paper-with-me

Papers

Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge

2021-11-02 · NeurIPS 2021 12 · Reda Ouhamma, Odalric Maillard, Vianney Perchet

We consider the problem of online linear regression in the stochastic setting. We derive high probability regret bounds for online ridge regression and the forward algorithm. This enables us to compare online regression algorithms more accurately and eliminate assumptions of bounded observations and predictions. Our study advocates for the use of the forward algorithm in lieu of ridge due to its enhanced bounds and robustness to the regularization parameter. Moreover, we explain how to integrate it in algorithms involving linear function approximation to remove a boundedness assumption without deteriorating theoretical bounds. We showcase this modification in linear bandit settings where it yields improved regret bounds. Last, we provide numerical experiments to illustrate our results and endorse our intuitions.

📄 PDF Abstract BibTeX arXiv:2111.01602

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

A Forward Propagation Algorithm for Online Optimization of Nonlinear Stochastic Differential Equations

2022-07-10 · Ziheng Wang, Justin Sirignano

Optimizing over the stationary distribution of stochastic differential equations (SDEs) is computationally challenging. A new forward propagation algorithm has been recently proposed for the online optimization of SDEs. …

Forward Reachability for Discrete-Time Nonlinear Stochastic Systems via Mixed-Monotonicity and Stochastic Order

2024-07-04 · Vignesh Sivaramakrishnan, Rosalyn A. Devonport, Murat Arcak, Meeko M. K. Oishi

We present a method to overapproximate forward stochastic reach sets of discrete-time, stochastic nonlinear systems with interval geometry. This is made possible by extending the theory of mixed-monotone systems to incor…

Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits

2022-02-28 · Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu

We study the problem of online generalized linear regression in the stochastic setting, where the label is generated from a generalized linear model with possibly unbounded additive noise. We provide a sharp analysis of …

regression

A Convergent Linear Regression Method for Forward-Backward Stochastic Differential Equations with Jumps

2018-05-15 · Tingting Ye, Liangliang Zhang

In this paper, we introduce a large class of convergent numerical methods, based on (linear) basis function regression technique, to approximate the solution to a forward-backward stochastic differential equation with ju…

regression

Sparsity regret bounds for individual sequences in online linear regression

2011-01-05 · Sébastien Gerchinovitz

We consider the problem of online linear regression on arbitrary deterministic sequences when the ambient dimension d can be much larger than the number of time rounds T. We introduce the notion of sparsity regret bound,…

regression