1 citations · 1 across the 7 of their papers we have counts for
7 papers
A General and Streamlined Differentiable Optimization Framework
Andrew W. Rosemberg, Joaquim Dias Garcia, François Pacaud +5
Differentiating through constrained optimization problems is increasingly central to learning, control, and large-scale decision-making systems, yet practical integration remains c…
Nonlinear Optimization with GPU-Accelerated Neural Network Constraints
Robert Parker, Oscar Dowson, Nicole LoGiudice +2
We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neur…
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
Oscar Dowson, Robert B Parker, Russel Bent
We present \texttt{MathOptAI.jl}, an open-source Julia library for embedding trained machine learning predictors into a JuMP model. \texttt{MathOptAI.jl} can embed a wide variety o…
Tightening optimality gap with confidence through conformal prediction
Miao Li, Michael Klamkin, Russell Bent +1
Decision makers routinely use constrained optimization technology to plan and operate complex systems like global supply chains or power grids. In this context, practitioners must…
Transient Stability-Constrained OPF: Neural Network Surrogate Models and Pricing Stability
Manuel Garcia, Nicole LoGiudice, Robert Parker +1
A Transient Stability-Constrained Optimal Power Flow (TSC-OPF) problem is proposed that enforces frequency stability constraints using Neural Network (NN) surrogate models. NNs are…
Variable aggregation for nonlinear optimization problems
Sakshi Naik, Lorenz Biegler, Russell Bent +1
Variable aggregation has been largely studied as an important pre-solve algorithm for optimization of linear and mixed-integer programs. Although some nonlinear solvers and algebra…
Formulations and scalability of neural network surrogates in nonlinear optimization problems
Robert B. Parker, Oscar Dowson, Nicole LoGiudice +2
We compare full-space, reduced-space, and gray-box formulations for representing trained neural networks in nonlinear constrained optimization problems. We test these formulations…