Justin Romberg

Finite-Time Analysis of Decentralized Stochastic Approximation with Applications in Multi-Agent and Multi-Task Learning

Stochastic approximation, a data-driven approach for finding the fixed p...
10/28/2020 ∙ by Sihan Zeng, et al. ∙ 0 ∙ share

read it
Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification

The attention mechanism has demonstrated superior performance for infere...
06/15/2020 ∙ by Rakshith S Srinivasa, et al. ∙ 0 ∙ share

read it
Sample complexity and effective dimension for regression on manifolds

We consider the theory of regression on a manifold using reproducing ker...
06/13/2020 ∙ by Andrew McRae, et al. ∙ 0 ∙ share

read it
A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning

We develop a mathematical framework for solving multi-task reinforcement...
06/08/2020 ∙ by Sihan Zeng, et al. ∙ 4 ∙ share

read it
Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness

Motivated by broad applications in reinforcement learning and machine le...
03/24/2020 ∙ by Thinh T. Doan, et al. ∙ 0 ∙ share

read it
Localized sketching for matrix multiplication and ridge regression

We consider sketched approximate matrix multiplication and ridge regress...
03/20/2020 ∙ by Rakshith S Srinivasa, et al. ∙ 0 ∙ share

read it
Hardware-aware Pruning of DNNs using LFSR-Generated Pseudo-Random Indices

Deep neural networks (DNNs) have been emerged as the state-of-the-art al...
11/09/2019 ∙ by Foroozan Karimzadeh, et al. ∙ 0 ∙ share

read it
Phase Retrieval of Low-Rank Matrices by Anchored Regression

We study the low-rank phase retrieval problem, where we try to recover a...
10/25/2019 ∙ by Kiryung Lee, et al. ∙ 0 ∙ share

read it
Convex Programming for Estimation in Nonlinear Recurrent Models

We propose a formulation for nonlinear recurrent models that includes si...
08/26/2019 ∙ by Sohail Bahmani, et al. ∙ 0 ∙ share

read it
Finite-Time Performance of Distributed Temporal Difference Learning with Linear Function Approximation

We study the policy evaluation problem in multi-agent reinforcement lear...
07/25/2019 ∙ by Thinh T. Doan, et al. ∙ 0 ∙ share

read it
Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variables

Deep learning models have significantly improved the visual quality and ...
02/19/2019 ∙ by Shaojie Xu, et al. ∙ 0 ∙ share

read it
Appearance-based Gesture recognition in the compressed domain

We propose a novel appearance-based gesture recognition algorithm using ...
02/19/2019 ∙ by Shaojie Xu, et al. ∙ 0 ∙ share

read it
Trading beams for bandwidth: Imaging with randomized beamforming

We study the problem of actively imaging a range-limited far-field scene...
01/31/2019 ∙ by Rakshith Sharma Srinivasa, et al. ∙ 0 ∙ share

read it
Fast Convex Pruning of Deep Neural Networks

We develop a fast, tractable technique called Net-Trim for simplifying a...
06/17/2018 ∙ by Alireza Aghasi, et al. ∙ 0 ∙ share

read it
ROAST: Rapid Orthogonal Approximate Slepian Transform

In this paper, we provide a Rapid Orthogonal Approximate Slepian Transfo...
12/13/2017 ∙ by Zhihui Zhu, et al. ∙ 0 ∙ share

read it
Solving Equations of Random Convex Functions via Anchored Regression

We consider the question of estimating a solution to a system of equatio...
02/17/2017 ∙ by Sohail Bahmani, et al. ∙ 0 ∙ share

read it
Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee

We introduce and analyze a new technique for model reduction for deep ne...
11/16/2016 ∙ by Alireza Aghasi, et al. ∙ 0 ∙ share

read it
Phase Retrieval Meets Statistical Learning Theory: A Flexible Convex Relaxation

We propose a flexible convex relaxation for the phase retrieval problem ...
10/13/2016 ∙ by Sohail Bahmani, et al. ∙ 0 ∙ share

read it
A Light-powered, Always-On, Smart Camera with Compressed Domain Gesture Detection

In this paper we propose an energy-efficient camera-based gesture recogn...
05/26/2016 ∙ by Anvesha A, et al. ∙ 0 ∙ share

read it
Sweep Distortion Removal from THz Images via Blind Demodulation

Heavy sweep distortion induced by alignments and inter-reflections of la...
03/29/2016 ∙ by Alireza Aghasi, et al. ∙ 0 ∙ share

read it
Learning Shapes by Convex Composition

We present a mathematical and algorithmic scheme for learning the princi...
02/23/2016 ∙ by Alireza Aghasi, et al. ∙ 0 ∙ share

read it
Sparse Recovery of Streaming Signals Using L1-Homotopy

Most of the existing methods for sparse signal recovery assume a static ...
06/14/2013 ∙ by M. Salman Asif, et al. ∙ 0 ∙ share

read it
Fast and Accurate Algorithms for Re-Weighted L1-Norm Minimization

To recover a sparse signal from an underdetermined system, we often solv...
08/03/2012 ∙ by M. Salman Asif, et al. ∙ 0 ∙ share

read it

Justin Romberg

Featured Co-authors

Ramesh Raskar

Jimeng Sun

Cao Xiao

Lam M. Nguyen

Arijit Raychowdhury

Zhihui Zhu

M. Salman Asif

Mark A. Davenport

Michael B. Wakin

Alireza Aghasi

Sohail Bahmani

Finite-Time Analysis of Decentralized Stochastic Approximation with Applications in Multi-Agent and Multi-Task Learning

Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification

Sample complexity and effective dimension for regression on manifolds

A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning

Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness

Localized sketching for matrix multiplication and ridge regression

Hardware-aware Pruning of DNNs using LFSR-Generated Pseudo-Random Indices

Phase Retrieval of Low-Rank Matrices by Anchored Regression

Convex Programming for Estimation in Nonlinear Recurrent Models

Finite-Time Performance of Distributed Temporal Difference Learning with Linear Function Approximation

Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variables

Appearance-based Gesture recognition in the compressed domain

Trading beams for bandwidth: Imaging with randomized beamforming

Fast Convex Pruning of Deep Neural Networks

ROAST: Rapid Orthogonal Approximate Slepian Transform

Solving Equations of Random Convex Functions via Anchored Regression

Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee

Phase Retrieval Meets Statistical Learning Theory: A Flexible Convex Relaxation

A Light-powered, Always-On, Smart Camera with Compressed Domain Gesture Detection

Sweep Distortion Removal from THz Images via Blind Demodulation

Learning Shapes by Convex Composition

Sparse Recovery of Streaming Signals Using L1-Homotopy

Fast and Accurate Algorithms for Re-Weighted L1-Norm Minimization