289 citations · 607 across the 31 of their papers we have counts for
36 papers
SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
Mohammad Partohaghighi, Roummel Marcia
Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, but its high-variance updates…
Deep Learning under Fractional-Order Differential Privacy
Mohammad Partohaghighi, Roummel Marcia
Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation,…
Fractional-Order Federated Learning
Mohammad Partohaghighi, Roummel Marcia, YangQuan Chen
Federated learning (FL) allows remote clients to train a global model collaboratively while protecting client privacy. Despite its privacy-preserving benefits, FL has significant d…
Fractional Order Federated Learning for Battery Electric Vehicle Energy Consumption Modeling
Mohammad Partohaghighi, Roummel Marcia, Bruce J. West +1
Federated learning on connected electric vehicles (BEVs) faces severe instability due to intermittent connectivity, time-varying client participation, and pronounced client-to-clie…
Roughness-Informed Federated Learning
Mohammad Partohaghighi, Roummel Marcia, Bruce J. West +1
Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, yet faces challenges in non-independent and identically distr…
When Gradient Clipping Becomes a Control Mechanism for Differential Privacy in Deep Learning
Mohammad Partohaghighi, Roummel Marcia, Bruce J. West +1
Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is…
Statistical Roughness-Informed Machine Unlearning
Mohammad Partohaghighi, Roummel Marcia, Bruce J. West +1
Machine unlearning aims to remove the influence of a designated forget set from a trained model while preserving utility on the retained data. In modern deep networks, approximate…
More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems
Mohammad Partohaghighi, Roummel Marcia, YangQuan Chen
Fractional-order stochastic gradient descent (FOSGD) leverages fractional exponents to capture long-memory effects in optimization. However, its utility is often limited by the dif…
Effective Dimension Aware Fractional-Order Stochastic Gradient Descent for Convex Optimization Problems
Mohammad Partohaghighi, Roummel Marcia, YangQuan Chen
Fractional-order stochastic gradient descent (FOSGD) leverages fractional exponents to capture long-memory effects in optimization. However, its utility is often limited by the dif…
Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization
Aditya Ranganath, Mukesh Singhal, Roummel Marcia
Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-…
Sparse Signal Reconstruction for Overdispersed Low-photon Count Biomedical Imaging Using Total Variation
Yu Lu, Roummel F. Marcia
The negative binomial model, which generalizes the Poisson distribution model, can be found in applications involving low-photon signal recovery, including medical imaging. Recent…
Alternating Direction Method of Multipliers for Negative Binomial Model with The Weighted Difference of Anisotropic and Isotropic Total Variation
Yu Lu, Kevin Bui, Roummel F. Marcia
In many applications such as medical imaging, the measurement data represent counts of photons hitting a detector. Such counts in low-photon settings are often modeled using a Pois…
Negative Binomial Matrix Completion
Yu Lu, Kevin Bui, Roummel F. Marcia
Matrix completion focuses on recovering missing or incomplete information in matrices. This problem arises in various applications, including image processing and network analysis.…
Shape-Changing Trust-Region Methods Using Multipoint Symmetric Secant Matrices
Johannes J. Brust, Jennifer B. Erway, Roummel F. Marcia
In this work, we consider methods for large-scale and nonconvex unconstrained optimization. We propose a new trust-region method whose subproblem is defined using a so-called "shap…
Large-scale Optimization with Linear Equality Constraints using Reduced Compact Representation
Johannes J. Brust, Roummel F. Marcia, Cosmin G. Petra +1
For optimization problems with linear equality constraints, we prove that the (1,1) block of the inverse KKT matrix remains unchanged when projected onto the nullspace of the const…
Quasi-Newton Optimization Methods For Deep Learning Applications
Jacob Rafati, Roummel F. Marcia
Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machin…
Deep Reinforcement Learning via L-BFGS Optimization
Jacob Rafati, Roummel F. Marcia
Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement…
Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations
Jennifer B. Erway, Joshua Griffin, Roummel F. Marcia +1
Machine learning (ML) problems are often posed as highly nonlinear and nonconvex unconstrained optimization problems. Methods for solving ML problems based on stochastic gradient d…
A Dense Initialization for Limited-Memory Quasi-Newton Methods
Johannes Brust, Oleg Burdakov, Jennifer B. Erway +1
We consider a family of dense initializations for limited-memory quasi-Newton methods. The proposed initialization exploits an eigendecomposition-based separation of the full space…
Compact representation of the full Broyden class of quasi-Newton updates
Omar DeGuchy, Jennifer B. Erway, Roummel F. Marcia
In this paper, we present the compact representation for matrices belonging to the the Broyden class of quasi-Newton updates, where each update may be either rank-one or rank-two.…
Nonconvex Regularization Based Sparse Recovery and Demixing with Application to Color Image Inpainting
Fei Wen, Lasith Adhikari, Ling Pei +3
This work addresses the recovery and demixing problem of signals that are sparse in some general dictionary. Involved applications include source separation, image inpainting, supe…
Algorithm XXX: SC-SR1: Matlab software for solving shape-changing L-SR1 trust-region subproblems
Johannes Brust, Oleg Burdakov, Jennifer B. Erway +2
We present a MATLAB implementation of the symmetric rank-one (SC-SR1) method that solves trust-region. subproblems when a limited-memory symmetric rank-one (L-SR1) matrix is used i…
Trust-Region Methods for Sparse Relaxation
Lasith Adhikari, Jennifer B. Erway, Shelby Lockhart +1
In this paper, we solve the l2-l1 sparse recovery problem by transforming the objective function of this problem into an unconstrained differentiable function and apply a limited-m…
On solving large-scale limited-memory quasi-Newton equations
Jennifer B. Erway, Roummel F. Marcia
We consider the problem of solving linear systems of equations arising with limited-memory members of the restricted Broyden class of updates and the symmetric rank-one (SR1) updat…