Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

Optimal Rates in Continual Linear Regression via Increasing Regularization

Authors: Ran Levinstein, Amit Attia, Matan Schliserman, Uri Sherman, Daniel Soudry, Tomer Koren, Itay Evron

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our paper proves that this gap can be narrowed, or even closed, using two frequently used regularization schemes... We prove that, under jointly realizable tasks, specific choices of fixed and increasing regularization strength schedules yield nearly-optimal and optimal rates of O(log k/k) and O(1/k), respectively. (From NeurIPS checklist, question 4: The paper does not include experiments.)
Researcher Affiliation Collaboration Department of Computer Science, Technion. Blavatnik School of Computer Science and AI, Tel Aviv University. Blavatnik School of Computer Science and AI, Tel Aviv University, and Google Research. Department of Electrical and Computer Engineering, Technion.
Pseudocode Yes Scheme 1 Regularized continual linear regression Input: Regression tasks {(Xm, ym)}M m=1, task ordering τ, regularization coefficients (λt)k t=1. Initialize w0 = 0d For each iteration t = 1, . . . , k: wt arg minw 1 2 Xτtw yτt 2 + λt 2 w wt 1 2 Output wk
Open Source Code No The paper does not include experiments requiring code.
Open Datasets No We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. (From NeurIPS checklist, question 4: The paper does not include experiments.)
Dataset Splits No The paper does not include experiments.
Hardware Specification No The paper does not include experiments.
Software Dependencies No The paper does not include experiments.
Experiment Setup No The paper does not include experiments.