Learning curve extrapolation aims to predict model performance in later
epochs of training, based on the performance in earlier epochs. In this work,
we argue that, while the inherent uncertainty in the extrapolation of learning
curves warrants a Bayesian approach, existing methods are (i) overly
restrictive, and/or (ii) computationally expensive. We describe the first
application of prior-data fitted neural networks (PFNs) in this context. A PFN
is a transformer, pre-trained on data generated from a prior, to perform
approximate Bayesian inference in a single forward pass. We propose LC-PFN, a
PFN trained to extrapolate 10 million artificial right-censored learning curves
generated from a parametric prior proposed in prior art using MCMC. We
demonstrate that LC-PFN can approximate the posterior predictive distribution
more accurately than MCMC, while being over 10 000 times faster. We also show
that the same LC-PFN achieves competitive performance extrapolating a total of
20 000 real learning curves from four learning curve benchmarks (LCBench,
NAS-Bench-201, Taskset, and PD1) that stem from training a wide range of model
architectures (MLPs, CNNs, RNNs, and Transformers) on 53 different datasets
with varying input modalities (tabular, image, text, and protein data).
Finally, we investigate its potential in the context of model selection and
find that a simple LC-PFN based predictive early stopping criterion obtains 2 -
6x speed-ups on 45 of these datasets, at virtually no overhead.

本研究论文通过利用先验数据拟合的神经网络模型（PFN），将贝叶斯推断应用于学习曲线外推，实现更准确且高效的后验预测分布，并展示了该模型在模型选择中的潜在应用，证明基于 LC-PFN 的预测性提前停止准则在 45 个数据集上可以实现 2-6 倍的加速且几乎没有额外的开销。

使用先验 - 数据拟合网络实现高效贝叶斯学习曲线外推

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted  Networks

While early research in neural architecture search (NAS) required extreme
computational resources, the recent releases of tabular and surrogate
benchmarks have greatly increased the speed and reproducibility of NAS
research. However, two of the most popular benchmarks do not provide the full
training information for each architecture. As a result, on these benchmarks it
is not possible to run many types of multi-fidelity techniques, such as
learning curve extrapolation, that require evaluating architectures at
arbitrary epochs. In this work, we present a method using singular value
decomposition and noise modeling to create surrogate benchmarks, NAS-Bench-111,
NAS-Bench-311, and NAS-Bench-NLP11, that output the full training information
for each architecture, rather than just the final validation accuracy. We
demonstrate the power of using the full training information by introducing a
learning curve extrapolation framework to modify single-fidelity algorithms,
showing that it leads to improvements over popular single-fidelity algorithms
which claimed to be state-of-the-art upon release. Our code and pretrained
models are available at this https URL

本论文介绍了一种新的方法，使用奇异值分解和噪声建模来创建代理基准，该方法可以替代缺乏完整训练信息的流行基准，如 NAS-Bench-111、NAS-Bench-311 和 NAS-Bench-NLP11，从而实现对多保真技术的评估。展示了使用全面的训练信息修改单保真算法的学习曲线外推框架的强大能力，并表明这种方法比当时声称是最先进的保真算法有更好的表现。