AI RESEARCH
ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization
arXiv CS.LG
•
ArXi:2603.14254v1 Announce Type: cross Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods rely on backpropagation (BP), which is computationally costly and incompatible with non-differentiable models such as quantized models, limiting practical deployment on numerous edge devices. Recent BP-free approaches alleviate overhead but remain either architecture-specific or limited in optimization capacity to handle high-dimensional models.