Non-asymptotic estimates of the minimal risk in statistical learning

• URL: http://arxiv.org/abs/2606.23295v1
• Date: Mon, 22 Jun 2026 13:09:28 GMT
• Title: Non-asymptotic estimates of the minimal risk in statistical learning
• Abstract summary: We prove some concentration inequalities for two types of error probabilities in the Empirical Risk Principle (ERP) in statistical learning.<n>The confidence of the lower bound of the minimal risk is shown to be independent of the number of training parameters and the dimension of the input vectors.
• Score: 4.385387101894569
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we prove some concentration inequalities for two types of error probabilities in the Empirical Risk Principle (ERP) in statistical learning, which provide a lower bound and an upper bound for the minimal risk (in terms of the minimal empirical risk) with non-asymptotic high confidence. The usual boundedness condition of the empirical risk function is relaxed to the Gaussian or exponential integrability condition. The confidence of the lower bound of the minimal risk is shown to be independent of the number of training parameters and the dimension of the input vectors, allowing one to detect the deficiency of a learning machine efficiently; and the confidence of the upper bound of the minimal risk is proved to be high provided that the sample size $n$ is much greater than the box dimension of the parameter set $Θ$ in the Orlicz metric $d_{ψ_1}$ associated with the risk functions. Our work is based on Talagrand's concentration inequalities (the sharp versions by Bousquet and Klein-Rio), transport-entropy inequalities and the recent progress in the theory of empirical processes and statistical learning.

Related papers

• Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling [50.872910438715486]
  Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting.<n>We propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling.
  arXiv  Detail & Related papers  (2026-01-30T06:54:35Z)
• Error Bounds of Supervised Classification from Information-Theoretic Perspective [0.0]
  We explore bounds on the expected risk when using deep neural networks for supervised classification from an information theoretic perspective. We introduce model risk and fitting error, which are derived from further decomposing the empirical risk.
  arXiv  Detail & Related papers  (2024-06-07T01:07:35Z)
• Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation [54.61816424792866]
  We introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general function approximation. We design two innovative meta-algorithms: textttRS-DisRL-M, a model-based strategy for model-based function approximation, and textttRS-DisRL-V, a model-free approach for general value function approximation.
  arXiv  Detail & Related papers  (2024-02-28T08:43:18Z)
• Sharp error bounds for imbalanced classification: how many examples in the minority class? [6.74159270845872]
  Reweighting the loss function is a standard procedure allowing to equilibrate between the true positive and true negative rates within the risk measure. Despite significant theoretical work in this area, existing results do not adequately address a main challenge within the imbalanced classification framework. We present two contributions in the setting where the rare class probability approaches zero.
  arXiv  Detail & Related papers  (2023-10-23T11:45:34Z)
• On the Variance, Admissibility, and Stability of Empirical Risk Minimization [57.63331017830154]
  Empirical Risk Minimization (ERM) may attain minimax suboptimal rates in terms of the mean squared error.<n>We prove that under relatively mild assumptions, the suboptimality of ERM must be due to its large bias.
  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)
• Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis [7.953455469099826]
  The sensitivity of the expected empirical risk to deviations from the solution of the ERM-RER problem is studied. The expectation of the sensitivity is upper bounded, up to a constant factor, by the square root of the lautum information between the models and the datasets.
  arXiv  Detail & Related papers  (2022-02-09T10:55:14Z)
• Minimax Off-Policy Evaluation for Multi-Armed Bandits [58.7013651350436]
  We study the problem of off-policy evaluation in the multi-armed bandit model with bounded rewards. We develop minimax rate-optimal procedures under three settings.
  arXiv  Detail & Related papers  (2021-01-19T18:55:29Z)
• Learning Bounds for Risk-sensitive Learning [86.50262971918276]
  In risk-sensitive learning, one aims to find a hypothesis that minimizes a risk-averse (or risk-seeking) measure of loss. We study the generalization properties of risk-sensitive learning schemes whose optimand is described via optimized certainty equivalents.
  arXiv  Detail & Related papers  (2020-06-15T05:25:02Z)
• Asymptotic normality of robust risk minimizers [2.0432586732993374]
  This paper investigates properties of algorithms that can be viewed as robust analogues of the classical empirical risk. We show that for a wide class of parametric problems, minimizers of the appropriately defined robust proxy of risk converge to the minimizers of the true risk at the same rate.
  arXiv  Detail & Related papers  (2020-04-05T22:03:03Z)
• Statistical Agnostic Mapping: a Framework in Neuroimaging based on Concentration Inequalities [0.0]
  We derive a Statistical Agnostic (non-parametric) Mapping at voxel or multi-voxel level. We propose a novel framework in neuroimaging based on concentration inequalities.
  arXiv  Detail & Related papers  (2019-12-27T18:27:50Z)

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.