Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

• URL: http://arxiv.org/abs/2210.07612v2
• Date: Tue, 25 Jul 2023 22:51:42 GMT
• Title: Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
• Authors: Liam Hodgkinson, Chris van der Heide, Fred Roosta, Michael W. Mahoney
• Abstract summary: It is commonly believed that the marginal likelihood should be reminiscent of cross-validation metrics and that both should deteriorate with larger input dimensions. We prove that by tuning hyper parameters, the performance, as measured by the marginal likelihood, improves monotonically with the input dimension. We also prove that cross-validation metrics exhibit qualitatively different behavior that is characteristic of double descent.
• Score: 52.92110730286403
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their importance for assessing reliability of predictions, uncertainty quantification (UQ) measures for machine learning models have only recently begun to be rigorously characterized. One prominent issue is the curse of dimensionality: it is commonly believed that the marginal likelihood should be reminiscent of cross-validation metrics and that both should deteriorate with larger input dimensions. We prove that by tuning hyperparameters to maximize marginal likelihood (the empirical Bayes procedure), the performance, as measured by the marginal likelihood, improves monotonically} with the input dimension. On the other hand, we prove that cross-validation metrics exhibit qualitatively different behavior that is characteristic of double descent. Cold posteriors, which have recently attracted interest due to their improved performance in certain settings, appear to exacerbate these phenomena. We verify empirically that our results hold for real data, beyond our considered assumptions, and we explore consequences involving synthetic covariates.

Related papers

• Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density [93.32594873253534]
  Trustworthy machine learning requires meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input.
  arXiv  Detail & Related papers  (2024-07-05T09:16:56Z)
• Valid causal inference with unobserved confounding in high-dimensional settings [0.0]
  We show how valid semiparametric inference can be obtained in the presence of unobserved confounders and high-dimensional nuisance models. We propose uncertainty intervals which allow for unobserved confounding, and show that the resulting inference is valid when the amount of unobserved confounding is small.
  arXiv  Detail & Related papers  (2024-01-12T13:21:20Z)
• A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning [68.76846801719095]
  We show that double descent appears exactly when and where it occurs, and that its location is not inherently tied to the threshold p=n. This provides a resolution to tensions between double descent and statistical intuition.
  arXiv  Detail & Related papers  (2023-10-29T12:05:39Z)
• Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference [9.940560505044122]
  We propose a method to improve the efficiency and accuracy of amortized Bayesian inference. We estimate the marginal likelihood based on approximate representations of the joint model.
  arXiv  Detail & Related papers  (2023-10-06T17:41:41Z)
• Measurement-altered Ising quantum criticality [6.436344983789632]
  We show that measurements can alter long-distance correlations in a manner dependent on the choice of entangling gate, ancilla measurement basis, measurement outcome, and nature of ancilla correlations. We also identify two strategies for detecting measurement-altered Ising criticality in measurement-averaged quantities.
  arXiv  Detail & Related papers  (2023-02-08T20:40:26Z)
• Bayesian Model Selection, the Marginal Likelihood, and Generalization [49.19092837058752]
  We first revisit the appealing properties of the marginal likelihood for learning constraints and hypothesis testing. We show how marginal likelihood can be negatively correlated with generalization, with implications for neural architecture search. We also re-examine the connection between the marginal likelihood and PAC-Bayes bounds and use this connection to further elucidate the shortcomings of the marginal likelihood for model selection.
  arXiv  Detail & Related papers  (2022-02-23T18:38:16Z)
• Theoretical characterization of uncertainty in high-dimensional linear classification [24.073221004661427]
  We show that uncertainty for learning from limited number of samples of high-dimensional input data and labels can be obtained by the approximate message passing algorithm. We discuss how over-confidence can be mitigated by appropriately regularising, and show that cross-validating with respect to the loss leads to better calibration than with the 0/1 error.
  arXiv  Detail & Related papers  (2022-02-07T15:32:07Z)
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [70.54920804222031]
  Most existing forecasting models disregard uncertainty quantification, resulting in mis-calibrated predictions. Recent works in deep neural models for uncertainty-aware time-series forecasting also have several limitations. We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP.
  arXiv  Detail & Related papers  (2021-06-07T18:31:47Z)
• Machine learning for causal inference: on the use of cross-fit estimators [77.34726150561087]
  Doubly-robust cross-fit estimators have been proposed to yield better statistical properties. We conducted a simulation study to assess the performance of several estimators for the average causal effect (ACE) When used with machine learning, the doubly-robust cross-fit estimators substantially outperformed all of the other estimators in terms of bias, variance, and confidence interval coverage.
  arXiv  Detail & Related papers  (2020-04-21T23:09:55Z)
• Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction [6.170898159041278]
  We present a novel variational recurrent network that estimates the distribution of missing variables, updates hidden states, and predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner.
  arXiv  Detail & Related papers  (2020-03-02T04:41:28Z)

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.