On Regression in Extreme Regions

• URL: http://arxiv.org/abs/2303.03084v2
• Date: Wed, 10 Apr 2024 14:52:19 GMT
• Title: On Regression in Extreme Regions
• Authors: Nathan Huet, Stephan Clémençon, Anne Sabourin,
• Abstract summary: This paper focuses on the case of extreme (i.e. very large) observations $X$. Because of their rarity, the contributions of such observations to the (empirical) error is negligible. We show that an empirical and nonasymptotic version of this 'extreme risk', based on a fraction of the largest observations solely, yields good generalization capacity.
• Score: 1.0338669373504403
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The statistical learning problem consists in building a predictive function $\hat{f}$ based on independent copies of $(X,Y)$ so that $Y$ is approximated by $\hat{f}(X)$ with minimum (squared) error. Motivated by various applications, special attention is paid here to the case of extreme (i.e. very large) observations $X$. Because of their rarity, the contributions of such observations to the (empirical) error is negligible, and the predictive performance of empirical risk minimizers can be consequently very poor in extreme regions. In this paper, we develop a general framework for regression on extremes. Under appropriate regular variation assumptions regarding the pair $(X,Y)$, we show that an asymptotic notion of risk can be tailored to summarize appropriately predictive performance in extreme regions. It is also proved that minimization of an empirical and nonasymptotic version of this 'extreme risk', based on a fraction of the largest observations solely, yields good generalization capacity. In addition, numerical results providing strong empirical evidence of the relevance of the approach proposed are displayed.

Related papers

• Nonparametric logistic regression with deep learning [1.2509746979383698]
  In the nonparametric logistic regression, the Kullback-Leibler divergence could diverge easily. Instead of analyzing the excess risk itself, it suffices to show the consistency of the maximum likelihood estimator. As an important application, we derive the convergence rates of the NPMLE with deep neural networks.
  arXiv  Detail & Related papers  (2024-01-23T04:31:49Z)
• Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression [19.31269916674961]
  We show that, in the realizable case, under no moment assumptions, $O(d)$ samples are enough to exactly recover the target. We extend this result to the case $p in (1, 2)$ under mild assumptions that guarantee the existence of the Hessian of the risk at its minimizer.
  arXiv  Detail & Related papers  (2023-10-19T03:21:28Z)
• On the Variance, Admissibility, and Stability of Empirical Risk Minimization [80.26309576810844]
  Empirical Risk Minimization (ERM) with squared loss may attain minimax suboptimal error rates. We show that under mild assumptions, the suboptimality of ERM must be due to large bias rather than variance. We also show that our estimates imply stability of ERM, complementing the main result of Caponnetto and Rakhlin (2006) for non-Donsker classes.
  arXiv  Detail & Related papers  (2023-05-29T15:25:48Z)
• Mitigating multiple descents: A model-agnostic framework for risk monotonization [84.6382406922369]
  We develop a general framework for risk monotonization based on cross-validation. We propose two data-driven methodologies, namely zero- and one-step, that are akin to bagging and boosting.
  arXiv  Detail & Related papers  (2022-05-25T17:41:40Z)
• Heavy-tailed Streaming Statistical Estimation [58.70341336199497]
  We consider the task of heavy-tailed statistical estimation given streaming $p$ samples. We design a clipped gradient descent and provide an improved analysis under a more nuanced condition on the noise of gradients.
  arXiv  Detail & Related papers  (2021-08-25T21:30:27Z)
• Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments [55.24895403089543]
  Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments. We present a new algorithm based on performing iterative feature matching that is guaranteed with high probability to yield a predictor that generalizes after seeing only $O(logd_s)$ environments.
  arXiv  Detail & Related papers  (2021-06-18T04:39:19Z)
• SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression [68.66245730450915]
  We develop an improved method for debiasing predictions and estimating frequentist uncertainty for practical datasets. Our main contribution is SLOE, an estimator of the signal strength with convergence guarantees that reduces the computation time of estimation and inference by orders of magnitude.
  arXiv  Detail & Related papers  (2021-03-23T17:48:56Z)
• Sharp Statistical Guarantees for Adversarially Robust Gaussian Classification [54.22421582955454]
  We provide the first result of the optimal minimax guarantees for the excess risk for adversarially robust classification. Results are stated in terms of the Adversarial Signal-to-Noise Ratio (AdvSNR), which generalizes a similar notion for standard linear classification to the adversarial setting.
  arXiv  Detail & Related papers  (2020-06-29T21:06:52Z)
• Error bounds in estimating the out-of-sample prediction error using leave-one-out cross validation in high-dimensions [19.439945058410203]
  We study the problem of out-of-sample risk estimation in the high dimensional regime. Extensive empirical evidence confirms the accuracy of leave-one-out cross validation. One technical advantage of the theory is that it can be used to clarify and connect some results from the recent literature on scalable approximate LO.
  arXiv  Detail & Related papers  (2020-03-03T20:07:07Z)
• Weighted Empirical Risk Minimization: Sample Selection Bias Correction based on Importance Sampling [2.599882743586164]
  We consider statistical learning problems when the distribution $P'$ of the training observations $Z'_i$ differs from the distribution $P'$ involved in the risk one seeks to minimize. We show that, in various situations frequently encountered in practice, it takes a simple form and can be directly estimated from the $Phi(z)$. We then prove that the capacity generalization of the approach aforementioned is preserved when plugging the resulting estimates of the $Phi(Z'_i)$'s into the weighted empirical risk.
  arXiv  Detail & Related papers  (2020-02-12T18:42:47Z)
• Interpolating Predictors in High-Dimensional Factor Regression [2.1055643409860743]
  This work studies finite-sample properties of the risk of the minimum-norm interpolating predictor in high-dimensional regression models. We show that the min-norm interpolating predictor can have similar risk to predictors based on principal components regression and ridge regression, and can improve over LASSO based predictors, in the high-dimensional regime.
  arXiv  Detail & Related papers  (2020-02-06T22:08:36Z)

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.