Optimization
Efficient Prompt Optimization Through the Lens of Best Arm Identification
Most existing works follow the scheme of selecting from a pre-generated pool of candidate prompts.
Convexity and Lipschitz Hessian: Minimax Sample Complexity
We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds.
SuperDeepFool: a new fast and accurate minimal adversarial attack
However, existing methods for evaluating this robustness metric are either computationally expensive or not very accurate.
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Monte Carlo stopping rules in a manner that is both sample efficient and robust to estimation error.
Learning-Augmented Algorithms with Explicit Predictors
Recent advances in algorithmic design show how to utilize predictions obtained by machine learning models from past and present data.
Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
We further discuss the sample complexity for a desired approximation accuracy.