• Mathematics, Computer Science
  • Published in AAAI 2015

Selecting Near-Optimal Learners via Incremental Data Allocation

@inproceedings{Sabharwal2015SelectingNL,
  title={Selecting Near-Optimal Learners via Incremental Data Allocation},
  author={Ashish Sabharwal and Horst Samulowitz and Gerald Tesauro},
  booktitle={AAAI},
  year={2015}
}
We study a novel machine learning (ML) problem setting of sequentially allocating small subsets of training data amongst a large set of classifiers. The goal is to select a classifier that will give near-optimal accuracy when trained on all data, while also minimizing the cost of misallocated samples. This is motivated by large modern datasets and ML toolkits with many combinations of learning algorithms and hyper-parameters. Inspired by the principle of "optimism under uncertainty," we propose… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 27 CITATIONS

Deep Learning: Computational Aspects

VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Formal Method for AutoML via ADMM.

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

A Survey on Neural Architecture Search

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning

VIEW 3 EXCERPTS
CITES BACKGROUND

Hyper-parameter Tuning under a Budget Constraint

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

DeepArchitect: Automatically Designing and Training Deep Architectures

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

Searching for exotic particles in high-energy physics with deep learning.

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Analysis of Thompson Sampling for the Multi-armed Bandit Problem

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

A modern Bayesian look at the multi-armed bandit

VIEW 1 EXCERPT
HIGHLY INFLUENTIAL

From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning

  • Rémi Munos
  • Mathematics, Computer Science
  • Foundations and Trends in Machine Learning
  • 2014
VIEW 1 EXCERPT