2 papers
cs.LG2026
TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
Abhijit Chakraborty, Suddhasvatta Das, Yash Shah +2
As machine learning(ML) systems evolve to continual adaptation, each re-training cycle uses compute, annotation, and energy. We introduce TIMEGATE, a policy layer managing adaptati…
cs.LG2026
Learning Resilient Elections with Adversarial GNNs
Hao Xiang Li, Yash Shah, Lorenzo Giusti
In the face of adverse motives, it is indispensable to achieve a consensus. Elections have been the canonical way by which modern democracy has operated since the 17th century. Now…