Noise-Tolerant Interactive Learning from Pairwise Comparisons
This addresses the challenge of learning from noisy data in scenarios where direct labels are hard to obtain but pairwise comparisons are easier, offering improved query efficiency for applications like preference learning or ranking.
The paper tackles the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, showing that the comparison oracle reduces the problem to learning a threshold function and presenting an algorithm with almost optimal query complexity under Tsybakov and adversarial noise conditions.
We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder but pairwise comparisons are easier, and the algorithm can leverage both types of oracles. In this paper, we attempt to characterize how the access to an easier comparison oracle helps in improving the label and total query complexity. We show that the comparison oracle reduces the learning problem to that of learning a threshold function. We then present an algorithm that interactively queries the label and comparison oracles and we characterize its query complexity under Tsybakov and adversarial noise conditions for the comparison and labeling oracles. Our lower bounds show that our label and total query complexity is almost optimal.