Posts
All the articles I've posted.
-
Nonparametric learning of covariate-based Markov jump processes using RKHS techniques
本文提出了一种基于再生核希尔伯特空间(RKHS)的非参数化方法,通过频率学和贝叶斯框架建模连续时间马尔可夫链(CTMC)中协变量驱动的非线性转移率,显著提升了个体化状态转移预测的准确性。
-
Wasserstein Distributionally Robust Nonparametric Regression
This paper introduces a Wasserstein Distributionally Robust Optimization framework for nonparametric regression, using Lipschitz-constrained feedforward neural networks to derive non-asymptotic error bounds for local worst-case risk under model misspecification, demonstrating robustness through simulations and MNIST dataset application.
-
When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator
This paper demonstrates that a 1.5B parameter reasoning model (Distill-R1) outperforms larger non-reasoning LLMs as a discriminator in a text-to-SQL planning framework by leveraging a novel soft score extraction method from chain-of-thought outputs, though it struggles significantly as a generator.
-
From Compression to Expansion: A Layerwise Analysis of In-Context Learning
本文通过统计几何分析揭示了大型语言模型在上下文学习中的层级压缩-扩展现象,早期层压缩任务信息,后期层扩展生成预测,并探讨了模型大小、演示数量和噪声对性能的影响。
-
Parameter-Efficient Fine-Tuning with Column Space Projection
本文提出PiCa,一种基于谱特性的参数高效微调方法,通过将梯度投影到预训练权重的低秩列子空间并结合权重共享,在显著减少参数量的同时实现了优于LoRA和SVFT的性能。