optimization algorithm
An optimization algorithm is a method used to adjust the parameters of an AI model in order to minimize a loss function. Common optimization algorithms include SGD, Adam, and RMSprop, each with unique strengths for different types of problems.
- Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
- Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization
- Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
- MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention
- Robust Explanations of Graph Neural Networks via Graph Curvatures
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
- The Rich and the Simple: On the Implicit Bias of Adam and SGD