CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG

2026-05-08 · Pengzhou Chen, Tao Chen arxiv

Retrieval-Augmented Generation (RAG) is sensitive to the vast hyperparameters of the retriever and generator, yet optimizing them using given queries is a challenging task due to the complex interactions and expensive evaluation costs. Existing algorithms are ineffective and slow in convergence, since they often treat RAG as a monolithic black box or only optimize partial hyperparameters. In this paper, we propose CDS4RAG, a framework that optimizes the full RAG hyperparameters using given queries via a new cyclic dual-sequential formulation. CDS4RAG is special in the sense that it distinguishes the hyperparameters of the retriever and generator, cyclically optimizing them in turn. Such a paradigm allows us to design fine-grained within-cycle budget provision and expedite the optimization via cross-cycle seeding when optimizing the generator. CDS4RAG is also an algorithm-agnostic framework that can be paired with diverse general algorithms. Through experiments on four common benchmarks and two backbone LLMs, we reveal that CDS4RAG considerably boosts the vanilla algorithms in 21/24 cases while significantly outperforming state-of-the-art algorithms in all cases with up to 1.54x improvements of generation quality and better speedup.

📄 PDF Abstract BibTeX arXiv:2605.08333

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter Optimization

Deep Reinforcement Learning using Cyclical Learning Rates

2020-07-31 · Ralf Gulde, Marc Tuscher, Akos Csiszar, Oliver Riedel 외

Deep Reinforcement Learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gra…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

StochaLM: a Stochastic alternate Linearization Method for distributed optimization

2020-04-23 · Inês Almeida, João Xavier

We present the Stochastic alternate Linearization Method (StochaLM), a token-based method for distributed optimization. This algorithm finds the solution of a consensus optimization problem by solving a sequence of subpr…

Distributed Optimization Federated Learning

Hyperparameter Optimization via Sequential Uniform Designs

2020-09-08 · Zebin Yang, Aijun Zhang

Hyperparameter optimization (HPO) plays a central role in the automated machine learning (AutoML). It is a challenging task as the response surfaces of hyperparameters are generally unknown, hence essentially a global op…

AutoML global-optimization Hyperparameter Optimization

Hyp-RL : Hyperparameter Optimization by Reinforcement Learning

2019-06-27 · Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme

Hyperparameter tuning is an omnipresent problem in machine learning as it is an integral aspect of obtaining the state-of-the-art performance for any model. Most often, hyperparameters are optimized just by training a mo…

Bayesian Optimization Hyperparameter Optimization reinforcement-learning Reinforcement Learning+1

Memory-Based Dual Gaussian Processes for Sequential Learning

2023-06-06 · Paul E. Chang, Prakhar Verma, S. T. John, Arno Solin 외

Sequential learning with Gaussian processes (GPs) is challenging when access to past data is limited, for example, in continual and active learning. In such cases, errors can accumulate over time due to inaccuracies in t…

Active Learning Bayesian Optimization Continual Learning Gaussian Processes