no code implementations • 16 Jun 2022 • R Adithya Gowtham, Gokularam M, Thulasi Tholeti, Sheetal Kalyani
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.
no code implementations • 1 Jun 2022 • Thulasi Tholeti, Sheetal Kalyani
Recent research has established that the local Lipschitz constant of a neural network directly influences its adversarial robustness.
no code implementations • 28 Oct 2021 • Sai Krishna, Thulasi Tholeti, Sheetal Kalyani
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.
no code implementations • 27 Oct 2021 • Deepsayan Sadhukhan, Nitin Priyadarshini Shankar, Nancy Nayak, Thulasi Tholeti, Sheetal Kalyani
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.
no code implementations • 18 Jan 2021 • Thulasi Tholeti, Sheetal Kalyani
We consider the problem of empirical risk minimization given a database, using the gradient descent algorithm.
no code implementations • 22 Mar 2020 • Thulasi Tholeti, Sheetal Kalyani
Effective hyper-parameter tuning is essential to guarantee the performance that neural networks have come to be known for.
no code implementations • 20 Mar 2020 • Nancy Nayak, Thulasi Tholeti, Muralikrishnan Srinivasan, Sheetal Kalyani
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.
no code implementations • 28 May 2019 • Thulasi Tholeti, Sheetal Kalyani
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.
no code implementations • 30 Apr 2018 • Thulasi Tholeti, Vishnu Raj, Sheetal Kalyani
Owing to the ever-increasing demand in wireless spectrum, Cognitive Radio (CR) was introduced as a technique to attain high spectral efficiency.
no code implementations • 31 Jul 2017 • Vishnu Raj, Irene Dias, Thulasi Tholeti, Sheetal Kalyani
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.