Sublinear neural networks parametrize convex sets by learning their support and gauge functions, backed by a universal approximation theorem and tested on shape optimization tasks.
Cambridge university press, 2004
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
GECKO traverses level sets of the quantum control landscape using SU group geometry to improve pulse quality metrics while preserving the target unitary to first order.
Physics-augmented neural networks act as stable, thermodynamically consistent surrogates for microscale problems, enabling simultaneous optimization of macroscale material layout and microscale descriptors in nonlinear finite-strain anisotropic hyperelastic structures.
Proposes ε-Fair-MTSP (MISOCP) and Δ-Fair-MTSP (MILP) as parametric alternatives to min-max MTSP with optimality guarantees and Pareto-front extraction for bi-objective routing.
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
citing papers explorer
-
Parametrizing Convex Sets Using Sublinear Neural Networks
Sublinear neural networks parametrize convex sets by learning their support and gauge functions, backed by a universal approximation theorem and tested on shape optimization tasks.
-
Pulse Quality Optimisation in Quantum Optimal Control
GECKO traverses level sets of the quantum control landscape using SU group geometry to improve pulse quality metrics while preserving the target unitary to first order.
-
Multiscale topology optimization of compressible and nearly incompressible anisotropic hyperelastic structures using physics-augmented neural networks
Physics-augmented neural networks act as stable, thermodynamically consistent surrogates for microscale problems, enabling simultaneous optimization of macroscale material layout and microscale descriptors in nonlinear finite-strain anisotropic hyperelastic structures.
-
Equitable Routing--Rethinking the Multiple Traveling Salesman Problem
Proposes ε-Fair-MTSP (MISOCP) and Δ-Fair-MTSP (MILP) as parametric alternatives to min-max MTSP with optimality guarantees and Pareto-front extraction for bi-objective routing.
-
When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.