paper-with-me

Papers

Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves

2022-04-06 · David Bosch, Ashkan Panahi, Ayca Özcelikkale, Devdatt Dubhash

We compute precise asymptotic expressions for the learning curves of least squares random feature (RF) models with either a separable strongly convex regularization or the $\ell_1$ regularization. We propose a novel multi-level application of the convex Gaussian min max theorem (CGMT) to overcome the traditional difficulty of finding computable expressions for random features models with correlated data. Our result takes the form of a computable 4-dimensional scalar optimization. In contrast to previous results, our approach does not require solving an often intractable proximal operator, which scales with the number of model parameters. Furthermore, we extend the universality results for the training and generalization errors for RF models to $\ell_1$ regularization. In particular, we demonstrate that under mild conditions, random feature models with elastic net or $\ell_1$ regularization are asymptotically equivalent to a surrogate Gaussian model with the same first and second moments. We numerically demonstrate the predictive capacity of our results, and show experimentally that the predicted test error is accurate even in the non-asymptotic regime.

📄 PDF Abstract BibTeX arXiv:2204.02678

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Optimal computational and statistical rates of convergence for sparse nonconvex learning problems

2013-06-20 · Zhaoran Wang, Han Liu, Tong Zhang

We provide theoretical analysis of the statistical and computational properties of penalized $M$-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators f…

regression

Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization

2021-08-25 · Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different sol…

Deep Learningimage-classificationImage Classification

Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees

2023-11-03 · Yingzhen Yang, Ping Li

Randomized algorithms are important for solving large-scale optimization problems. In this paper, we propose a fast sketching algorithm for least square problems regularized by convex or nonconvex regularization function…

Sparse Learning

Nonconvex Sparse Logistic Regression with Weakly Convex Regularization

2017-08-07 · Xinyue Shen, Yuantao Gu

In this work we propose to fit a sparse logistic regression model by a weakly convex regularized nonconvex optimization problem. The idea is based on the finding that a weakly convex function as an approximation of the $…

regression

Deterministic equivalent and error universality of deep random features learning

2023-02-01 · Dominik Schröder, Hugo Cui, Daniil Dmitriev, Bruno Loureiro

This manuscript considers the problem of learning a random Gaussian network function using a fully connected network with frozen intermediate layers and trainable readout layer. This problem can be seen as a natural gene…