Search Results for author:
Found 37 papers, 2 papers with code
Unrolling SVT to obtain computationally efficient SVT for n-qubit quantum state tomography
Existing works focus on estimating the density matrix that represents the state, using a compressive sensing approach, with only fewer measurements than that required for a tomographically complete set, with the assumption that the true state has a low rank.
Introducing the Huber mechanism for differentially private low-rank matrix completion
We also propose using the Iteratively Re-Weighted Least Squares algorithm to complete low-rank matrices and study the performance of different noise mechanisms in both synthetic and real datasets.
Rotate the ReLU to implicitly sparsify deep networks
We show that this activation wherein the rotation is learned via training results in the elimination of those parameters/filters in the network which are not important for the task.
The robust way to stack and bag: the local Lipschitz way
Recent research has established that the local Lipschitz constant of a neural network directly influences its adversarial robustness.
How to boost autoencoders?
Autoencoders are a category of neural networks with applications in numerous domains and hence, improvement of their performance is gaining substantial interest from the machine learning community.
Binarized ResNet: Enabling Robust Automatic Modulation Classification at the resource-constrained Edge
The proposed MC method with RBLResNets has an adversarial accuracy of $87. 25\%$ over a wide range of SNRs, surpassing the robustness of all existing SOTA methods to the best of our knowledge.
BayesAoA: A Bayesian method for Computation Efficient Angle of Arrival Estimation
The proposed method achieves $92\%$ accuracy in a channel of noise variance $10^{-6}$ with $19. 3\%$ of the brute-force method's computation.
Cooperative 3D Beamforming for Small-Cell and Cell-Free 6G Systems
Three dimensional (3D) resource reuse is an important design requirement for the prospective 6G wireless communication systems.
Deep learned SVT: Unrolling singular value thresholding to obtain better MSE
Affine rank minimization problem is the generalized version of low rank matrix completion problem where linear combinations of the entries of a low rank matrix are observed and the matrix is estimated from these measurements.
Outage Probability Analysis of Uplink Cell-Free Massive MIMO Network with and without Pilot Contamination
The signal-to-interference-plus-noise ratio (SINR) of the CF-mMIMO system is approximated via a Log-normal distribution using a two-step moment matching method.
Dimensionality Reduction
Information Theory
Information Theory
On the Differentially Private Nature of Perturbed Gradient Descent
We consider the problem of empirical risk minimization given a database, using the gradient descent algorithm.
On the Asymptotic Performance Analysis of the k-th Best Link Selection over Non-identical Non-central Chi-square Fading Channels
This paper derives the asymptotic distribution of the normalized $k$-th maximum order statistics of a sequence of non-central chi-square random variables with non-identical non-centrality parameter.
Information Theory Information Theory
Airplane-Aided Integrated Next-Generation Networking
A high-rate yet low-cost air-to-ground (A2G) communication backbone is conceived for integrating the space and terrestrial network by harnessing the opportunistic assistance of the passenger planes or high altitude platforms (HAPs) as mobile base stations (BSs) and millimetre wave communication.
Understanding Learning Dynamics of Binary Neural Networks via Information Bottleneck
Compact neural networks are essential for affordable and power efficient deep learning solutions.
Intelligent Reflecting Surface Assisted Beam Index-Modulation for Millimeter Wave Communication
Millimeter wave communication is eminently suitable for high-rate wireless systems, which may be beneficially amalgamated with intelligent reflecting surfaces (IRS), relying on beam-index modulation.
Tune smarter not harder: A principled approach to tuning learning rates for shallow nets
Effective hyper-parameter tuning is essential to guarantee the performance that neural networks have come to be known for.
Green DetNet: Computation and Memory efficient DetNet using Smart Compression and Training
This paper introduces an incremental training framework for compressing popular Deep Neural Network (DNN) based unfolded multiple-input-multiple-output (MIMO) detection algorithms like DetNet.
Deep Reinforcement Learning based Blind mmWave MIMO Beam Alignment
Directional beamforming is a crucial component for realizing robust wireless communication systems using millimeter wave (mmWave) technology.
Generalized Residual Ratio Thresholding
Simultaneous orthogonal matching pursuit (SOMP) and block OMP (BOMP) are two widely used techniques for sparse support recovery in multiple measurement vector (MMV) and block sparse (BS) models respectively.
Beyond 5G: Leveraging Cell Free TDD Massive MIMO using Cascaded Deep learning
This paper deals with the calibration of Time Division Duplexing (TDD) reciprocity in an Orthogonal Frequency Division Multiplexing (OFDM) based Cell Free Massive MIMO system where the responses of the (Radio Frequency) RF chains render the end to end channel non-reciprocal, even though the physical wireless channel is reciprocal.
Subspace clustering without knowing the number of clusters: A parameter free approach
In this work, a parameter free method for subspace clustering is proposed, where the data points are clustered on the basis of the difference in statistical distribution of the angles subtended by the data points within a subspace and those by points belonging to different subspaces.
Concavifiability and convergence: necessary and sufficient conditions for gradient descent analysis
We show that concavifiability is a necessary and sufficient condition to satisfy the upper quadratic approximation which is key in proving that the objective function decreases after every gradient descent update.
Design of Communication Systems using Deep Learning: A Variational Inference Perspective
However, in communication systems, the receiver has to work with noise corrupted versions of transmit symbols.
High SNR Consistent Compressive Sensing Without Signal and Noise Statistics
The HSC results available in literature for support recovery techniques applicable to underdetermined linear regression models like least absolute shrinkage and selection operator (LASSO), orthogonal matching pursuit (OMP) etc.
Noise Statistics Oblivious GARD For Robust Regression With Sparse Outliers
Both inlier and outlier noise statistics are rarely known \textit{a priori} and this limits the efficient operation of many SRIRR algorithms.
Structured and Unstructured Outlier Identification for Robust PCA: A Non iterative, Parameter free Algorithm
Most of the existing methods for this model assumes either the knowledge of the dimension of the lower dimensional subspace or the fraction of outliers in the system.
Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit
Orthogonal matching pursuit (OMP) is a widely used algorithm for recovering sparse high dimensional vectors in linear regression models.
A Centralized Multi-stage Non-parametric Learning Algorithm for Opportunistic Spectrum Access
Owing to the ever-increasing demand in wireless spectrum, Cognitive Radio (CR) was introduced as a technique to attain high spectral efficiency.
Fast, Parameter free Outlier Identification for Robust PCA
Robust PCA, the problem of PCA in the presence of outliers has been extensively investigated in the last few years.
An aggregating strategy for shifting experts in discrete sequence prediction
We study how we can adapt a predictor to a non-stationary environment with advises from multiple experts.
Reinforcement learning techniques for Outer Loop Link Adaptation in 4G/5G systems
Wireless systems perform rate adaptation to transmit at highest possible instantaneous rates.
Spectrum Access In Cognitive Radio Using A Two Stage Reinforcement Learning Approach
Here, we propose an algorithm to not only select a channel for data transmission but also to predict how long the channel will remain unoccupied so that the time spent on channel sensing can be minimized.
Taming Non-stationary Bandits: A Bayesian Approach
We consider the multi armed bandit problem in non-stationary environments.
Signal and Noise Statistics Oblivious Sparse Reconstruction using OMP/OLS
Orthogonal matching pursuit (OMP) and orthogonal least squares (OLS) are widely used for sparse signal reconstruction in under-determined linear regression problems.
Tuning Free Orthogonal Matching Pursuit
We also produce a tuning free algorithm (TF-GARD) for efficient estimation in the presence of sparse outliers by extending the operating principle of TF-OMP to GARD.
High SNR Consistent Compressive Sensing
Further, the limited literature available on the high SNR consistency of subset selection procedures (SSPs) is applicable to linear regression with full rank measurement matrices only.
Rate Prediction and Selection in LTE systems using Modified Source Encoding Techniques
Finding the optimal depth of the frequency tree used for prediction is cast as a model order selection problem.
