Related papers: Improving Accuracy of Interpretability Measures in…

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Selecting the optimal combination of a machine learning (ML) algorithm and its hyper-parameters is crucial for the development of high-performance ML systems. However, since the combination of ML algorithms and hyper-parameters is enormous,…

Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications. Surrogate Optimization (SO) is a common resolution, yet its proprietary nature introduced by the…

Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how…

The performance of fine-tuning pre-trained language models largely depends on the hyperparameter configuration. In this paper, we investigate the performance of modern hyperparameter optimization methods (HPO) on fine-tuning pre-trained…

Model-based optimization approaches for monitoring and control, such as model predictive control and optimal state and parameter estimation, have been used for decades in many engineering applications. Models describing the dynamics,…

Bayesian optimization (BO) has gained attention as an efficient algorithm for black-box optimization of expensive-to-evaluate systems, where the BO algorithm iteratively queries the system and suggests new trials based on a probabilistic…

In machine learning algorithm design, there exists a trade-off between the interpretability and performance of the algorithm. In general, algorithms which are simpler and easier for humans to comprehend tend to show worse performance than…

Prompt optimization methods have demonstrated significant effectiveness in aligning black-box large language models (LLMs). In parallel, inference scaling strategies such as Best-of-N Sampling and Majority Voting have likewise been shown to…

While sample efficiency is the main motive for use of Bayesian optimisation when black-box functions are expensive to evaluate, the standard approach based on type II maximum likelihood (ML-II) may fail and result in disappointing…

Machine learning (ML) techniques applied to quantum many-body physics have emerged as a new research field. While the numerical power of this approach is undeniable, the most expressive ML algorithms, such as neural networks, are black…

Gaussian process (GP) based Bayesian optimization (BO) is a powerful method for optimizing black-box functions efficiently. The practical performance and theoretical guarantees of this approach depend on having the correct GP hyperparameter…

Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters. However, these online HPO algorithms still require running evaluation on a set of validation…

Given a Hyperparameter Optimization(HPO) problem, how to design an algorithm to find optimal configurations efficiently? Bayesian Optimization(BO) and the multi-fidelity BO methods employ surrogate models to sample configurations based on…

Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged as a way to leverage knowledge from related tasks to optimize…

From self-driving vehicles and back-flipping robots to virtual assistants who book our next appointment at the hair salon or at that restaurant for dinner - machine learning systems are becoming increasingly ubiquitous. The main reason for…

Hyperparameter optimization (HPO) is known to be costly in deep learning, especially when leveraging automated approaches. Most of the existing automated HPO methods are accuracy-based, i.e., accuracy metrics are used to guide the trials of…

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…

Optimization of LLM training and inference configurations, such as hyperparameters, data mixtures, and prompts, is critical to performance, but it is often approached heuristically in practice, leading to potentially suboptimal outcomes. By…

Mathematical reasoning is a fundamental capability for large language models (LLMs), yet achieving high performance in this domain remains a significant challenge. The auto-regressive generation process often makes LLMs susceptible to…