6 papers
Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
Rahul D Ray
The ability to detect out-of-distribution (OOD) inputs is fundamental to safe deployment of machine learning systems. Yet, current methods often rely on feature representations tha…
VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
Rahul D Ray, Utkarsh Srivastava
Uncertainty quantification (UQ) is essential for deploying deep learning models in safety critical applications, yet no consensus exists on which UQ method performs best across dif…
Beyond a Single Signal: SPECTREG2, A Unified MultiExpert Anomaly Detector for Unknown Unknowns
Rahul D Ray
Epistemic intelligence requires machine learning systems to recognise the limits of their own knowledge and act safely under uncertainty, especially when faced with unknown unknown…
From Data to Laws: Neural Discovery of Conservation Laws Without False Positives
Rahul D Ray
Conservation laws are fundamental to understanding dynamical systems, but discovering them from data remains challenging due to parameter variation, non-polynomial invariants, loca…
ARTEMIS: A Neuro Symbolic Framework for Economically Constrained Market Dynamics
Rahul D Ray
Deep learning models in quantitative finance often operate as black boxes, lacking interpretability and failing to incorporate fundamental economic principles such as no-arbitrage…
The Physics Constraint Paradox: When Removing Explicit Constraints Improves Physics-Informed Data for Machine Learning
Rahul D Ray
Physics-constrained data generation is essential for machine learning in scientific domains where real data are scarce; however, existing approaches often over-constrain models wit…