collaborators

6 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…