Constrained Learning

Constrained learning focuses on training machine learning models that satisfy specific requirements beyond accuracy, such as fairness, robustness, or resource limitations (e.g., memory, computation time). Current research emphasizes developing algorithms and frameworks that efficiently handle various constraint types, including convex and non-convex constraints, often employing techniques like Lagrangian duality, augmented Lagrangian methods, and primal-dual approaches within diverse model architectures (e.g., neural networks, gradient boosting machines). This field is crucial for deploying reliable and responsible machine learning systems in real-world applications, addressing issues of safety, fairness, and efficiency in domains ranging from healthcare to autonomous systems.

Papers

October 31, 2024

Projected Neural Differential Equations for Learning Constrained Dynamics
Alistair White, Anna Büttner, Maximilian Gelbrecht, Valentin Duruisseaux, Niki Kilbertus, Frank Hellmann, Niklas Boers
Dynamical System Differential Equation Chaotic System Constrained Learning Manifold Constraint

October 30, 2024

Solving Differential Equations with Constrained Learning
Viggo Moro, Luiz F. O. Chamon
Neural Operator Differential Equation Constrained Learning

October 22, 2024

Hierarchical Upper Confidence Bounds for Constrained Online Learning
Ali Baheri
Multi Armed Bandit Regret Bound Sequential Decision Confidence Bound Contextual Bandit Problem Constrained Learning Hierarchical Decision

September 28, 2024

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
Xinrui Wang, Chuanxing Geng, Wenhai Wan, Shaoyuan Li, Songcan Chen
Technical Challenge Catastrophic Forgetting Anti Forgetting Online Continual Learning Worst Case User Throughput Constrained Learning Sparse Classification High Myopia

September 26, 2024

Spatial embedding promotes a specific form of modularity with low entropy and heterogeneous spectral dynamics
Cornelia Sheeran, Andrew S. Ham, Duncan E. Astle, Jascha Achterberg, Danyal Akarca
Recurrent Neural Network Spatial Domain Modularity Function Computational Neuroscience Shannon Entropy Neural Network Weight Neural Computation Constrained Learning

August 23, 2024

Data-Centric Approach to Constrained Machine Learning: A Case Study on Conway's Game of Life
Anton Bibin, Anton Dereventsov
Data Centric Machine Learning Application Dynamic Network Game Content Domain Expert Constrained Learning Real World Constraint

May 15, 2024

C-Learner: Constrained Learning for Causal Inference and Semiparametric Statistics
Tiffany Tianhui Cai, Yuri Fonseca, Kaiwen Hou, Hongseok Namkoong
Causal Inference Causal Effect Estimation Semi Parametric Optimal Estimation Constrained Learning Nuisance Parameter C Program

April 15, 2024

Statistical learning for constrained functional parameters in infinite-dimensional models with applications in fair machine learning
Razieh Nabi, Nima S. Hejazi, Mark J. van der Laan, David Benkeser
Financial Application Fairness Constraint Fair Machine Learning Statistical Learning Constrained Learning Functional Constrained Optimization

March 18, 2024

Near-Optimal Solutions of Constrained Learning Problems
Juan Elenter, Luiz F. O. Chamon, Alejandro Ribeiro
Constrained Learning Dual Learning Dual Optimization Dual Ascent

March 6, 2024

Learning Constrained Optimization with Deep Augmented Lagrangian Methods
James Kotary, Ferdinando Fioretto
Constrained Optimization Constrained Learning Lagrangian Method Dual Ascent Dual Feasible Solution

December 13, 2023

PySCIPOpt-ML: Embedding Trained Machine Learning Models into Mixed-Integer Programs
Mark Turner, Antonia Chmiela, Thorsten Koch, Michael Winkler
Machine Learning Machine Learning Model Mixed Integer Constrained Learning Scikit Learn

December 9, 2023

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen
Hao Zhang, Fang Li, Lu Qi, Ming-Hsuan Yang, Narendra Ahuja
Segmentation Based Approach Structure Learning Zero Shot Semantic Segmentation Constrained Learning Distribution Segmentation

November 26, 2023

ConstraintMatch for Semi-constrained Clustering
Jann Goschenhofer, Bernd Bischl, Zsolt Kira
Self Supervised Semi Supervised Learning Constrained Learning Constrained Clustering Label Constraint Constraint Compliance

October 16, 2023

Federated Learning with Convex Global and Local Constraints
Chuan He, Le Peng, Ju Sun
Federated Learning Convex Function Constrained Learning Convex Constraint Nonconvex Constraint

September 29, 2023

Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
Juan Elenter, Navid NaderiAlizadeh, Tara Javidi, Alejandro Ribeiro
Continual LEArning Continual Learning Core Stability Primal Dual Plasticity Rule Continual Learning Benchmark Constrained Learning Memory Based Memory Allocation

August 21, 2023

GBM-based Bregman Proximal Algorithms for Constrained Learning
Zhenwei Lin, Qi Deng
Constrained Learning Bregman Information Bregman Proximal

June 9, 2023

Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach
Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Xingchen Wan, Vu Nguyen, Harald Oberhauser, Michael A. Osborne
Active Learning Bayesian Optimization Constrained Learning Front Diverse Batch

June 4, 2023

Resilient Constrained Learning
Ignacio Hounie, Alejandro Ribeiro, Luiz F. O. Chamon
Heterogeneous Federated Learning Generalization Guarantee Constrained Learning Resilient Constrained Learning

February 22, 2023

Quantized Low-Rank Multivariate Regression with Random Dithering
Junren Chen, Yueqi Wang, Michael K. Ng
Low Rank Constrained Learning Multivariate Regression Uniform Quantization Lasso Estimator

February 2, 2023

Online Learning under Budget and ROI Constraints via Weak Adaptivity
Matteo Castiglioni, Andrea Celli, Christian Kroer
Adaptive Importance Online Learning Primal Dual Local Authority Budget Constrained Learning Adaptive Regret Cost Constraint Online Learning Problem Offline Optimization