# Optimally Combining Classifiers Using Unlabeled Data

arXiv: https://arxiv.org/abs/1503.01811 · HTML: https://mlsanity.com/paper/1503.01811/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2015.

## Built on by (most cited first, 9 of 9)

- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [Learning from Multiple Noisy Partial Labelers](https://mlsanity.com/paper/2106.04530/) (2021)
- [Losses over Labels: Weakly Supervised Learning via Direct Loss Construction](https://mlsanity.com/paper/2212.06921/) (2022)
- [Minimax risk classifiers with 0-1 loss](https://mlsanity.com/paper/2201.06487/) (2022)
- [Data Consistency for Weakly Supervised Learning](https://mlsanity.com/paper/2202.03987/) (2022)
- [Entropy, concentration, and learning: a statistical mechanics primer](https://mlsanity.com/paper/2409.18630/) (2024)
- [An Adaptive Method for Weak Supervision with Drifting Data](https://mlsanity.com/paper/2306.01658/) (2023)
- [Convergence Behavior of an Adversarial Weak Supervision Method](https://mlsanity.com/paper/2405.16013/) (2024)
- [Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes](https://mlsanity.com/paper/2205.13068/) (2022)

## Abstract (arXiv)

We develop a worst-case analysis of aggregation of classifier ensembles for binary classification. The task of predicting to minimize error is formulated as a game played over a given set of unlabeled data (a transductive setting), where prior label information is encoded as constraints on the game. The minimax solution of this game identifies cases where a weighted combination of the classifiers can perform significantly better than any single classifier.