Bayesian vs. PAC-Bayesian Deep Neural Network Ensembles
- URL: http://arxiv.org/abs/2406.05469v1
- Date: Sat, 8 Jun 2024 13:19:18 GMT
- Title: Bayesian vs. PAC-Bayesian Deep Neural Network Ensembles
- Authors: Nick Hauptvogel, Christian Igel,
- Abstract summary: We argue that neither the sampling nor the weighting in a Bayes ensemble are particularly well-suited for increasing generalization performance.
We show that state-of-the-art Bayes ensembles from the literature, despite being computationally demanding, do not improve over simple uniformly weighted deep ensembles.
- Score: 7.883369697332076
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Bayesian neural networks address epistemic uncertainty by learning a posterior distribution over model parameters. Sampling and weighting networks according to this posterior yields an ensemble model referred to as Bayes ensemble. Ensembles of neural networks (deep ensembles) can profit from the cancellation of errors effect: Errors by ensemble members may average out and the deep ensemble achieves better predictive performance than each individual network. We argue that neither the sampling nor the weighting in a Bayes ensemble are particularly well-suited for increasing generalization performance, as they do not support the cancellation of errors effect, which is evident in the limit from the Bernstein-von~Mises theorem for misspecified models. In contrast, a weighted average of models where the weights are optimized by minimizing a PAC-Bayesian generalization bound can improve generalization performance. This requires that the optimization takes correlations between models into account, which can be achieved by minimizing the tandem loss at the cost that hold-out data for estimating error correlations need to be available. The PAC-Bayesian weighting increases the robustness against correlated models and models with lower performance in an ensemble. This allows us to safely add several models from the same learning process to an ensemble, instead of using early-stopping for selecting a single weight configuration. Our study presents empirical results supporting these conceptual considerations on four different classification datasets. We show that state-of-the-art Bayes ensembles from the literature, despite being computationally demanding, do not improve over simple uniformly weighted deep ensembles and cannot match the performance of deep ensembles weighted by optimizing the tandem loss, which additionally come with non-vacuous generalization guarantees.
Related papers
- EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models [70.60381055741391]
Image restoration challenges related to illposed problems, resulting in deviations between single model predictions and ground-truths.
Ensemble learning aims to address these deviations by combining the predictions of multiple base models.
We employ an expectation (EM)-based algorithm to estimate ensemble weights for prediction candidates.
Our algorithm is model-agnostic and training-free, allowing seamless integration and enhancement of various pre-trained image restoration models.
arXiv Detail & Related papers (2024-10-30T12:16:35Z) - Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging [24.64264715041198]
We introduce Sparse Model Soups (SMS), a novel method for merging sparse models by initiating each prune-retrain cycle with the averaged model from the previous phase.
SMS preserves sparsity, exploits sparse network benefits, is modular and fully parallelizable, and substantially improves IMP's performance.
arXiv Detail & Related papers (2023-06-29T08:49:41Z) - Joint Training of Deep Ensembles Fails Due to Learner Collusion [61.557412796012535]
Ensembles of machine learning models have been well established as a powerful method of improving performance over a single model.
Traditionally, ensembling algorithms train their base learners independently or sequentially with the goal of optimizing their joint performance.
We show that directly minimizing the loss of the ensemble appears to rarely be applied in practice.
arXiv Detail & Related papers (2023-01-26T18:58:07Z) - Deep Negative Correlation Classification [82.45045814842595]
Existing deep ensemble methods naively train many different models and then aggregate their predictions.
We propose deep negative correlation classification (DNCC)
DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated.
arXiv Detail & Related papers (2022-12-14T07:35:20Z) - Model soups: averaging weights of multiple fine-tuned models improves
accuracy without increasing inference time [69.7693300927423]
We show that averaging the weights of multiple models fine-tuned with different hyper parameter configurations improves accuracy and robustness.
We show that the model soup approach extends to multiple image classification and natural language processing tasks.
arXiv Detail & Related papers (2022-03-10T17:03:49Z) - Learning to Solve Routing Problems via Distributionally Robust
Optimization [14.506553345693536]
Recent deep models for solving routing problems assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability.
We exploit group distributionally robust optimization (group DRO) to tackle this issue, where we jointly optimize the weights for different groups of distributions and the parameters for the deep model in an interleaved manner during training.
We also design a module based on convolutional neural network, which allows the deep model to learn more informative latent pattern among the nodes.
arXiv Detail & Related papers (2022-02-15T08:06:44Z) - Repulsive Deep Ensembles are Bayesian [6.544954579068863]
We introduce a kernelized repulsive term in the update rule of the deep ensembles.
We show that this simple modification not only enforces and maintains diversity among the members but, even more importantly, transforms the maximum a posteriori inference into proper Bayesian inference.
arXiv Detail & Related papers (2021-06-22T09:50:28Z) - Post-mortem on a deep learning contest: a Simpson's paradox and the
complementary roles of scale metrics versus shape metrics [61.49826776409194]
We analyze a corpus of models made publicly-available for a contest to predict the generalization accuracy of neural network (NN) models.
We identify what amounts to a Simpson's paradox: where "scale" metrics perform well overall but perform poorly on sub partitions of the data.
We present two novel shape metrics, one data-independent, and the other data-dependent, which can predict trends in the test accuracy of a series of NNs.
arXiv Detail & Related papers (2021-06-01T19:19:49Z) - VAE Approximation Error: ELBO and Conditional Independence [78.72292013299868]
This paper analyzes VAE approximation errors caused by the combination of the ELBO objective with the choice of the encoder probability family.
We show that the ELBO subset can not be enlarged, and the respective error cannot be decreased, by only considering deeper encoder networks.
arXiv Detail & Related papers (2021-02-18T12:54:42Z) - DessiLBI: Exploring Structural Sparsity of Deep Networks via
Differential Inclusion Paths [45.947140164621096]
We propose a new approach based on differential inclusions of inverse scale spaces.
We show that DessiLBI unveils "winning tickets" in early epochs.
arXiv Detail & Related papers (2020-07-04T04:40:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.