TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
-
Updated
May 24, 2024 - Python
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
Ph.D daily work log
This repository contains the source code used in the computational experiments of the paper: Learning to Solve Bilevel Programs with Binary Tender (ICLR 2024, available on OpenReview.net).
Benchmark for bi-level optimization solvers
MetaOpt: Towards efficient heuristic design with quantifiable and confident performance
Code accompanying the paper "Heuristic Methods for Mixed-Integer, Linear, and Gamma-Robust Bilevel Problems" (with Ivana Ljubic and Martin Schmidt)
Metaheuristics for solving bilevel optimization problems.
Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization
A library for differentiable nonlinear optimization
BROT is a self-adaptation algorithm that trade offs traffic mitigation and shortest path length on transportation networks
RECKONING is a bi-level learning algorithm that improves language models' reasoning ability by folding contextual knowledge into parametric knowledge through back-propagation.
Solver for Bilevel Parameter Learning using a MPCC reformulation
Nonsmooth Bilevel Parameter Learning of Imaging Variational Models
Thousands of bibliographic references on bi-level optimization.
A Julia package for adaptive proximal gradient for convex bilevel optimization
Julia library for the Network Pricing Problem (NPP)
C++/python codes for contact-rich trajectory optimization.
In this repository, we implement Targeted Meta-Learning (or Targeted Data-driven Regularization) architecture for training machine learning models with biased data.
In this repository, we implement Targeted Meta-Learning (or Targeted Data-driven Regularization) architecture for training machine learning models with biased data.
Implementation and examples from Trajectory Optimization with Optimization-Based Dynamics https://arxiv.org/abs/2109.04928
Add a description, image, and links to the bilevel-optimization topic page so that developers can more easily learn about it.
To associate your repository with the bilevel-optimization topic, visit your repo's landing page and select "manage topics."