Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach

• URL: http://arxiv.org/abs/2206.12708v1
• Date: Sat, 25 Jun 2022 18:44:06 GMT
• Title: Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach
• Authors: Syrine Belakaria, Rishit Sheth, Janardhan Rao Doppa, Nicolo Fusi
• Abstract summary: This paper proposes a novel approach referred to as Budget-Aware Planning for Iterative learners (BAPI) to solve HPO problems under a constrained cost budget. Experiments on diverse HPO benchmarks for iterative learners show that BAPI performs better than state-of-the-art baselines in most of the cases.
• Score: 31.918476422203412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training. Many methods for hyperparameter optimization (HPO) of iterative learners including DNNs attempt to solve this problem by querying and learning a response surface while searching for the optimum of that surface. However, many of these methods make myopic queries, do not consider prior knowledge about the response structure, and/or perform biased cost-aware search, all of which exacerbate identifying the best-performing model when a total cost budget is specified. This paper proposes a novel approach referred to as Budget-Aware Planning for Iterative Learners (BAPI) to solve HPO problems under a constrained cost budget. BAPI is an efficient non-myopic Bayesian optimization solution that accounts for the budget and leverages the prior knowledge about the objective function and cost function to select better configurations and to take more informed decisions during the evaluation (training). Experiments on diverse HPO benchmarks for iterative learners show that BAPI performs better than state-of-the-art baselines in most of the cases.

Related papers

• Cost-Sensitive Multi-Fidelity Bayesian Optimization with Transfer of Learning Curve Extrapolation [55.75188191403343]
  We introduce utility, which is a function predefined by each user and describes the trade-off between cost and performance of BO. We validate our algorithm on various LC datasets and found it outperform all the previous multi-fidelity BO and transfer-BO baselines we consider.
  arXiv  Detail & Related papers  (2024-05-28T07:38:39Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• Evolve Cost-aware Acquisition Functions Using Large Language Models [11.209139558885035]
  This paper introduces EvolCAF, a novel framework that integrates large language models (LLMs) with evolutionary computation (EC) to automatically design cost-aware AFs. The designed cost-aware AF maximizes the utilization of available information from historical data, surrogate models and budget details. In comparison to the well-known EIpu and EI-cool methods designed by human experts, our approach showcases remarkable efficiency and generalization across various tasks.
  arXiv  Detail & Related papers  (2024-04-25T12:19:18Z)
• $\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model [50.636423457653066]
  We present a generalized version of the 24-Puzzle: the $(N,K)$-Puzzle, which challenges language models to reach a target value $K$ with $N$ integers. We evaluate the effectiveness of established RL algorithms such as Proximal Policy Optimization (PPO), alongside novel approaches like Identity Policy Optimization (IPO) and Direct Policy Optimization (DPO)
  arXiv  Detail & Related papers  (2024-03-11T22:24:14Z)
• Reinforcement Learning from Human Feedback with Active Queries [67.27150911254155]
  Current reinforcement learning approaches often require a large amount of human-labelled preference data. We propose query-efficient RLHF methods, inspired by the success of active learning. Our experiments show that ADPO, while only making about half of queries for human preference, matches the performance of the state-of-the-art DPO method.
  arXiv  Detail & Related papers  (2024-02-14T18:58:40Z)
• EERO: Early Exit with Reject Option for Efficient Classification with limited budget [0.0]
  We propose EERO, a new methodology to translate the problem of early exiting to a problem of using multiple classifiers with reject option. We calibrate the probabilities of exiting at the different heads using aggregation with exponential weights to guarantee a fixed budget. Experimental results, conducted using a ResNet-18 model and a ConvNext architecture on Cifar and ImageNet datasets, demonstrate that our method not only effectively manages budget allocation but also enhances accuracy in overthinking scenarios.
  arXiv  Detail & Related papers  (2024-02-06T07:50:27Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Dynamic Multi-objective Ensemble of Acquisition Functions in Batch Bayesian Optimization [1.1602089225841632]
  The acquisition function plays a crucial role in the optimization process. Three acquisition functions are dynamically selected from a set based on their current and historical performance. Using an evolutionary multi-objective algorithm to optimize such a MOP, a set of non-dominated solutions can be obtained.
  arXiv  Detail & Related papers  (2022-06-22T14:09:18Z)
• Cost-Efficient Online Hyperparameter Optimization [94.60924644778558]
  We propose an online HPO algorithm that reaches human expert-level performance within a single run of the experiment. Our proposed online HPO algorithm reaches human expert-level performance within a single run of the experiment, while incurring only modest computational overhead compared to regular training.
  arXiv  Detail & Related papers  (2021-01-17T04:55:30Z)
• A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumeration [17.75042918159419]
  A cost-based algorithm is adopted in almost all current database systems. In the cost model, cardinality, the number of the numbers through an operator plays a crucial role. Due to the inaccuracy in cardinality estimation, errors in cost, and the huge plan space model, the algorithm cannot find the optimal execution plan for a complex query in a reasonable time.
  arXiv  Detail & Related papers  (2021-01-05T13:47:45Z)
• FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks [4.596221278839825]
  We develop a novel multi-objective optimization algorithm, we call Flexible Multi-Objective Bayesian Optimization (FlexiBO) to address this issue. We evaluate FlexiBO on seven state-of-the-art DNNs for image recognition, natural language processing (NLP), and speech-to-text translation.
  arXiv  Detail & Related papers  (2020-01-18T03:26:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.