Nishant Jain

Instance-Conditional Timescales of Decay for Non-Stationary Learning

2022 · arXiv (Cornell University)

Slow concept drift is a ubiquitous, yet under-studied problem in practical machine learning systems. In such settings, although recent data is more indicative of future data, naively prioritizing recent instances runs the risk of losing …

Efficiently Robustify Pre-Trained Models

2023

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still …