paper-with-me

홈 › Papers

ReLU Regression with Massart Noise

2021-09-10 · NeurIPS 2021 12 · Ilias Diakonikolas, Jongho Park, Christos Tzamos

We study the fundamental problem of ReLU regression, where the goal is to fit Rectified Linear Units (ReLUs) to data. This supervised learning task is efficiently solvable in the realizable setting, but is known to be computationally hard with adversarial label noise. In this work, we focus on ReLU regression in the Massart noise model, a natural and well-studied semi-random noise model. In this model, the label of every point is generated according to a function in the class, but an adversary is allowed to change this value arbitrarily with some probability, which is {\em at most} $\eta < 1/2$. We develop an efficient algorithm that achieves exact parameter recovery in this model under mild anti-concentration assumptions on the underlying distribution. Such assumptions are necessary for exact recovery to be information-theoretically possible. We demonstrate that our algorithm significantly outperforms naive applications of $\ell_1$ and $\ell_2$ regression on both synthetic and real data.

📄 PDF Abstract BibTeX arXiv:2109.04623

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Stochastic gradient descent for streaming linear and rectified linear systems with adversarial corruptions

2024-03-02 · Halyun Jeong, Deanna Needell, Elizaveta Rebrova

We propose SGD-exp, a stochastic gradient descent approach for linear and ReLU regressions under Massart noise (adversarial semi-random corruption model) for the fully streaming setting. We show novel nearly linear conve…

regression

SQ Lower Bounds for Learning Single Neurons with Massart Noise

2022-10-18 · Ilias Diakonikolas, Daniel M. Kane, Lisheng Ren, Yuxin Sun

We study the problem of PAC learning a single neuron in the presence of Massart noise. Specifically, for a known activation function $f: \mathbb{R} \to \mathbb{R}$, the learner is given access to labeled examples $(\math…

PAC learning

Boosting in the Presence of Massart Noise

2021-06-14 · Ilias Diakonikolas, Russell Impagliazzo, Daniel Kane, Rex Lei 외

We study the problem of boosting the accuracy of a weak learner in the (distribution-independent) PAC model with Massart noise. In the Massart noise model, the label of each example $x$ is independently misclassified wit…

Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise

2021-02-10 · Chicheng Zhang, Yinan Li

We give a computationally-efficient PAC active learning algorithm for $d$-dimensional homogeneous halfspaces that can tolerate Massart noise (Massart and N\'ed\'elec, 2006) and Tsybakov noise (Tsybakov, 2004). Specialize…

Active Learning

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random

2025-01-16 · Gautam Chandrasekaran, Vasilis Kontonis, Konstantinos Stavropoulos, Kevin Tian

We study the problem of PAC learning $\gamma$-margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the Perspectron, that has sample complexity $\widetilde{O}((\epsilon\gamma)^{-2})$ and ac…

PAC learning