Related papers: Python Wrapper for Simulating Multi-Fidelity Optim…

Deep learning (DL) models are piquing high interest and scaling at an unprecedented rate. To this end, a handful of tiled accelerators have been proposed to support such large-scale training tasks. However, these accelerators often…

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address…

Software systems increasingly include AI components based on deep learning (DL). Reliable testing of such systems requires near-perfect test-input validity and label accuracy, with minimal human effort. Yet, the DL community has largely…

Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency. Despite its impressive success so far, it is still unclear how to appropriately schedule the important hyperparameters to achieve…

We introduce ordered transfer hyperparameter optimisation (OTHPO), a version of transfer learning for hyperparameter optimisation (HPO) where the tasks follow a sequential order. Unlike for state-of-the-art transfer HPO, the assumption is…

Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-exploitation trade-off. Existing approaches address this trade-off in rigid ways:…

The increasing demand for democratizing machine learning algorithms calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters which can cause a large variation in the training…

Hyperparameter optimization is critical in modern machine learning, requiring expert knowledge, numerous trials, and high computational and human resources. Despite the advancements in Automated Machine Learning (AutoML), challenges in…

Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks.…

Hyperparameter optimization (HPO) is a crucial step in achieving strong predictive performance. Yet, the impact of individual hyperparameters on model generalization is highly context-dependent, prohibiting a one-size-fits-all solution and…

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

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…

Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level performance,…

Choosing a suitable ML model is a complex task that can depend on several objectives, e.g., accuracy, fairness, or energy consumption. In practice, this requires trading off multiple, often competing, objectives through multi-objective…

Hyperparameters play a critical role in the performances of many machine learning methods. Determining their best settings or Hyperparameter Optimization (HPO) faces difficulties presented by the large number of hyperparameters as well as…

Reinforcement Learning with Human Feedback (RLHF) has revolutionized language modeling by aligning models with human preferences. However, the RL stage, Proximal Policy Optimization (PPO), requires over 3x the memory of Supervised…

In this paper, we address the problem of cost-sensitive multi-fidelity Bayesian Optimization (BO) for efficient hyperparameter optimization (HPO). Specifically, we assume a scenario where users want to early-stop the BO when the performance…

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves. This makes it difficult to understand the decision process which leads to the selected configuration, reduces…

The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters simultaneously. In this work, we introduce a new class of HPO…