empirical demonstration
The process of validating an AI model or algorithm through real-world experiments or data. It ensures that theoretical claims about performance can be observed in practice.
- A Provable Approach for End-to-End Safe Reinforcement Learning
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
- A Temporal Difference Method for Stochastic Continuous Dynamics
- Activation-Informed Merging of Large Language Models
- Beyond Prediction: Managing the Repercussions of Machine Learning Applications
- CellVerse: Do Large Language Models Really Understand Cell Biology?
- Composition and Alignment of Diffusion Models using Constrained Learning
- Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
- Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
- Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth
- Evolutionary Prediction Games
- Improving the Generation and Evaluation of Synthetic Data for Downstream Medical Causal Inference
- ProDAG: Projected Variational Inference for Directed Acyclic Graphs
- Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
- Sparse Optimistic Information Directed Sampling
- Strategic Classification with Non-Linear Classifiers
- The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
- Uncertainty Estimation by Flexible Evidential Deep Learning