How many classifiers do we need?

• URL: http://arxiv.org/abs/2411.00328v1
• Date: Fri, 01 Nov 2024 02:59:56 GMT
• Title: How many classifiers do we need?
• Authors: Hyunsuk Kim, Liam Hodgkinson, Ryan Theisen, Michael W. Mahoney,
• Abstract summary: We provide a detailed analysis of how the disagreement and the polarization among classifiers relate to the performance gain achieved by aggregating individual classifiers. We prove results for the behavior of the disagreement in terms of the number of classifiers. Our theories and claims are supported by empirical results on several image classification tasks with various types of neural networks.
• Score: 50.69951049206484
• License:
• Abstract: As performance gains through scaling data and/or model size experience diminishing returns, it is becoming increasingly popular to turn to ensembling, where the predictions of multiple models are combined to improve accuracy. In this paper, we provide a detailed analysis of how the disagreement and the polarization (a notion we introduce and define in this paper) among classifiers relate to the performance gain achieved by aggregating individual classifiers, for majority vote strategies in classification tasks. We address these questions in the following ways. (1) An upper bound for polarization is derived, and we propose what we call a neural polarization law: most interpolating neural network models are 4/3-polarized. Our empirical results not only support this conjecture but also show that polarization is nearly constant for a dataset, regardless of hyperparameters or architectures of classifiers. (2) The error of the majority vote classifier is considered under restricted entropy conditions, and we present a tight upper bound that indicates that the disagreement is linearly correlated with the target, and that the slope is linear in the polarization. (3) We prove results for the asymptotic behavior of the disagreement in terms of the number of classifiers, which we show can help in predicting the performance for a larger number of classifiers from that of a smaller number. Our theories and claims are supported by empirical results on several image classification tasks with various types of neural networks.

Related papers

• Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection [51.11833609431406]
  Homophily distribution differences between different classes are significantly greater than those in homophilic and heterophilic graphs. We introduce a new metric called Class Homophily Variance, which quantitatively describes this phenomenon. To mitigate its impact, we propose a novel GNN model named Homophily Edge Generation Graph Neural Network (HedGe)
  arXiv  Detail & Related papers  (2024-03-15T14:26:53Z)
• Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models [4.093769373833101]
  We resolve the conjecture posed in Subramanian et al.'22, where the number of data points, features, and classes all grow together. Our new lower bounds are akin to an information-theoretic strong converse: they establish that the misclassification rate goes to 0 or 1ally. The key to our tight analysis is a new variant of the Hanson-Wright inequality which is broadly useful for multiclass problems with sparse labels.
  arXiv  Detail & Related papers  (2023-06-23T00:59:15Z)
• When are ensembles really effective? [49.37269057899679]
  We study the question of when ensembling yields significant performance improvements in classification tasks. We show that ensembling improves performance significantly whenever the disagreement rate is large relative to the average error rate. We identify practical scenarios where ensembling does and does not result in large performance improvements.
  arXiv  Detail & Related papers  (2023-05-21T01:36:25Z)
• Soft-margin classification of object manifolds [0.0]
  A neural population responding to multiple appearances of a single object defines a manifold in the neural response space. The ability to classify such manifold is of interest, as object recognition and other computational tasks require a response that is insensitive to variability within a manifold. Soft-margin classifiers are a larger class of algorithms and provide an additional regularization parameter used in applications to optimize performance outside the training set.
  arXiv  Detail & Related papers  (2022-03-14T12:23:36Z)
• Adversarial Examples for $k$-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams [69.4411417775822]
  Adversarial examples are a widely studied phenomenon in machine learning models. We propose an algorithm for evaluating the adversarial robustness of $k$-nearest neighbor classification.
  arXiv  Detail & Related papers  (2020-11-19T08:49:10Z)
• Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization [39.35822033674126]
  We study binary linear classification under a generative Gaussian mixture model. We derive novel non-asymptotic bounds on the classification error of the latter. Our results extend to a noisy model with constant probability noise flips.
  arXiv  Detail & Related papers  (2020-11-18T07:59:55Z)
• Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View [82.80085730891126]
  We provide the first modernally precise analysis of linear multiclass classification. Our analysis reveals that the classification accuracy is highly distribution-dependent. The insights gained may pave the way for a precise understanding of other classification algorithms.
  arXiv  Detail & Related papers  (2020-11-16T05:17:29Z)
• Large scale analysis of generalization error in learning using margin based classification methods [2.436681150766912]
  We derive the expression for the generalization error of a family of large-margin classifiers in the limit of both sample size $n$ and dimension $p$. For two layer neural networks, we reproduce the recently developed double descent' phenomenology for several classification models.
  arXiv  Detail & Related papers  (2020-07-16T20:31:26Z)
• On Counterfactual Explanations under Predictive Multiplicity [14.37676876556672]
  Counterfactual explanations are usually obtained by identifying the smallest change made to an input to change a prediction made by a fixed model. Recent work has revitalized an old insight: there often does not exist one superior solution to a prediction problem with respect to commonly used measures of interest.
  arXiv  Detail & Related papers  (2020-06-23T16:25:47Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)

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.