106 citations · 310 across the 82 of their papers we have counts for
17 papers · 1 filter
Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference
Nitin Priyadarshini Shankar, Soham Lahiri, Sheetal Kalyani +1
Federated Learning (FL) preserves privacy by distributing training across devices. However, using DNNs is computationally intensive at the low-powered edge during inference. Edge d…
Tuning-Free Structured Sparse Recovery of Multiple Measurement Vectors using Implicit Regularization
Lakshmi Jayalal, Sheetal Kalyani
Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods often require careful para…
BERTO: Intent-Driven Network Time Series Forecasting via Natural Language Operator Preferences
Nitin Priyadarshini Shankar, Vaibhav Singh, Sheetal Kalyani +1
Traditional cellular traffic forecasting models are optimized for minimizing symmetric errors, leaving them indifferent to shifting operational priorities. To bridge this gap, we i…
Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
Prasenjit K Mudi, Anshi Sachan, Dahlia Devapriya +1
Whisper models have achieved remarkable progress in speech recognition; yet their large size remains a bottleneck for deployment on resource-constrained edge devices. This paper pr…
Learning Rate Optimization for Deep Neural Networks Using Lipschitz Bandits
Padma Priyanka, Sheetal Kalyani, Avhishek Chatterjee
Learning rate is a crucial parameter in training of neural networks. A properly tuned learning rate leads to faster training and higher test accuracy. In this paper, we propose a L…
Geometry Aware Meta-Learning Neural Network for Joint Phase and Precoder Optimization in RIS
Dahlia Devapriya, Aparna V C, Sheetal Kalyani
In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves signi…
Tuning-Free Online Robust Principal Component Analysis through Implicit Regularization
Lakshmi Jayalal, Gokularam Muthukrishnan, Sheetal Kalyani
The performance of the standard Online Robust Principal Component Analysis (OR-PCA) technique depends on the optimum tuning of the explicit regularizers and this tuning is dataset…
First line of defense: A robust first layer mitigates adversarial attacks
Janani Suresh, Nancy Nayak, Sheetal Kalyani
Adversarial training (AT) incurs significant computational overhead, leading to growing interest in designing inherently robust architectures. We demonstrate that a carefully desig…
Randomness Helps Rigor: A Probabilistic Learning Rate Scheduler Bridging Theory and Deep Learning Practice
Dahlia Devapriya, Thulasi Tholeti, Janani Suresh +1
Learning rate schedulers have shown great success in speeding up the convergence of learning algorithms in practice. However, their convergence to a minimum has not been proven the…
The robust way to stack and bag: the local Lipschitz way
Thulasi Tholeti, Sheetal Kalyani
Recent research has established that the local Lipschitz constant of a neural network directly influences its adversarial robustness. We exploit this relationship to construct an e…
Rotate the ReLU to implicitly sparsify deep networks
Nancy Nayak, Sheetal Kalyani
In the era of Deep Neural Network based solutions for a variety of real-life tasks, having a compact and energy-efficient deployable model has become fairly important. Most of the…
How to boost autoencoders?
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 le…
Deep learned SVT: Unrolling singular value thresholding to obtain better MSE
Siva Shanmugam, Sheetal Kalyani
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…
On the Differentially Private Nature of Perturbed Gradient Descent
Thulasi Tholeti, Sheetal Kalyani
We consider the problem of empirical risk minimization given a database, using the gradient descent algorithm. We note that the function to be optimized may be non-convex, consisti…
Understanding Learning Dynamics of Binary Neural Networks via Information Bottleneck
Vishnu Raj, Nancy Nayak, Sheetal Kalyani
Compact neural networks are essential for affordable and power efficient deep learning solutions. Binary Neural Networks (BNNs) take compactification to the extreme by constraining…
Tune smarter not harder: A principled approach to tuning learning rates for shallow nets
Thulasi Tholeti, Sheetal Kalyani
Effective hyper-parameter tuning is essential to guarantee the performance that neural networks have come to be known for. In this work, a principled approach to choosing the learn…
An aggregating strategy for shifting experts in discrete sequence prediction
Vishnu Raj, Sheetal Kalyani
We study how we can adapt a predictor to a non-stationary environment with advises from multiple experts. We study the problem under complete feedback when the best expert changes…