Ran Levinstein — accepted AI-conference papers

2025

Are Greedy Task Orderings Better Than Random in Continual Linear Regression?

Matan Tsipory, Ran Levinstein, Itay Evron, Mark Kong, Deanna Needell, Daniel Soudry

NeurIPS 2025poster

We analyze task orderings in continual learning for linear regression, assuming joint realizability of training data. We focus on orderings that greedily maximize dissimilarity between consecutive tasks, a concept briefly explored in prior work but still surrounded by open questions. Using tools fro…

Cited by 0 Source ↗Scholar ↗

2025

Optimal Rates in Continual Linear Regression via Increasing Regularization

Ran Levinstein, Amit Attia, Matan Schliserman, Uri Sherman, Daniel Soudry, Tomer Koren +1

NeurIPS 2025poster

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of $\Omega(1/k)$. However, prior work using an unregularized scheme…

Cited by 0 Source ↗Scholar ↗