26 citations · 55 across the 9 of their papers we have counts for
11 papers
A Generalisation Signal Need Not Be a Model-Selection Signal
Aditya Nagarsekar, M P Ashish Bhat, Aadi Nesarkar +5
Model selection in computational biology often relies on validation data drawn from the training regime, even when deployment lies outside it. When validation no longer preserves w…
A Radon-Nikodým Perspective on Anomaly Detection: Theory and Implications
Shlok Mehendale, Aditya Challa, Rahul Yedida +3
Which principle underpins the design of an effective anomaly detection loss function? The answer lies in the concept of Radon-Nikodým theorem, a fundamental concept in measure theo…
Strong convexity-guided hyper-parameter optimization for flatter losses
Rahul Yedida, Snehanshu Saha
We propose a novel white-box approach to hyper-parameter optimization. Motivated by recent work establishing a relationship between flat minima and generalization, we first establi…
Lessons learned from hyper-parameter tuning for microservice candidate identification
Rahul Yedida, Rahul Krishna, Anup Kalia +3
When optimizing software for the cloud, monolithic applications need to be partitioned into many smaller *microservices*. While many tools have been proposed for this task, we warn…
Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets
Rahul Yedida, Saad Mohammad Abrar, Cleber Melo-Filho +3
Objective: We aim to learn potential novel cures for diseases from unstructured text sources. More specifically, we seek to extract drug-disease pairs of potential cures to disease…
On the Value of Oversampling for Deep Learning in Software Defect Prediction
Rahul Yedida, Tim Menzies
One truism of deep learning is that the automatic feature engineering (seen in the first layers of those networks) excuses data scientists from performing tedious manual feature en…
Learning to Recognize Actionable Static Code Warnings (is Intrinsically Easy)
Xueqi Yang, Jianfeng Chen, Rahul Yedida +2
Static code warning tools often generate warnings that programmers ignore. Such tools can be made more useful via data mining algorithms that select the "actionable" warnings; i.e.…
Parsimonious Computing: A Minority Training Regime for Effective Prediction in Large Microarray Expression Data Sets
Shailesh Sridhar, Snehanshu Saha, Azhar Shaikh +2
Rigorous mathematical investigation of learning rates used in back-propagation in shallow neural networks has become a necessity. This is because experimental evidence needs to be…
Evolution of Novel Activation Functions in Neural Network Training with Applications to Classification of Exoplanets
Snehanshu Saha, Nithin Nagaraj, Archana Mathur +1
We present analytical exploration of novel activation functions as consequence of integration of several ideas leading to implementation and subsequent use in habitability classifi…
LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence
Rahul Yedida, Snehanshu Saha, Tejas Prashanth
Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout…
Employee Attrition Prediction
Rahul Yedida, Rahul Reddy, Rakshit Vahi +3
We aim to predict whether an employee of a company will leave or not, using the k-Nearest Neighbors algorithm. We use evaluation of employee performance, average monthly hours at w…