature geometry and code statistics to capture…
Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit
Valérie Costa, Thomas Fel, Ekdeep Singh Lubana +2
Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural…
From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
Valérie Costa, Thomas Fel, Ekdeep Singh Lubana +2
Motivated by the hypothesis that neural network representations encode abstract, interpretable features as linearly accessible, approximately orthogonal directions, sparse autoenco…
Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models
Alexander Lin, Bahareh Tolooshams, Yves Atchadé +1
Latent Gaussian models have a rich history in statistics and machine learning, with applications ranging from factor analysis to compressed sensing to time series analysis. The cla…
Unrolled Compressed Blind-Deconvolution
Bahareh Tolooshams, Satish Mulleti, Demba Ba +1
The problem of sparse multichannel blind deconvolution (S-MBD) arises frequently in many engineering applications such as radar/sonar/ultrasound imaging. To reduce its computationa…
A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networks
Bahareh Tolooshams, Kazuhito Koishida
Deep learning-based speech enhancement has shown unprecedented performance in recent years. The most popular mono speech enhancement frameworks are end-to-end networks mapping the…
Stable and Interpretable Unrolled Dictionary Learning
Bahareh Tolooshams, Demba Ba
The dictionary learning problem, representing data as a combination of a few atoms, has long stood as a popular method for learning representations in statistics and signal process…
Gaussian Process Convolutional Dictionary Learning
Andrew H. Song, Bahareh Tolooshams, Demba Ba
Convolutional dictionary learning (CDL), the problem of estimating shift-invariant templates from data, is typically conducted in the absence of a prior/structure on the templates.…
On the convergence of group-sparse autoencoders
Emmanouil Theodosis, Bahareh Tolooshams, Pranay Tankala +2
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 g…
Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution
Bahareh Tolooshams, Satish Mulleti, Demba Ba +1
We propose a learned-structured unfolding neural network for the problem of compressive sparse multichannel blind-deconvolution. In this problem, each channel's measurements are gi…
Discriminative reconstruction via simultaneous dense and sparse coding
Abiy Tasissa, Emmanouil Theodosis, Bahareh Tolooshams +1
Discriminative features extracted from the sparse coding model have been shown to perform well for classification. Recent deep learning architectures have further improved reconstr…
Channel-Attention Dense U-Net for Multichannel Speech Enhancement
Bahareh Tolooshams, Ritwik Giri, Andrew H. Song +2
Supervised deep learning has gained significant attention for speech enhancement recently. The state-of-the-art deep learning methods perform the task by learning a ratio/binary ma…
RandNet: deep learning with compressed measurements of images
Thomas Chang, Bahareh Tolooshams, Demba Ba
Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these me…
Convolutional Dictionary Learning in Hierarchical Networks
Javier Zazo, Bahareh Tolooshams, Demba Ba
Filter banks are a popular tool for the analysis of piecewise smooth signals such as natural images. Motivated by the empirically observed properties of scale and detail coefficien…
Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
Bahareh Tolooshams, Andrew H. Song, Simona Temereanca +1
We introduce a class of auto-encoder neural networks tailored to data from the natural exponential family (e.g., count data). The architectures are inspired by the problem of learn…
Deep Residual Autoencoders for Expectation Maximization-inspired Dictionary Learning
Bahareh Tolooshams, Sourav Dey, Demba Ba
We introduce a neural-network architecture, termed the constrained recurrent sparse autoencoder (CRsAE), that solves convolutional dictionary learning problems, thus establishing a…
Scalable Convolutional Dictionary Learning with Constrained Recurrent Sparse Auto-encoders
Bahareh Tolooshams, Sourav Dey, Demba Ba
Given a convolutional dictionary underlying a set of observed signals, can a carefully designed auto-encoder recover the dictionary in the presence of noise? We introduce an auto-e…