Where Should Learning Live? Regret Analysis for Text, Parameter, and Joint Adaptation
stat.ML, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- WHALE: A Simple Recipe for Joint Harness-Weight Optimization
- MemGPT: Towards LLMs as Operating Systems
- Learning, Fast and Slow: Towards LLMs That Adapt Continually
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference