François Fleuret: clever O(T) memory trick, but it can't implement a real RNN

francoisfleuret · x · 2026-11-17

François Fleuret discusses a trick that cuts state memory from O(timesteps × statecomponents) to O(timesteps), letting you scale both dimensions. The catch: you can't rewrite a past state component with later information, so it can't implement a "real" RNN.

Related event: Fleuret Explains Memory Trick That Cuts State Storage Complexity by a Dimension(2 posts)→

Original post →

More from Research

Research channel →