Black-box Methods for Restoring Monotonicity

Testing Monotonicity of Machine Learning Models

Today, machine learning (ML) models are increasingly applied in decision making. This induces an urgent need for quality assurance of ML models with respect to (often domain-dependent) requirements. Monotonicity is one such requirement. It specifies a software as 'learned' by an ML algorithm to give an increasing prediction with the increase of some attribute values. While there exist multiple ML algorithms for ensuring monotonicity of the generated model, approaches for checking monotonicity, in particular of black-box models, are largely lacking. In this work, we propose verification-based t…

神经网络中正性条件的数学认证及其在部分单调性与可信人工智能中的应用

A mathematical certification for positivity conditions in Neural Networks with applications to partial monotonicity and Trustworthy AI

针对已训练黑箱人工神经网络的部分单调性认证难题，提出基于有限评估、Lipschitz性与Voronoi图的LipVor算法，无需受限架构即可认证正性相关性质，助力无约束ANN在关键领域应用。

无效文本还是绑定条款？测量并恢复黑盒大语言模型对话中的约束影响

Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues

该研究针对黑盒大语言模型对话中撤销约束失效的问题，提出 sysname 方法，通过合约账本、顺序消融探针和修复阶梯实现复发率的测量、预测与修复，降低了约束撤销的失效概率。

ParamBoost：基于梯度提升的分段三次多项式

ParamBoost: Gradient Boosted Piecewise Cubic Polynomials

ParamBoost是一种新型广义加性模型，通过梯度提升算法学习分段三次多项式函数，结合连续性、单调性、凸性等约束，提升模型性能与可解释性。

单调性和保守性策略迭代超越表格情形

Monotone and Conservative Policy Iteration Beyond the Tabular Case

本文提出RPI和CRPI，通过贝尔曼约束优化在函数逼近中保留表格保证，恢复价值估计的单调性并提供下界，同时改进策略更新以应对函数逼近误差，从而解决强化学习中函数逼近导致的收敛问题。