A hypothesis class is learnable in this online precision-recall feedback model if and only if it has finite VC dimension, with algorithms achieving regret bounds in realizable and agnostic settings despite ERM failing.
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Provides the first systematic generalization analysis via algorithmic stability for single-timescale and two-timescale stochastic gradient descent-ascent in bilevel minimax problems.
citing papers explorer
-
Online Set Learning from Precision and Recall Feedback
A hypothesis class is learnable in this online precision-recall feedback model if and only if it has finite VC dimension, with algorithms achieving regret bounds in realizable and agnostic settings despite ERM failing.
-
On the Stability and Generalization of First-order Bilevel Minimax Optimization
Provides the first systematic generalization analysis via algorithmic stability for single-timescale and two-timescale stochastic gradient descent-ascent in bilevel minimax problems.