276 citations · 300 across the 10 of their papers we have counts for
12 papers
Spectral Gap Bounds for Langevin Dynamics in Mixed Spherical Spin Glasses
Masoud Badiei Khuzani
We prove lower bounds on the relaxation time of Langevin dynamics for mixed spherical spin glasses with even mixture , under a one-step-repli…
A Coulomb Particle Model for Learning Kernel Attention in Transformers
Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam +2
Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution. We propose a particle-based m…
A Mean-Field Theory for Learning the Schönberg Measure of Radial Basis Functions
Masoud Badiei Khuzani, Yinyu Ye, Sandy Napel +1
We develop and analyze a projected particle Langevin optimization method to learn the distribution in the Schönberg integral representation of the radial basis functions from train…
Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications
Hyunseok Seo, Masoud Badiei Khuzani, Varun Vasudevan +5
In recent years, significant progress has been made in developing more accurate and efficient machine learning algorithms for segmentation of medical and natural images. In this re…
A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
Masoud Badiei Khuzani, Liyue Shen, Shahin Shahrampour +1
We propose a novel supervised learning method to optimize the kernel in the maximum mean discrepancy generative adversarial networks (MMD GANs), and the kernel support vector machi…
On Sample Complexity of Projection-Free Primal-Dual Methods for Learning Mixture Policies in Markov Decision Processes
Masoud Badiei Khuzani, Varun Vasudevan, Hongyi Ren +1
We study the problem of learning policy of an infinite-horizon, discounted cost, Markov decision process (MDP) with a large number of states. We compute the actions of a policy tha…
A Distributionally Robust Optimization Method for Adversarial Multiple Kernel Learning
Masoud Badiei Khuzani, Hongyi Ren, Md Tauhidul Islam +1
We propose a novel data-driven method to learn a mixture of multiple kernels with random features that is certifiabaly robust against adverserial inputs. Specifically, we consider…
Stochastic Primal-Dual Method on Riemannian Manifolds with Bounded Sectional Curvature
Masoud Badiei Khuzani, Na Li
We study a stochastic primal-dual method for constrained optimization over Riemannian manifolds with bounded sectional curvature. We prove non-asymptotic convergence to the optimal…
Distributed Regularized Primal-Dual Method: Convergence Analysis and Trade-offs
Masoud Badiei Khuzani, Na Li
We study deterministic and stochastic primal-dual sub-gradient algorithms for distributed optimization of a separable objective function with global inequality constraints. In both…
On Lossy Joint Source-Channel Coding In Energy Harvesting Communication Systems
Meysam Shahrbaf Motlagh, Masoud Badiei Khuzani, Patrick Mitran
We study the problem of lossy joint source-channel coding in a single-user energy harvesting communication system with causal energy arrivals and the energy storage unit may have l…
Time-Asynchronous Gaussian Multiple Access Relay Channel with Correlated Sources
Hamidreza Ebrahimzadeh Saffar, Masoud Badiei Khuzani, Patrick Mitran
We study the transmission of a set of correlated sources over a Gaussian multiple access relay channel with time asynchronism between the encoders. We assume tha…
On online energy harvesting in multiple access communication systems
Masoud Badiei Khuzani, Patrick Mitran
We investigate performance limits of a multiple access communication system with energy harvesting nodes where the utility function is taken to be the long-term average sum-through…