论文检索

RLHF 对齐的算法偏差：偏好坍缩与匹配正则化AI 解读

Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning LLMs with human preferences through a reward model—reinforcement learning from human feedback (RLHF)—suffers from an inherent algorithmic bias due to its Kullback–Leibler-based regularization in optimization. In extreme cases, this bias…

大语言模型水印的统计框架：枢轴量、检测效率与最优规则AI 解读

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection of LLM-generated text from its human-written counterpart. In this paper, we introduce a general and flexible framework for reasoning about the statistical efficiency of watermarks and designing powerful detection rules. Inspired by the…

良性过拟合与含噪特征AI 解读

Modern machine learning models often exhibit the benign overfitting phenomenon, which has recently been characterized using the double descent curves. In addition to the classical U-shaped learning curve, the learning risk undergoes another descent as we increase the number of parameters beyond a certain threshold. In this article, we examine the conditions under which benign overfitting occurs in the random feature (RF) models, that is, in a two-layer neural network with…

使用 ℓp 正则化统计量的 Model-X knockoffs 功效分析AI 解读

Variable selection properties of procedures utilizing penalized-likelihood estimates is a central topic in the study of high-dimensional linear regression problems. Existing literature emphasizes the quality of ranking of the variables by such procedures as reflected in the receiver operating characteristic curve or in prediction performance. Specifically, recent works have harnessed modern theory of approximate message-passing (AMP) to obtain, in a particular setting, exact…

刻画 SLOPE 的权衡：变分视角与 Donoho–Tanner 极限AI 解读

Sorted ℓ1 regularization has been incorporated into many methods for solving high-dimensional statistical estimation problems, including the SLOPE estimator in linear regression. In this paper, we study how this relatively new regularization technique improves variable selection by characterizing the optimal SLOPE trade-off between the false discovery proportion (FDP) and true positive proportion (TPP) or, equivalently, between measures of type I error and power. Assuming a…

利用自适应筛选程序检测多个可重复信号AI 解读

Replicability is a fundamental quality of scientific discoveries: we are interested in those signals that are detectable in different laboratories, different populations, across time etc. Unlike meta-analysis which accounts for experimental variability but does not guarantee replicability, testing a partial conjunction (PC) null aims specifically to identify the signals that are discovered in multiple studies. In many contemporary applications, for example, comparing…

摘要暂缺

高斯差分隐私AI 解读

Abstract In the past decade, differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analysing important primitives like privacy amplification by subsampling. Inspired by the hypothesis testing formulation of privacy, this paper proposes a new relaxation of…

通过矩调整随机梯度对总体目标景观进行统计推断AI 解读

Summary Modern statistical inference tasks often require iterative optimization methods to compute the solution. Convergence analysis from an optimization viewpoint informs us only how well the solution is approximated numerically but overlooks the sampling nature of the data. In contrast, recognizing the randomness in the data, statisticians are keen to provide uncertainty quantification, or confidence, for the solution obtained by using iterative optimization methods. The…