Leveraging tails for adaptation

• URL: http://arxiv.org/abs/2606.20480v2
• Date: Fri, 19 Jun 2026 08:00:38 GMT
• Title: Leveraging tails for adaptation
• Abstract summary: We consider contraction of Bayesian posterior distributions in nonparametric settings.<n>We show that contraction rates improve as $p$ decreases.<n>In particular, we show that overparametrised shallow ReLU networks can adapt to any regularity $0le le 2$.
• Score: 0.5352699766206809
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider contraction of Bayesian posterior distributions in nonparametric settings where coefficients of a function over a basis or dictionary are given priors with $p$--exponential tails, including Laplace tails $(p=1)$ and heavier tails $(p<1)$. It is shown that contraction rates improve as $p$ decreases and that full adaptation to smoothness, up to logarithmic factors, is obtained in an appropriate $p\to 0$ regime. As applications, we consider both series priors in white noise regression and shallow ReLU neural networks in random design regression. In particular, we show that overparametrised shallow ReLU networks can adapt to any regularity $0\le β\le 2$. Through a simulation study, we show strong empirical agreement with the behavior predicted by our theory.

Related papers

• How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis [53.063298916923976]
  We study the feedback in a Gaussian single-index model with $r*(x) = *(langle *, xrangle)$ and $x sim N(0, I_d)$.<n>We analyze a two-stage neural reward model that first learns the hidden direction $*$ from reward-weighted samples and then fits the readout layer by weighted ridge regression.
  arXiv  Detail & Related papers  (2026-05-23T22:00:38Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Parametric Mean-Field empirical Bayes in high-dimensional linear regression [8.197187859375694]
  We characterize a sharp phase transition behavior for the Empirical Bayes (vEB) estimator.<n>In the first regime, we show how the estimated prior can be calibrated to enable valid coordinate-wise and delocalized inference.<n>In the second regime, we propose a debiasing technique as a way to improve the performance of the vEB estimator.
  arXiv  Detail & Related papers  (2026-01-23T15:44:01Z)
• Tail Distribution of Regret in Optimistic Reinforcement Learning [3.9962751777898955]
  We characterize the tail distribution of the cumulative regret $R_K$ over $K$ episodes, rather than only its expectation or a single high-probability quantile.<n>A proposed algorithm depends on a tuning parameter $$, which balances the expected regret and the range over which the regret exhibits a sub-Gaussian tail.
  arXiv  Detail & Related papers  (2025-11-23T02:23:09Z)
• Convergence Rate Analysis of LION [54.28350823319057]
  LION converges iterations of $cal(sqrtdK-)$ measured by gradient Karush-Kuhn-T (sqrtdK-)$. We show that LION can achieve lower loss and higher performance compared to standard SGD.
  arXiv  Detail & Related papers  (2024-11-12T11:30:53Z)
• Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization [7.977229957867868]
  Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L$ risk are universally consistent. In this paper, we show that the regularization term is not necessary to obtain similar results.
  arXiv  Detail & Related papers  (2023-11-24T17:04:21Z)
• Distributional Reinforcement Learning with Dual Expectile-Quantile Regression [51.87411935256015]
  quantile regression approach to distributional RL provides flexible and effective way of learning arbitrary return distributions.<n>We show that distributional estimation guarantees vanish, and we empirically observe that the estimated distribution rapidly collapses to its mean.<n>Motivated by the efficiency of $L$-based learning, we propose to jointly learn expectiles and quantiles of the return distribution in a way that allows efficient learning.
  arXiv  Detail & Related papers  (2023-05-26T12:30:05Z)
• Nonparametric regression with modified ReLU networks [77.34726150561087]
  We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function $alpha$ before being multiplied by input vectors.
  arXiv  Detail & Related papers  (2022-07-17T21:46:06Z)
• $p$-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets [74.37849422071206]
  We study the $p$-generalized probit regression model, which is a generalized linear model for binary responses. We show how the maximum likelihood estimator for $p$-generalized probit regression can be approximated efficiently up to a factor of $(1+varepsilon)$ on large data.
  arXiv  Detail & Related papers  (2022-03-25T10:54:41Z)
• Online nonparametric regression with Sobolev kernels [99.12817345416846]
  We derive the regret upper bounds on the classes of Sobolev spaces $W_pbeta(mathcalX)$, $pgeq 2, beta>fracdp$. The upper bounds are supported by the minimax regret analysis, which reveals that in the cases $beta> fracd2$ or $p=infty$ these rates are (essentially) optimal.
  arXiv  Detail & Related papers  (2021-02-06T15:05:14Z)

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.