FMOW

Findings

• IC-1105PAC-Bayes generalization bounds for discrete class prompts on CLIP are within a few percentage points of the actual test error across CIFAR-10, CIFAR-100, ImageNet, FMOW, and OfficeHome [eval]
• IC-1106CLIP prompts found by greedy search do not fit random labels: train and test error drop in tandem as the fraction of flipped labels increases, unlike a linear probe which achieves near-random accuracy [eval]