Matan Tsipory

[Matan Tsipory @tsipory]

@itayevron @ranlevinstein [6/6]
Are Greedy Task Orderings Better Than Random in Continual Linear Regression?

With my collaborators:
*Tsipory, *Levinstein, *Evron, *Kong, Needell and Soudry.

#NeurIPS #NeurIPS2025

Full paper:
https://t.co/HPASNh2wIw

Poster info:
https://t.co/4DG9gMoACY

[Matan Tsipory @tsipory]

[1/6] Tomorrow (Thursday) at #NeurIPS:
Are Greedy Task Orderings Better Than Random in Continual Linear Regression?

Q: Do models learn better when consecutive tasks are similar or dissimilar?
A: Our analysis suggests that they should be dissimilar!

https://t.co/HPASNh2wIw

[Matan Tsipory @tsipory]

@itayevron @ranlevinstein [5/6]
However, these failure modes disappear when we allow task repetition or use greedy-then-random orderings.

In conclusion, we now understand that dissimilarity-guided orderings typically converge faster, and that a bit of randomness can prevent pathological failures.

[Itay Evron @itayevron]

[1/5] Next week at #NeurIPS
*Optimal Rates in Continual Linear Regression via Increasing Regularization*

In the brain, ageing naturally reduces synaptic plasticity.
Our theory suggests continual learning models may benefit from a similar mechanism!

https://t.co/9tyYYZbpT5