Optimization was one of the top five topics at NeurIPS 2024, reflecting a clear trend of increasing interest in this area compared to previous years. While optimization in machine learning often focuses on specific tasks like training neural networks (using algorithms such as gradient descent and its variants), my focus here is on optimization in a broader sense.
This includes research exploring the use of AI methods for classical optimization problems, bridging the gap between traditional optimization techniques and modern AI-driven approaches. Below is a curated list of papers that stood out in this domain.
Non-Linear Programming
- Dual Lagrangian Learning for Conic Optimization
Poster | Paper - BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
Poster | Paper - IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Poster | Paper
Combinatorial Optimization
- Controlling Continuous Relaxation for Combinatorial Optimization
Poster | Paper - Learning to Handle Complex Constraints for Vehicle Routing Problems
Poster | Paper - ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Poster | Paper
Stochastic and Contextual Optimization
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
Poster | Paper - Improved Algorithms for Contextual Dynamic Pricing
Poster | Paper - Conformal Inverse Optimization
Poster | Paper - Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs
Poster | Paper - There is No Silver Bullet: Benchmarking Methods in Predictive Combinatorial Optimization
Poster | Paper - Regret Minimization in Stackelberg Games with Side Information
Poster | Paper
Linear Programming and MILP
- GLinSAT: The General Linear Satisfiability Neural Network Layer
Poster | Paper - SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization
Poster | Paper - Learning Generalized Linear Programming Value Functions
Poster | Paper - Rethinking the Capacity of Graph Neural Networks for Branching Strategy
Poster | Paper - On the Power of Small-Size Graph Neural Networks for Linear Programming
Poster | Paper
Application-Specific Optimization
- Randomized Sparse Matrix Compression for Large-Scale Constrained Optimization in Cancer Radiotherapy
Poster | Paper - DistrictNet: Decision-Aware Learning for Geographical Districting
Poster | Paper - Approximately Pareto-Optimal Solutions for Bi-Objective k-Clustering
Poster | Paper - Autoregressive Policy Optimization for Constrained Allocation Tasks
Poster | Paper
New Perspectives
- Optimization Algorithm Design via Electric Circuits
Poster | Paper - FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
Poster | Paper
Optimization for Machine Learning
While there are many works related to optimization in machine learning, the following papers stood out for their relevance to OR techniques.
- Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
Poster | Paper - Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
Poster | Paper - Can Learned Optimization Make Reinforcement Learning Less Difficult?
Poster | Paper - Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
Poster | Paper - SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
Poster | Paper - ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making
Poster | Paper - Adaptive Proximal Gradient Method for Convex Optimization
Poster | Paper - Functional Bilevel Optimization for Machine Learning
Poster | Paper - First-Order Minimax Bilevel Optimization
Poster | Paper