Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms

• URL: http://arxiv.org/abs/2405.14778v1
• Date: Thu, 23 May 2024 16:45:52 GMT
• Title: Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
• Authors: Dimitri Meunier, Zikai Shen, Mattes Mollenhauer, Arthur Gretton, Zhu Li,
• Abstract summary: We study theoretical properties of a broad class of regularized algorithms with vector-valued output. We rigorously confirm the so-called saturation effect for ridge regression with vector-valued output. We present the upper bound for the finite sample risk general vector-valued spectral algorithms.
• Score: 28.046728466038022
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study theoretical properties of a broad class of regularized algorithms with vector-valued output. These spectral algorithms include kernel ridge regression, kernel principal component regression, various implementations of gradient descent and many more. Our contributions are twofold. First, we rigorously confirm the so-called saturation effect for ridge regression with vector-valued output by deriving a novel lower bound on learning rates; this bound is shown to be suboptimal when the smoothness of the regression function exceeds a certain level. Second, we present the upper bound for the finite sample risk general vector-valued spectral algorithms, applicable to both well-specified and misspecified scenarios (where the true regression function lies outside of the hypothesis space) which is minimax optimal in various regimes. All of our results explicitly allow the case of infinite-dimensional output variables, proving consistency of recent practical applications.

Related papers

• A randomized algorithm to solve reduced rank operator regression [27.513149895229837]
  We present and analyze an algorithm designed for addressing vector-valued regression problems involving possibly infinite-dimensional input and output spaces. The algorithm is a randomized adaptation of reduced rank regression, a technique to optimally learn a low-rank vector-valued function.
  arXiv  Detail & Related papers  (2023-12-28T20:29:59Z)
• Stochastic Gradient Descent for Gaussian Processes Done Right [86.83678041846971]
  We show that when emphdone right -- by which we mean using specific insights from optimisation and kernel communities -- gradient descent is highly effective. We introduce a emphstochastic dual descent algorithm, explain its design in an intuitive manner and illustrate the design choices. Our method places Gaussian process regression on par with state-of-the-art graph neural networks for molecular binding affinity prediction.
  arXiv  Detail & Related papers  (2023-10-31T16:15:13Z)
• Stochastic Optimization for Non-convex Problem with Inexact Hessian Matrix, Gradient, and Function [99.31457740916815]
  Trust-region (TR) and adaptive regularization using cubics have proven to have some very appealing theoretical properties. We show that TR and ARC methods can simultaneously provide inexact computations of the Hessian, gradient, and function values.
  arXiv  Detail & Related papers  (2023-10-18T10:29:58Z)
• Coefficient-based Regularized Distribution Regression [4.21768682940933]
  We consider the coefficient-based regularized distribution regression which aims to regress from probability measures to real-valued responses over a kernel reproducing Hilbert space (RKHS) Asymptotic behaviors of the algorithm in different regularity ranges of the regression function are comprehensively studied. We get the optimal rates under some mild conditions, which matches the one-stage sampled minimax optimal rate.
  arXiv  Detail & Related papers  (2022-08-26T03:46:14Z)
• Robust Regularized Low-Rank Matrix Models for Regression and Classification [14.698622796774634]
  We propose a framework for matrix variate regression models based on a rank constraint, vector regularization (e.g., sparsity), and a general loss function. We show that the algorithm is guaranteed to converge, all accumulation points of the algorithm have estimation errors in the order of $O(sqrtn)$ally and substantially attaining the minimax rate.
  arXiv  Detail & Related papers  (2022-05-14T18:03:48Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• On the Benefits of Large Learning Rates for Kernel Methods [110.03020563291788]
  We show that a phenomenon can be precisely characterized in the context of kernel methods. We consider the minimization of a quadratic objective in a separable Hilbert space, and show that with early stopping, the choice of learning rate influences the spectral decomposition of the obtained solution.
  arXiv  Detail & Related papers  (2022-02-28T13:01:04Z)
• Fine-grained Generalization Analysis of Vector-valued Learning [28.722350261462463]
  We start the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size. To understand the interaction between optimization and learning, we further use our results to derive the first bounds for descent with vector-valued functions. As a byproduct, we derive a Rademacher complexity bound for loss function classes defined in terms of a general strongly convex function.
  arXiv  Detail & Related papers  (2021-04-29T07:57:34Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• 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)
• Improved SVRG for quadratic functions [0.0]
  We analyse an iterative algorithm to minimize quadratic functions whose Hessian matrix $H$ is the expectation of a random symmetric $dtimes d$ matrix. In several applications, including least-squares regressions, ridge regressions, linear discriminant analysis and regularized linear discriminant analysis, the running time of each iteration is proportional to $d$.
  arXiv  Detail & Related papers  (2020-06-01T15:28:08Z)

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.