algorithm performance
A metric for assessing how effectively an algorithm achieves its intended objectives, often evaluated using criteria like accuracy, speed, and scalability. It can vary widely depending on the dataset and problem domain.
- A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
- Balanced Active Inference
- Constrained Best Arm Identification
- Efficient Last-Iterate Convergence in Solving Extensive-Form Games
- Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles
- GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
- Generalized Top-k Mallows Model for Ranked Choices
- Horizon Reduction Makes RL Scalable
- Instance-Optimality for Private KL Distribution Estimation
- Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo
- Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
- Sparse Optimistic Information Directed Sampling