paper-with-me

홈 › Papers

Online Forgetting Process for Linear Regression Models

2020-12-03 · Yuantong Li, Chi-Hua Wang, Guang Cheng

Motivated by the EU's "Right To Be Forgotten" regulation, we initiate a study of statistical data deletion problems where users' data are accessible only for a limited period of time. This setting is formulated as an online supervised learning task with \textit{constant memory limit}. We propose a deletion-aware algorithm \texttt{FIFD-OLS} for the low dimensional case, and witness a catastrophic rank swinging phenomenon due to the data deletion operation, which leads to statistical inefficiency. As a remedy, we propose the \texttt{FIFD-Adaptive Ridge} algorithm with a novel online regularization scheme, that effectively offsets the uncertainty from deletion. In theory, we provide the cumulative regret upper bound for both online forgetting algorithms. In the experiment, we showed \texttt{FIFD-Adaptive Ridge} outperforms the ridge regression algorithm with fixed regularization level, and hopefully sheds some light on more complex statistical models.

📄 PDF Abstract BibTeX arXiv:2012.01668

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Model-free Online Learning for the Kalman Filter: Forgetting Factor and Logarithmic Regret

2025-05-13 · Jiachen Qian, Yang Zheng

We consider the problem of online prediction for an unknown, non-explosive linear stochastic system. With a known system model, the optimal predictor is the celebrated Kalman filter. In the case of unknown systems, exist…

Inductive Biasregression

Adaptive observer of state variables of a nonlinear time varying system with unknown constant parameters

2023-05-24 · Olga Kozachek, Alexey Bobtsov, Nikolay Nikolaev

The paper proposes an adaptive observer of the state vector of a nonlinear time varying system based on measurements of the output variable. The problem is solved under the assumption that the control matrix (vector) and…

parameter estimationregression

Online Limited Memory Neural-Linear Bandits

2021-01-01 · Tom Zahavy, Ofir Nabati, Leor Cohen, Shie Mannor

We study neural-linear bandits for solving problems where both exploration and representation learning play an important role. Neural-linear bandits leverage the representation power of deep neural networks and combine i…

Efficient ExplorationMulti-Armed BanditsRepresentation LearningSentiment Analysis

Gaussian Gated Linear Networks

2020-06-10 · NeurIPS 2020 12 · David Budden, Adam Marblestone, Eren Sezener, Tor Lattimore 외

We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Instead of using backpropagation to learn features, GLNs have a distributed and local credit…

DenoisingDensity EstimationMulti-Armed Banditsregression

The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model

2024-01-23 · Daniel Goldfarb, Itay Evron, Nir Weinberger, Daniel Soudry 외

In continual learning, catastrophic forgetting is affected by multiple aspects of the tasks. Previous works have analyzed separately how forgetting is affected by either task similarity or overparameterization. In contra…

Continual Learningregression