An alternative complementarity formulation for primal-dual interior-point methods keeps linear systems spectrally bounded near the solution, enabling stable single-precision solves and differentiation for bilevel and end-to-end learning.
Wright.Numerical Optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
CONDITIONAL 2representative citing papers
FANoS-v2 augments momentum optimization with feedback-controlled thermostat damping, delivering small top-1 accuracy gains over AdamW on MNIST-scale tasks while increasing wall-clock time by roughly 50%.
citing papers explorer
-
A Differentiable Interior-Point Method in Single Precision
An alternative complementarity formulation for primal-dual interior-point methods keeps linear systems spectrally bounded near the solution, enabling stable single-precision solves and differentiation for bilevel and end-to-end learning.
-
FANoS-v2: Feedback-Controlled Momentum with Thermostat Damping for Lightweight Neural Optimization
FANoS-v2 augments momentum optimization with feedback-controlled thermostat damping, delivering small top-1 accuracy gains over AdamW on MNIST-scale tasks while increasing wall-clock time by roughly 50%.