• Corpus ID: 209516359

Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples

@article{Bhatia2021SimpleAF,
  title={Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples},
  author={Jagdeep Bhatia},
  journal={J. Mach. Learn. Res.},
  year={2021},
  volume={22},
  pages={15:1-15:30}
}
  • Jagdeep Bhatia
  • Published 1 October 2018
  • Computer Science
  • J. Mach. Learn. Res.
This work describes simple and efficient algorithms for interactively learning non-binary concepts in the learning from random counter-examples (LRC) model. Here, learning takes place from random counter-examples that the learner receives in response to their proper equivalence queries. In this context, the learning time is defined as the number of counter-examples needed by the learner to identify the target concept. Such learning is particularly suited for online ranking, classification… 

Figures from this paper

Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm
TLDR
This paper considers the optimal teacher who picks bestcase counterexamples to teach the target hypothesis within a hypothesis class, and introduces LwEQ-TD, a notion of TD capturing the teaching complexity (i.e., the number of queries made) in this paradigm.

References

SHOWING 1-10 OF 14 REFERENCES
An Introduction to Computational Learning Theory
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm
  • N. Littlestone
  • Computer Science
    28th Annual Symposium on Foundations of Computer Science (sfcs 1987)
  • 1987
TLDR
This work presents one such algorithm that learns disjunctive Boolean functions, along with variants for learning other classes of Boolean functions.
A General Framework for Robust Interactive Learning
TLDR
A general framework for interactively learning models, such as (binary or non-binary) classifiers, orderings/rankings of items, or clusterings of data points, based on a generalization of Angluin's equivalence query model and Littlestone's online learning model is proposed.
Queries and concept learning
We consider the problem of using queries to learn an unknown concept. Several types of queries are described and studied: membership, equivalence, subset, superset, disjointness, and exhaustiveness
On the prediction of general recursive functions
  • Soviet Math. Doklady,
  • 1972
Queries revisited
Lower bound methods and separation results for on-line learning models
We consider the complexity of concept learning in various common models for on-line learning, focusing on methods for proving lower bounds to the learning complexity of a concept class. Among others,
Algorithms and Lower Bounds for On-Line Learning of Geometrical Concepts
The complexity of on-line learning is investigated for the basic classes of geometrical objects over a discrete (“digitized”) domain. In particular, upper and lower bounds are derived for the
Local algorithms for interactive clustering
TLDR
This work studies the design of interactive clustering algorithms for data sets satisfying natural stability assumptions and shows that in this constrained setting one can still design provably efficient algorithms that produce accurate clusterings.
...
...