4 papers
TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
Krish Sharma, Omar Naim, Soumadeep Saha +3
Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we investigate when such improvements…
Algorithmic Compliance and Regulatory Loss in Digital Assets
Khem Raj Bhatt, Krishna Sharma
We study the deployment performance of machine learning based enforcement systems used in cryptocurrency anti money laundering (AML). Using forward looking and rolling evaluations…
Clear Messages, Ambiguous Audiences: Measuring Interpretability in Political Communication
Krishna Sharma, Khemraj Bhatt
Text-based measurement in political research often treats classi6ication disagreement as random noise. We examine this assumption using con6idence-weighted human annotations of 5,0…
Regulatory Migration to Europe: ICO Reallocation Following U.S. Securities Enforcement
Krishna Sharma, Khemraj Bhatt, Indra Giri
This paper examines whether a major U.S. regulatory clarification coincided with cross-border spillovers in crypto-asset entrepreneurial finance. We study the Securities and Exchan…