SMART Fine-tuning Factor Augmented Neural Lasso
SMART 微调：因子增强神经网络 LassoAI 解读 ↓
← 返回论文列表与筛选
阅读说明
本页整理公开书目信息，不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成，未完成全文核验，可能有误；具体假设、证明与结论请核对原文。摘要保留来源文本，未经模型改写。
DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要；缺少可靠材料时保留待补状态。
本页为预印本版本；arXiv 收录、作者填写的期刊信息以及作者既有发表经历，都不单独证明本篇已接收。作者发表记录按 OpenAlex 身份与完整姓名、本站覆盖期刊 ISSN 及正式卷期核对，只展示已核实例，档案仍可能误合并。
引用量采用 OpenAlex 单条关联记录，不合计多个记录；关联记录可能包含正式发表版本，不等于此版本单独引用。缺失不视为零，引用指标不代表论文质量。
关注作者按书目中的完整姓名匹配，同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列，再参考通用方法与发表日期。
分类依据与纠错
AI 根据所提供的论文材料归类：摘要研究通用高维回归与迁移学习，因子结构用于处理协变量相关性，尚不足以定位宏观或金融因子研究。
反馈分类问题
正在核对关联版本…
代码、数据与补充材料
正在核对对应版本的资源…
SMART 微调：因子增强神经网络 Lasso
- 研究问题
- 在高维非参数回归与变量选择中，如何借助预训练模型适应目标任务，并判断微调何时比单任务学习更节省样本？
- 方法与思路
- 作者将源模型作为目标学习器的附加特征，仅拟合目标特有的残差部分，并结合低秩因子结构与神经网络 Lasso。
- 材料陈述的贡献
- 摘要称给出极小极大最优的超额风险界，刻画微调加速所需的相对样本量与函数复杂度条件，并报告多种分布偏移实验。
- 阅读关注点
- 应核对源模型误差如何进入目标风险界、变量选择的保证，以及协变量偏移和条件分布偏移下统计加速的具体条件。
- 阅读边界
- 所给版本为 arXiv 预印本，同行评审与期刊接收状态未核实；摘要未列出风险界的具体条件、选择一致性或实验数值。
原文摘要
Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with variable selection have not yet been developed. We propose a source-model-augmented residual tuning (SMART) framework, which incorporates the pre-trained source model as an augmented feature into the target learner and estimates only the residual target-specific component. The approach is widely applicable, from parametric and sparse models to neural networks and blackbox machine learning models. We focus on the development of fine-tuning factor-augmented neural Lasso, resulting in SMART-FAN-Lasso. This transfer-learning framework for high-dimensional nonparametric regression with variable selection simultaneously handles covariate and posterior shifts. We use a low-rank factor structure to manage high-dimensional dependent covariates and a residual tuning decomposition in which the target function is expressed as a function of source model and other target-specific variables, thereby reducing the effective complexity of the target task. We derive minimax-optimal excess risk bounds, characterizing the precise conditions, in terms of relative sample sizes and function complexities, under which fine-tuning yields statistical acceleration over single-task learning. Extensive numerical experiments across diverse covariate- and posterior-shift scenarios demonstrate that SMART-FAN-Lasso consistently outperforms standard baselines and achieves near-oracle performance even under severe target sample size constraints, empirically validating the derived rates.