Quasipolynomial algorithm finds approximate fixed points of ℓ∞ contractions
The method geometrically shrinks the search region and implies simple stochastic games can be solved in quasipolynomial time.
Stories per day · 30 days
Relatedhuginn2kv-cache2algorithms1chua1complexity1dynamical-systems1efficiency1inference1language-models1looped-language-models1looped-models1model-reduction1piecewise-linear1recurrent-neural-networks1reinforcement-learning1stochastic-games1theoretical-cs1
4 stories, newest first · one card per story
Stories tagged #fixed-points
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
Looped language models near fixed points cut training and decode cost via learned depth priors and orthogonal injection.
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
Learned depth priors and orthogonal injection improve looped language models while enabling cheaper KV sharing.
From Redundancy to Minimality: Fixed-Point-Guided Hierarchical Reduction of Learned Piecewise-Linear Dynamics
Fixed-point-guided reduction turns redundant AL-RNNs into minimal dynamics, lifting Chua success from 20% to 71%.