Search Results for author:
Found 10 papers, 0 papers with code
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.
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.
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.
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.
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.
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.
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.
