4 papers · 1 filter
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…
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…
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…