JinraeKim/ParametrisedConvexApproximators.jl
A Julia package for parameterized convex approximators including parameterized log-sum-exp (PLSE) network.
This is a Julia package for researchers and practitioners working with optimization problems, especially those that involve making decisions under varying conditions. It allows you to build and train specialized neural networks called 'parameterized convex approximators.' You input data about your problem's conditions and decision variables, and it outputs an approximation of a convex function and, crucially, a way to quickly find the best decision for any given condition.
Use this if you need to rapidly solve many similar optimization problems where the optimal decision changes based on some input parameters, especially for amortized optimization or learning-based parametric optimization.
Not ideal if your optimization problem is not convex or if you only need to solve a single, static optimization problem rather than a parameterized one.
Stars
9
Forks
1
Language
Julia
License
MIT
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JinraeKim/ParametrisedConvexApproximators.jl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
CliMA/Oceananigans.jl
🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs
JuliaLang/julia
The Julia Programming Language
WassimTenachi/PhySO
Physical Symbolic Optimization
FluxML/Flux.jl
Relax! Flux is the ML library that doesn't make you tensor
EnzymeAD/Enzyme.jl
Julia bindings for the Enzyme automatic differentiator