loss minimization
The process of adjusting a model's parameters to reduce a loss function, a numerical representation of the difference between predicted and actual outcomes, central to the training of machine learning models.
- Accelerating Optimization via Differentiable Stopping Time
- Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
- Improved Bounds for Swap Multicalibration and Swap Omniprediction
- Machine Unlearning under Overparameterization
- RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models