optimization methods
Techniques used to adjust the parameters of an AI model in order to minimize or maximize a specific objective function, often related to loss or reward.
- BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem
- Balancing Gradient and Hessian Queries in Non-Convex Optimization
- Constrained Optimization From a Control Perspective via Feedback Linearization
- Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
- Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
- Flat Channels to Infinity in Neural Loss Landscapes
- GPO: Learning from Critical Steps to Improve LLM Reasoning
- How Memory in Optimization Algorithms Implicitly Modifies the Loss
- MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
- Problem-Parameter-Free Decentralized Bilevel Optimization
- REINFORCE Converges to Optimal Policies with Any Learning Rate
- The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective