constrained optimization
An optimization problem where the solution must satisfy certain restrictions or constraints. In AI, this is commonly encountered when training models under specific resource limits or performance criteria.
- $O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization
- Autoencoding Random Forests
- Composition and Alignment of Diffusion Models using Constrained Learning
- Constrained Diffusers for Safe Planning and Control
- Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models
- Constrained Optimization From a Control Perspective via Feedback Linearization
- DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
- Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
- FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
- LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
- Learning (Approximately) Equivariant Networks via Constrained Optimization
- Learning (Approximately) Equivariant Networks via Constrained Optimization
- Learning with Statistical Equality Constraints
- MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions
- Near-Optimal Sample Complexity for Online Constrained MDPs
- Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
- Risk-aware Direct Preference Optimization under Nested Risk Measure
- SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function
- Taxonomy of reduction matrices for Graph Coarsening
- Training-Free Constrained Generation With Stable Diffusion Models