paper-with-me

홈 › Papers

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 convergence guarantees of SGD-exp to the true parameter with up to $50\%$ Massart corruption rate, and with any corruption rate in the case of symmetric oblivious corruptions. This is the first convergence guarantee result for robust ReLU regression in the streaming setting, and it shows the improved convergence rate over previous robust methods for $L_1$ linear regression due to a choice of an exponentially decaying step size, known for its efficiency in practice. Our analysis is based on the drift analysis of a discrete stochastic process, which could also be interesting on its own.

📄 PDF Abstract BibTeX arXiv:2403.01204

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

Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks

2018-11-21 · Difan Zou, Yuan Cao, Dongruo Zhou, Quanquan Gu

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification proble…

Binary Classification

Streaming regularization parameter selection via stochastic gradient descent

2015-11-06 · Ricardo Pio Monti, Romy Lorenz, Robert Leech, Christoforos Anagnostopoulos 외

We propose a framework to perform streaming covariance selection. Our approach employs regularization constraints where a time-varying sparsity parameter is iteratively estimated via stochastic gradient descent. This all…

regression

The Statistics of Streaming Sparse Regression

2014-12-13 · Jacob Steinhardt, Stefan Wager, Percy Liang

We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresentable noise features, our algorithm reco…

regression

Heavy-tailed Streaming Statistical Estimation

2021-08-25 · Che-Ping Tsai, Adarsh Prasad, Sivaraman Balakrishnan, Pradeep Ravikumar

We consider the task of heavy-tailed statistical estimation given streaming $p$-dimensional samples. This could also be viewed as stochastic optimization under heavy-tailed distributions, with an additional $O(p)$ space …

regressionStochastic Optimization

When is a Convolutional Filter Easy To Learn?

2017-09-18 · ICLR 2018 1 · Simon S. Du, Jason D. Lee, Yuandong Tian

We analyze the convergence of (stochastic) gradient descent algorithm for learning a convolutional filter with Rectified Linear Unit (ReLU) activation function. Our analysis does not rely on any specific form of the inpu…