Search Results for author:
Found 7 papers, 3 papers with code
Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization
In this work, we introduce a novel problem setting that departs from this paradigm: finding a smaller set of K solutions, where K < T, that collectively "covers" the T objectives.
Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting
In addition, we propose a novel strategy called chain-of-specification (CoS) prompting for improving diversity by first having the LLM generate a specification encoding one instance of structural features, and then prompting the LLM to generate text that satisfies these features; notably, our strategy works with blackbox LLMs.
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes.
Generative Adversarial Model-Based Optimization via Source Critic Regularization
Offline model-based optimization seeks to optimize against a learned surrogate model without querying the true oracle objective function during optimization.
Inverse Protein Folding Using Deep Bayesian Optimization
Furthermore, it is challenging to adapt pure generative approaches to other settings, e. g., when constraints exist.
Learning Performance-Improving Code Edits
Next, we propose a broad range of adaptation strategies for code optimization; for prompting, these include retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
Cyclical Kernel Adaptive Metropolis
We propose cKAM, cyclical Kernel Adaptive Metropolis, which incorporates a cyclical stepsize scheme to allow control for exploration and sampling.
