The Interplay of Optimization and Machine Learning Research

168 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Discriminative Batch Mode Active Learning (2007, background): “A concern about the instance selection process, therefore, is that some information in the unlabeled data that is inconsistent with the true classification partition might mislead instance selection.”
Optimization Models for Machine Learning: A Survey (2019, background): “While important criteria for contributions in operations research are the convergence guarantees, deviation to optimality and speed increments with respect to benchmarks, machine learning applications have a partly different set of goals, such as scalability, reasonable execution time and memory req”
The Symbolic Interior Point Method (2016, background): “for hard combinatorial problems ranging from classiﬁcation and regression in learning, to computing optimal policies and equilibria in decision theory, to entropy minimization in information sciences [1, 2, 3]. What makes optimization particularly ubiquitous is that, similar to probabilistic inferen”
Supervised classification and mathematical optimization (2013, background): “Other, algorithmically oriented, criteria have been proposed in [22].”
Large-scale distributed L-BFGS (2017, methodology): “A wide range of machine learning algorithms use optimization methods to train the model parameters [1].”