DABO：基于扩散学习先验的难度感知贝叶斯优化
DABO: Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priors
对视觉研究者而言，DABO 提供了一套可直接复用的超参数搜索框架：用条件扩散模型在真实学习曲线上生成合成数据，训练难度感知代理模型与采集函数，从而在有限算力预算下更高效地调参（如检测、分割、生成模型的训练超参），减少在简单区域浪费的搜索预算。
原文依据 we train a conditional diffusion model on 120,000 real learning curves, generating synthetic data with 2.3xhigher fidelity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论超参数优化（HPO）的效率对深度学习至关重要，然而最优方法都存在一个根本缺陷：它们对难度不敏感，将所有超参数配置同质对待。这种做法导致资源分配低效，在简单区域浪费预算，而对复杂崎岖的搜索空间探索不足，从而严重损害搜索效率与最终性能。为应对这一普遍挑战，我们提出 DABO，一个在 Freeze-Thaw 贝叶斯优化这一高效框架内率先实现难度感知调参的框架。我们首先对优化难度进行分层建模。随后，我们摒弃手工设计的先验，在 120,000 条真实学习曲线上训练条件扩散模型，生成保真度提高 2.3 倍的合成数据。该数据用于训练我们的难度感知代理模型与采集函数，以动态调整搜索策略。在 75 个任务上，DABO 相比领先的难度不敏感方法 ifBO 将遗憾降低 11-18%。我们的工作为 HPO 确立了新范式，将关注点从以配置为中心转向难度感知的资源分配，从而实现更稳健、更高效的优化。
英文原文摘要 1246 字符
The efficiency of hyperparameter optimization (HPO) is critical for deep learning, yet state-of-the-art methods share a fundamental flaw: they are difficulty-agnostic, treating all hyperparameter configurations homogeneously. This approach leads to inefficient resource allocation, wasting budget in simple regions while under-exploring complex, rugged landscapes, and thereby critically undermining both search efficiency and final performance. To address this universal challenge, we introduce DABO, a framework that pioneers difficulty-aware tuning within the efficient context of Freeze-Thaw Bayesian Optimization. We first model optimization difficulty hierarchically. Then, departing from hand-crafted priors, we train a conditional diffusion model on 120,000 real learning curves, generating synthetic data with 2.3xhigher fidelity. This data trains our difficulty-aware surrogate model and acquisition function to dynamically adapt the search strategy. Across 75 tasks, DABO reduces regret by 11-18% compared to the leading difficulty-agnostic method, ifBO. Our work establishes a new paradigm for HPO, shifting the focus from configuration-centric to difficulty-aware resource allocation to enable more robust and efficient optimization.