Search Results for author:
Found 5 papers, 3 papers with code
Localized Zeroth-Order Prompt Optimization
Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks.
Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers
We perform instruction optimization for ChatGPT and use extensive experiments to show that our INSTINCT consistently outperforms the existing methods in different tasks, such as in various instruction induction tasks and the task of improving the zero-shot chain-of-thought instruction.
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search
As a consequence, (a) the relationships among these metrics are unclear, (b) there is no theoretical interpretation for their empirical performances, and (c) there may exist untapped potential in existing training-free NAS, which probably can be unveiled through a unified theoretical understanding.
Validation Free and Replication Robust Volume-based Data Valuation
We observe that the diversity of the data points is an inherent property of the dataset that is independent of validation.
Trusted-Maximizers Entropy Search for Efficient Bayesian Optimization
Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function.
