18 citations · 69 across the 20 of their papers we have counts for
23 papers
Multi-Agent Adversarial Attacks for Multi-Channel Communications
Juncheng Dong, Suya Wu, Mohammadreza Sultani +1
Recently Reinforcement Learning (RL) has been applied as an anti-adversarial remedy in wireless communication networks. However, studying the RL-based approaches from the adversary…
On The Energy Statistics of Feature Maps in Pruning of Neural Networks with Skip-Connections
Mohammadreza Soltani, Suya Wu, Yuerong Li +2
We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip connections, based on measuring the statistical dependency of hidden layers and…
Toward Data-Driven STAP Radar
Shyam Venkatasubramanian, Chayut Wongkamthong, Mohammadreza Soltani +5
Using an amalgamation of techniques from classical radar, computer vision, and deep learning, we characterize our ongoing data-driven approach to space-time adaptive processing (ST…
Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions
Juncheng Dong, Simiao Ren, Yang Deng +5
Numerous physical systems are described by ordinary or partial differential equations whose solutions are given by holomorphic or meromorphic functions in the complex domain. In ma…
Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
Cat P. Le, Juncheng Dong, Mohammadreza Soltani +1
We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartit…
A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling
Anna K. Yanchenko, Mohammadreza Soltani, Robert J. Ravier +2
Understanding the features learned by deep models is important from a model trust perspective, especially as deep systems are deployed in the real world. Most recent approaches for…
Fisher Task Distance and Its Application in Neural Architecture Search
Cat P. Le, Mohammadreza Soltani, Juncheng Dong +1
We formulate an asymmetric (or non-commutative) distance between tasks based on Fisher Information Matrices, called Fisher task distance. This distance represents the complexity of…
Improved Automated Machine Learning from Transfer Learning
Cat P. Le, Mohammadreza Soltani, Robert Ravier +1
In this paper, we propose a neural architecture search framework based on a similarity measure between some baseline tasks and a target task. We first define the notion of the task…
Task-Aware Neural Architecture Search
Cat P. Le, Mohammadreza Soltani, Robert Ravier +1
The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than t…
Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery
Minsu Cho, Mohammadreza Soltani, Chinmay Hegde
In this paper, we study two important problems in the automated design of neural networks -- Hyper-parameter Optimization (HPO), and Neural Architecture Search (NAS) -- through the…
GeoStat Representations of Time Series for Fast Classification
Robert J. Ravier, Mohammadreza Soltani, Miguel Simões +2
Recent advances in time series classification have largely focused on methods that either employ deep learning or utilize other machine learning models for feature extraction. Thou…
Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows
Chris Cannella, Mohammadreza Soltani, Vahid Tarokh
We introduce Projected Latent Markov Chain Monte Carlo (PL-MCMC), a technique for sampling from the high-dimensional conditional distributions learned by a normalizing flow. We pro…
Perception-Distortion Trade-off with Restricted Boltzmann Machines
Chris Cannella, Jie Ding, Mohammadreza Soltani +1
In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy functio…
One-Shot Neural Architecture Search via Compressive Sensing
Minsu Cho, Mohammadreza Soltani, Chinmay Hegde
Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time…
Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing
Mohammadreza Soltani, Swayambhoo Jain, Abhinav Sambasivan
Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly as…
Fast Low-Rank Matrix Estimation without the Condition Number
Mohammadreza Soltani, Chinmay Hegde
In this paper, we study the general problem of optimizing a convex function over the set of matrices, subject to rank constraints on . However, existing firs…
Reconstruction from Periodic Nonlinearities, With Applications to HDR Imaging
Viraj Shah, Mohammadreza Soltani, Chinmay Hegde
We consider the problem of reconstructing signals and images from periodic nonlinearities. For such problems, we design a measurement scheme that supports efficient reconstruction;…
Demixing Structured Superposition Signals from Periodic and Aperiodic Nonlinear Observations
Mohammadreza Soltani, Chinmay Hegde
We consider the demixing problem of two (or more) structured high-dimensional vectors from a limited number of nonlinear observations where this nonlinearity is due to either a per…
Fast Algorithms for Learning Latent Variables in Graphical Models
Mohammadreza Soltani, Chinmay Hegde
We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the…
Improved Algorithms for Matrix Recovery from Rank-One Projections
Mohammadreza Soltani, Chinmay Hegde
We consider the problem of estimation of a low-rank matrix from a limited number of noisy rank-one projections. In particular, we propose two fast, non-convex \emph{proper} algorit…
Iterative Thresholding for Demixing Structured Superpositions in High Dimensions
Mohammadreza Soltani, Chinmay Hegde
We consider the demixing problem of two (or more) high-dimensional vectors from nonlinear observations when the number of such observations is far less than the ambient dimension o…
Stable Recovery Of Sparse Vectors From Random Sinusoidal Feature Maps
Mohammadreza Soltani, Chinmay Hegde
Random sinusoidal features are a popular approach for speeding up kernel-based inference in large datasets. Prior to the inference stage, the approach suggests performing dimension…
Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations
Mohammadreza Soltani, Chinmay Hegde
We study the problem of demixing a pair of sparse signals from noisy, nonlinear observations of their superposition. Mathematically, we consider a nonlinear signal observation mode…