We give the first agnostic, efficient, proper learning algorithm for monotone Boolean functions. Given [Formula: see text] uniformly random examples of an unknown function [Formula: see text], our algorithm outputs a hypothesis [Formula: see text] that is monotone and [Formula: see text]-close to [Formula: see text], where [Formula: see text] is the distance from [Formula: see text] to the closest monotone function. The running time of the algorithm (and consequently the size and evaluation time of the hypothesis) is also [Formula: see text], nearly matching the lower bound of [E. Blais et al., Proceedings of the 19 th International Workshop on Randomness and Computation, 2015, pp. 512–527]. We also give an algorithm for estimating up to additive error [Formula: see text] the distance of an unknown function [Formula: see text] to monotone using a run-time of [Formula: see text]. Previously, for both of these problems, sample-efficient algorithms were known, but these algorithms were not run-time efficient. Our work thus closes this gap in our knowledge between the run-time and sample complexity. This work builds upon the improper learning algorithm of [N. H. Bshouty and C. Tamon, J. ACM, 43 (1996), pp. 747–770] and the proper semiagnostic learning algorithm of [J. Lange, R. Rubinfeld, and A. Vasilyan, Proceedings of the 63 rd Annual Symposium on Foundations of Computer Science, IEEE, 2022, pp. 75–86], which obtains a nonmonotone Boolean-valued hypothesis, then “corrects” it to monotone using query-efficient local computation algorithms on graphs. This black-box correction approach can achieve no error better than [Formula: see text] information-theoretically; we bypass this barrier by (a) augmenting the improper learner with a convex optimization step, and (b) learning and correcting a real-valued function before rounding its values to Boolean. Our real-valued correction algorithm solves the “poset sorting” problem of Lange, Rubinfeld, and Vasilyan for functions over general posets with non-Boolean labels.