AIConfPaper
← Search

Richard G. Baraniuk

19 accepted papers

2025

Estimating the Number and Locations of Boundaries in Reverberant Environments with Deep Learning

Toros Arikan, Luca M. Chackalackal, Fatima Ahsan, Konrad Tittel, Andrew C. Singer, Gregory W. Wornell +1
ICASSP 2025accepted

Underwater acoustic environment estimation is a challenging but important task for remote sensing scenarios. Current estimation methods require high signal strength and a solution to the fragile echo labeling problem to be effective. In previous publications, we proposed a general deep learning-base…

Cited by 0Source ↗Scholar ↗
2024

Titan: Bringing the Deep Image Prior to Implicit Representations

Lorenzo Luzi, Daniel LeJeune, Ali Siahkoohi, Sina Alemohammad, Vishwanath Saragadam, Hossein Babaei +3
ICASSP 2024accepted

We study the interpolation capabilities of implicit neural representations (INRs) of images. In principle, INRs promise a number of advantages, such as continuous derivatives and arbitrary sampling, being freed from the restrictions of a raster grid. However, empirically, INRs have been observed to…

Cited by 0Source ↗Scholar ↗
2023

A Blessing of Dimensionality in Membership Inference through Regularization

Jasper Tan, Daniel LeJeune, Blake Mason, Hamid Javadi, Richard G. Baraniuk
AISTATS 2023poster

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier’s vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model can induce a privacy-utility trade-off: increasing the number…

Cited by 22Source ↗PDF ↗Scholar ↗
2023

A Probabilistic Framework for Pruning Transformers Via a Finite Admixture of Keys

Tan M. Nguyen, Tam Nguyen, Long Bui, Hai Do, Duy Khuong Nguyen, Dung D. Le +4
ICASSP 2023accepted

Pairwise dot product-based self-attention is key to the success of transformers which achieve state-of-the-art performance across a variety of applications in language and vision, but are costly to compute. It has been shown that most attention scores and keys in transformers are redundant and can b…

Cited by 0Source ↗Scholar ↗
2023

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries

Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard G. Baraniuk
CVPR 2023highlight

Current Deep Network (DN) visualization and interpretability methods rely heavily on data space visualizations such as scoring which dimensions of the data are responsible for their associated prediction or generating new data features or samples that best match a given DN unit or representation. In…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2023

WIRE: Wavelet Implicit Neural Representations

Vishwanath Saragadam, Daniel LeJeune, Jasper Tan, Guha Balakrishnan, Ashok Veeraraghavan, Richard G. Baraniuk
CVPR 2023poster

Implicit neural representations (INRs) have recently advanced numerous vision-related areas. INR performance depends strongly on the choice of activation function employed in its MLP network. A wide range of nonlinearities have been explored, but, unfortunately, current INRs designed to have high ac…

Cited by 163Source ↗PDF ↗code ↗Scholar ↗
2022

MINER: Multiscale Implicit Neural Representation

Vishwanath Saragadam, Jasper Tan, Guha Balakrishnan, Richard G. Baraniuk, Ashok Veeraraghavan
ECCV 2022poster

"We introduce a new neural signal model designed for efficient high-resolution representation of large-scale signals. The key innovation in our multiscale implicit neural representation (MINER) is an internal representation via a Laplacian pyramid, which provides a sparse multiscale decomposition of…

Cited by 87Source ↗PDF ↗Scholar ↗
2022

NFT-K: Non-Fungible Tangent Kernels

Sina Alemohammad, Hossein Babaei, C. J. Barberan, Naiming Liu, Lorenzo Luzi, Blake Mason +1
ICASSP 2022accepted

Deep neural networks have become essential for numerous applications due to their strong empirical performance such as vision, RL, and classification. Unfortunately, these networks are quite difficult to interpret, and this limits their applicability in settings where interpretability is important f…

Cited by 0Source ↗Scholar ↗
2022

No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds

Ahmed Imtiaz Humayun, Randall Balestriero, Anastasios Kyrillidis, Richard G. Baraniuk
ICASSP 2022accepted

Centroid based clustering methods such as k-means, k-medoids and k-centers are heavily applied as a go-to tool in exploratory data analysis. In many cases, those methods are used to obtain representative centroids of the data manifold for visualization or summarization of a dataset. Real world datas…

Cited by 0Source ↗Scholar ↗
2022

Unrolling Particles: Unsupervised Learning of Sampling Distributions

Fernando Gama, Nicolas Zilberstein, Richard G. Baraniuk, Santiago Segarra
ICASSP 2022accepted

Particle filtering is used to compute nonlinear estimates of complex systems. It samples trajectories from a chosen distribution and computes the estimate as a weighted average of them. Easy-to-sample distributions often lead to degenerate samples where only one trajectory carries all the weight, ne…

Cited by 0Source ↗Scholar ↗
2021

Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels

Sina Alemohammad, Hossein Babaei, Randall Balestriero, Matt Y. Cheung, Ahmed Imtiaz Humayun, Daniel LeJeune +5
ICASSP 2021accepted

High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation. Techniques abound to reduce the dimensionality of fixed-length sequences, yet these methods rarely generalize to variable-length sequences. To a…

Cited by 0Source ↗Scholar ↗
2020

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang, Xiaohan Chen +3
ICLR 2020spotlight

(Frankle & Carbin, 2019) shows that there exist winning tickets (small but critical subnetworks) for dense, randomly initialized networks, that can be trained alone to achieve comparable accuracies to the latter in a similar number of iterations. However, the identification of these winning tickets…

Cited by 310Source ↗code ↗Scholar ↗
2019

A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery

Ali Mousavi, Gautam Dasarathy, Richard G. Baraniuk
ICLR 2019poster

In this paper, we focus on two challenges which offset the promise of sparse signal representation, sensing, and recovery. First, real-world signals can seldom be described as perfectly sparse vectors in a known basis, and traditionally used random measurement schemes are seldom optimal for sensing…

Cited by 33Source ↗PDF ↗Scholar ↗
2019

Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks

Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Richard G. Baraniuk, Swarat Chaudhuri, Ankit B. Patel
ICLR 2019poster

We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specifically, we train a RNN on positive and negative examples from a regular language, and ask if there is a simple decoding function that maps states of thi…

Cited by 33Source ↗PDF ↗Scholar ↗
2018

Insense: Incoherent Sensor Selection for Sparse Signals

Amirali Aghazadeh, Mohammad Golbabaee, Andrew S. Lan, Richard G. Baraniuk
ICASSP 2018accepted

Sensor selection refers to the problem of intelligently selecting a small subset of a collection of available sensors to reduce the sensing cost while preserving signal acquisition performance. The majority of sensor selection algorithms find the subset of sensors that best recovers an arbitrary sig…

Cited by 0Source ↗Scholar ↗
2017

Contextual multi-armed bandit algorithms for personalized learning action selection

Indu Manickam, Andrew S. Lan, Richard G. Baraniuk
ICASSP 2017accepted

Optimizing the selection of learning resources and practice questions to address each individual student's needs has the potential to improve students' learning efficiency. In this paper, we study the problem of selecting a personalized learning action for each student (e.g. watching a lecture video…

Cited by 0Source ↗Scholar ↗
2017

Flat focus: depth of field analysis for the FlatCam lensless imaging system

Jasper Tan, Vivek Boominathan, Ashok Veeraraghavan, Richard G. Baraniuk
ICASSP 2017accepted

Lensless imaging systems, such as the recently proposed FlatCam, offer numerous advantages over lens-based systems such as a thin form-factor, low cost, and higher light throughput. However, little work has been done in analyzing these systems' depth of field characteristics. A depth-dependent calib…

Cited by 0Source ↗Scholar ↗