Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Monotone Optimisation with Learned Projections

About

Monotone optimisation problems admit specialised global solvers such as the Polyblock Outer Approximation (POA) algorithm, but these methods typically require explicit objective and constraint functions. In many applications, these functions are only available through data, making POA difficult to apply directly. We introduce an algorithm-aware learning approach that integrates learned models into POA by directly predicting its projection primitive via the radial inverse, avoiding the costly bisection procedure used in standard POA. We propose Homogeneous-Monotone Radial Inverse (HM-RI) networks, structured neural architectures that enforce key monotonicity and homogeneity properties, enabling fast projection estimation. We provide a theoretical characterisation of radial inverse functions and show that, under mild structural conditions, a HM-RI predictor corresponds to the radial inverse of a valid set of monotone constraints. To reduce training overhead, we further develop relaxed monotonicity conditions that remain compatible with POA. Across multiple monotone optimisation benchmarks (indefinite quadratic programming, multiplicative programming, and transmit power optimisation), our approach yields substantial speed-ups in comparison to direct function estimation while maintaining strong solution quality, outperforming baselines that do not exploit monotonic structure.

Ahmed Rashwan, Keith Briggs, Chris Budd, Lisa Kreusser• 2026

Related benchmarks

TaskDatasetResultRank
Monotone OptimisationQuadratic Unlimited data regime
P-Obj0.071
8
Monotone OptimisationMultiplicative Unlimited data regime
P-Obj Score0.151
8
Monotone OptimisationPower-law Unlimited data regime
P-Obj Score-0.95
8
Monotone OptimisationUMa Unlimited data regime
P-Obj Score-1.02
8
Monotone OptimisationQuadratic Limited data regime
P-Obj.0.056
5
Monotone OptimisationPower-law Limited data regime
P-Obj.-1.65
5
Monotone OptimisationMultiplicative Limited data regime
P-Obj.0.145
5
Monotone OptimisationUMa Limited data regime
P-Obj-1.4
5
Monotone OptimizationQuadratic Unlimited regime
Mean Runtime (s)0.91
5
Monotone OptimizationMultiplicative Unlimited regime
Mean Runtime (s)1.85
5
Showing 10 of 12 rows

Other info

Follow for update