Good Classifiers are Abundant in the Interpolating Regime

• URL: http://arxiv.org/abs/2006.12625v2
• Date: Thu, 4 Mar 2021 16:57:25 GMT
• Title: Good Classifiers are Abundant in the Interpolating Regime
• Authors: Ryan Theisen, Jason M. Klusowski, Michael W. Mahoney
• Abstract summary: 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.
• Score: 64.72044662855612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Within the machine learning community, the widely-used uniform convergence framework has been used to answer the question of how complex, over-parameterized models can generalize well to new data. This approach bounds the test error of the worst-case model one could have fit to the data, but it has fundamental limitations. Inspired by the statistical mechanics approach to learning, we formally define and develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers from several model classes. We apply our method to compute this distribution for several real and synthetic datasets, with both linear and random feature classification models. We find that test errors tend to concentrate around a small typical value $\varepsilon^*$, which deviates substantially from the test error of the worst-case interpolating model on the same datasets, indicating that "bad" classifiers are extremely rare. We provide theoretical results in a simple setting in which we characterize the full asymptotic distribution of test errors, and we show that these indeed concentrate around a value $\varepsilon^*$, which we also identify exactly. We then formalize a more general conjecture supported by our empirical findings. 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, and that approaches based on the statistical mechanics of learning may offer a promising alternative.

Related papers

• Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity [11.2120847961379]
  We consider in this paper a more realistic heterogeneity model, namely (G,B)-gradient dissimilarity, and show that it covers a larger class of learning problems than existing theory. We also prove a new lower bound on the learning error of any distributed learning algorithm.
  arXiv  Detail & Related papers  (2023-09-24T09:29:28Z)
• Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction [51.82628081279621]
  Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions. A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems. It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution.
  arXiv  Detail & Related papers  (2023-09-02T01:27:53Z)
• Testing for Overfitting [0.0]
  We discuss the overfitting problem and explain why standard and concentration results do not hold for evaluation with training data. We introduce and argue for a hypothesis test by means of which both model performance may be evaluated using training data.
  arXiv  Detail & Related papers  (2023-05-09T22:49:55Z)
• A Statistical Model for Predicting Generalization in Few-Shot Classification [6.158812834002346]
  We introduce a Gaussian model of the feature distribution to predict the generalization error. We show that our approach outperforms alternatives such as the leave-one-out cross-validation strategy.
  arXiv  Detail & Related papers  (2022-12-13T10:21:15Z)
• Predicting Unreliable Predictions by Shattering a Neural Network [145.3823991041987]
  Piecewise linear neural networks can be split into subfunctions. Subfunctions have their own activation pattern, domain, and empirical error. Empirical error for the full network can be written as an expectation over subfunctions.
  arXiv  Detail & Related papers  (2021-06-15T18:34:41Z)
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality [106.50867011164584]
  We show that we can compute the exact Bayes error of generative models learned using normalizing flows. We use our approach to conduct a thorough investigation of state-of-the-art classification models.
  arXiv  Detail & Related papers  (2021-06-07T06:21:20Z)
• Testing for Typicality with Respect to an Ensemble of Learned Distributions [5.850572971372637]
  One-sample approaches to the goodness-of-fit problem offer significant computational advantages for online testing. The ability to correctly reject anomalous data in this setting hinges on the accuracy of the model of the base distribution. Existing methods for the one-sample goodness-of-fit problem do not account for the fact that a model of the base distribution is learned. We propose training an ensemble of density models, considering data to be anomalous if the data is anomalous with respect to any member of the ensemble.
  arXiv  Detail & Related papers  (2020-11-11T19:47:46Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations [98.3066727301239]
  We identify two key properties of the training data that drive this behavior. We show how the inductive bias of models towards "memorizing" fewer examples can cause over parameterization to hurt.
  arXiv  Detail & Related papers  (2020-05-09T01:59:13Z)

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.