robust optimization
An approach to optimization that seeks solutions that are resilient to uncertainties and variations in data, ensuring satisfactory performance even under worst-case scenarios.
- ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
- Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
- GLID$^2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design
- Leveraging robust optimization for llm alignment under distribution shifts
- Noisy Multi-Label Learning through Co-Occurrence-Aware Diffusion
- Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
- Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
- RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models
- Robust Sampling for Active Statistical Inference
- Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks
- Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
- Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics