A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator

• URL: http://arxiv.org/abs/2403.08938v1
• Date: Wed, 13 Mar 2024 20:12:03 GMT
• Title: A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator
• Authors: Theodor Misiakiewicz, Basil Saeed,
• Abstract summary: We consider learning an unknown target function $f_*$ using kernel ridge regression. We establish a non-asymptotic deterministic approximation for the test error of KRR.
• Score: 7.163829696591103
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider learning an unknown target function $f_*$ using kernel ridge regression (KRR) given i.i.d. data $(u_i,y_i)$, $i\leq n$, where $u_i \in U$ is a covariate vector and $y_i = f_* (u_i) +\varepsilon_i \in \mathbb{R}$. A recent string of work has empirically shown that the test error of KRR can be well approximated by a closed-form estimate derived from an `equivalent' sequence model that only depends on the spectrum of the kernel operator. However, a theoretical justification for this equivalence has so far relied either on restrictive assumptions -- such as subgaussian independent eigenfunctions -- , or asymptotic derivations for specific kernels in high dimensions. In this paper, we prove that this equivalence holds for a general class of problems satisfying some spectral and concentration properties on the kernel eigendecomposition. Specifically, we establish in this setting a non-asymptotic deterministic approximation for the test error of KRR -- with explicit non-asymptotic bounds -- that only depends on the eigenvalues and the target function alignment to the eigenvectors of the kernel. Our proofs rely on a careful derivation of deterministic equivalents for random matrix functionals in the dimension free regime pioneered by Cheng and Montanari (2022). We apply this setting to several classical examples and show an excellent agreement between theoretical predictions and numerical simulations. These results rely on having access to the eigendecomposition of the kernel operator. Alternatively, we prove that, under this same setting, the generalized cross-validation (GCV) estimator concentrates on the test error uniformly over a range of ridge regularization parameter that includes zero (the interpolating solution). As a consequence, the GCV estimator can be used to estimate from data the test error and optimal regularization parameter for KRR.

Related papers

• Universality of kernel random matrices and kernel regression in the quadratic regime [18.51014786894174]
  In this work, we extend the study of kernel kernel regression to the quadratic regime. We establish an operator norm approximation bound for the difference between the original kernel random matrix and a quadratic kernel random matrix. We characterize the precise training and generalization errors for KRR in the quadratic regime when $n/d2$ converges to a nonzero constant.
  arXiv  Detail & Related papers  (2024-08-02T07:29:49Z)
• Dimension-free deterministic equivalents and scaling laws for random feature regression [11.607594737176973]
  We show that the test error is well approximated by a closed-form expression that only depends on the feature map eigenvalues. Notably, our approximation guarantee is non-asymptotic, multiplicative, and independent of the feature map dimension.
  arXiv  Detail & Related papers  (2024-05-24T16:43:26Z)
• Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation [49.67011673289242]
  This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a smooth manifold. It induces a geometry for the parameter manifold, as well as an intrinsic notion of the estimation error measure.
  arXiv  Detail & Related papers  (2023-11-08T15:17:13Z)
• Error Bounds for Learning with Vector-Valued Random Features [2.375038919274297]
  This paper provides a comprehensive error analysis of learning with vector-valued random features (RF) The theory is developed for RF ridge regression in a fully general infinite-dimensional input-output setting.
  arXiv  Detail & Related papers  (2023-05-26T18:00:08Z)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces [102.08678737900541]
  We provide algorithms for constructing bias-aware designs for linear functionals. We derive non-asymptotic confidence sets for fixed and adaptive designs under sub-Gaussian noise.
  arXiv  Detail & Related papers  (2022-05-26T20:56:25Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)
• Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model [0.0]
  We analyze the convergence of single-pass, fixed step-size gradient descent on the least-square risk under this model. As a special case, we analyze an online algorithm for estimating a real function on the unit interval from the noiseless observation of its value at randomly sampled points.
  arXiv  Detail & Related papers  (2020-06-15T08:25:50Z)
• SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives [86.01677297601624]
  We propose a novel approach for scaling GP regression with derivatives based on quadrature Fourier features. We prove deterministic, non-asymptotic and exponentially fast decaying error bounds which apply for both the approximated kernel as well as the approximated posterior.
  arXiv  Detail & Related papers  (2020-03-05T14:33:20Z)

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.