For average-reward MDPs with total-variation uncertainty, the minimax sample complexity is SA/epsilon^2 times min{H0,Hsigma}, with an extra SA sigma Hsigma^2/epsilon^2 term in the low-tolerance regime, and the paper provides matching algorithms.
Ada-LISTA: Learned Solvers Adaptive to Varying Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance. Nevertheless, as opposed to non-learned solvers, these networks are trained on a certain dictionary, and therefore they are inapplicable for varying model scenarios. This work introduces an adaptive learned solver, termed Ada-LISTA, which receives pairs of signals and their corresponding dictionaries as inputs, and learns a universal architecture to serve them all. We prove that this scheme is guaranteed to solve sparse coding in linear rate for varying models, including dictionary perturbations and permutations. We also provide an extensive numerical study demonstrating its practical adaptation capabilities. Finally, we deploy Ada-LISTA to natural image inpainting, where the patch-masks vary spatially, thus requiring such an adaptation.
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions
For average-reward MDPs with total-variation uncertainty, the minimax sample complexity is SA/epsilon^2 times min{H0,Hsigma}, with an extra SA sigma Hsigma^2/epsilon^2 term in the low-tolerance regime, and the paper provides matching algorithms.