Star algorithm for NN ensembling
Not on the map. Why?
Abstract (arXiv)
Neural network ensembling is a common and robust way to increase model efficiency. In this paper, we propose a new neural network ensemble algorithm based on Audibert's empirical star algorithm. We provide optimal theoretical minimax bound on the excess squared risk. Additionally, we empirically study this algorithm on regression and classification tasks and compare it to most popular ensembling methods.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 32 references that are in the map. First posted on arXiv 1 Jun 2022.
Builds on
13 of 32 references.
References · 13
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2016Deep Networks with Stochastic Depthcited by 979
- 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 588
- 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 433
- 2017Snapshot Ensembles: Train 1, get M for freecited by 350
- 2021Ensemble deep learning: A reviewcited by 284
- 2016Deep Learning without Poor Local Minimacited by 234
- 2015Learning with Square Loss: Localization through Offset Rademacher Complexitycited by 38
- 2013Empirical entropy, minimax regret and minimax riskcited by 21
1 more
- 2021Localization, Convexity, and Star Aggregationcited by 7
Built on by
Not cited yet.