论文检索

Papp、Fearnhead 与 Sherlock 对机器学习概率统计讨论会的评论AI 解读

We provide comments only on the read paper “From Denoising Diffusions to Denoising Markov Models” by Benton, Shi, De Bortoli, Deligiannidis and Doucet. We congratulate the authors on an important contribution to the exciting area of generative models: providing a simple framework for applying the idea of diffusion generative models to data defined on general spaces and for general noising processes. Diffusion models have shown remarkable empirical performance for several…

基于深度学习的时间序列自动变点检测AI 解读

Abstract Detecting change points in data is challenging because of the range of possible types of change and types of behaviour of data when there is no change. Statistically efficient methods for detecting a change will depend on both of these features, and it can be difficult for a practitioner to develop an appropriate detection method for their application of interest. We show how to automatically generate new offline detection methods based on training a neural network.…

van Lieshout 与 Lu 对机器学习概率统计讨论会论文的讨论意见AI 解读

We congratulate Professors Li, Fearnhead, Fryzlewics, and Wang on their fine work that represents classic test statistics for change-point detection as a neural network-based classifier and develops improved offline detection algorithms for historical, labelled data. The paper focuses on real-valued observation vectors in a temporal regression model with training data being either labelled historical data or obtained by simulation from a model. In many applications, though,…

Cribben 与 Anastasiou 对机器学习概率统计讨论会论文的评论AI 解读

We extend our congratulations to the authors for their innovative contribution. Here, we address three key points: change-point labelling, handling imbalanced datasets, and computational complexity. Change-point labelling in datasets has many flaws and challenges. The primary flaw is the subjectivity inherent in the task as it often relies on human judgement. This subjectivity introduces biases and inconsistencies. One challenge is the lack of a universally accepted standard…

Hernando Ombao 对机器学习概率与统计讨论会论文的评论AI 解读

I congratulate the authors for their fundamental contribution that demonstrates how the existing tests for change-points can be represented by a neural network. The major consequence is that with sufficient data, the performance of these neural networks should be at par with these existing tests. This formulation is very insightful and inspired me to revisit the previous work on models for non-stationary time series that use time-localized representations such as wavelets,…

Yingnian Wu 与 Weng Kee Wong 对机器学习概率与统计讨论会的评论AI 解读

We thank the authors for the interesting and timely article. Our commentaries are as follows: From equilibrium Langevin dynamics to non-equilibrium ordinary and stochastic differential equations. We wish to add a little background explanation, with no claim of originality, to this deep and elegant paper that greatly expands the scope of diffusion/score-based models. The diffusion-based model can be viewed as a refined variational auto-encoder and a non-equilibrium Langevin…

Gilbert MacKenzie 对机器学习概率与统计讨论会的评论AI 解读

I would like first to congratulate both authors on presenting their very stimulating work in the spirit of the conference’s theme of statisticians and machine learners working in alliance. There is no doubt in my mind that collaboration will lead to better, more parsimonious, models. My comments relate, mainly, to the second discussant’s points on over-parametrization. If a feed-forward neural net (Ripley, 1994) is denoted by Net(x,θ)⁠, where x is the input layer and ϕ is…

Gilliot 等对机器学习概率与统计讨论会的讨论意见：扩散模型的隐含分布约束AI 解读

We would like to thank the authors for their interesting contribution and the clarification brought on a particular aspect of diffusion models concerned with the criterion used in the fitting phase of the procedure. Another aspect, not discussed extensively, is the choice of the neural network used to model the gradients involved in the generative phase. In particular, the implicit prior information this induces on the class of distributions considered may seem mysterious…

洪永淼、Oliver Linton、孙佳静与朱美婷对机器学习概率与统计讨论会的评论AI 解读

This paper proposes a neural network-based approach for automating offline change-point detection. The authors show that cumulative sum (CUSUM) and generalized CUSUM are a special case of their neural network class. They emphasize misclassification error rates and their theoretical contribution is to establish some elegant results for these under i.i.d. unit variance Gaussian data with a possible change in mean. Their theoretical results outline the conditions on the…

Kanti Mardia 对“机器学习的概率与统计方面”讨论会论文的评论AI 解读

I enjoyed reading this paper which has so many outstanding features; this is where Modern Statistics is moving—high-level computing with sound mathematical statistical. My comments are as follows. The authors use the wrapped normal on SO(3) using the exponential map and I have some reservations related to this choice since the most common distribution used on SO(3) is the Fisher matrix distribution which has many desirable properties (see, e.g. Mardia & Jupp, 2000) whereas…

Andi Wang 对“机器学习概率与统计方面讨论会”的评论AI 解读

I would like to congratulate the authors for this excellent article, which includes both careful theoretical developments at the foundations of such denoising models and exciting methodological innovations and experiments. Of course, there are still many unanswered questions in relation to these denoising Markov models. One of the most tantalizing such questions is touched on by the authors in their concluding discussion, namely the nature of the implicit biases which are…

Shakeel Gavioli-Akilagun 对机器学习概率与统计讨论会论文的评论AI 解读

We congratulate the authors for the interesting and thought provoking paper. Lemma 3.2 shows that the generalized likelihood ratio (GLR) test for stability of a linear regression can be viewed as a simple feed forward neural network. However, close inspection of the lemma reveals that the setup rules out several common change point problems. Consider the piecewise polynomial regression: For ξ ’s distributed i.i.d. N(0,1)⁠, the likelihood ratio statistic for a change at…

关于“机器学习的概率与统计方面”讨论会的致谢提议与讨论意见AI 解读

Computational statistics and machine learning (ML) are closely related, and there are many opportunities for cross-fertilization of ideas between the two fields. Both can benefit from greater interaction, and the two papers being discussed here highlight some ways that this can happen. The main focus of this paper is offline detection of a single change-point using labelled training data. Interest is in the automatic generation of new offline detection methods using neural…

利用双重负对照识别与估计存在未测网络混杂的同伴因果效应AI 解读

Abstract Identification and estimation of causal peer effects are challenging in observational studies for two reasons. The first is the identification challenge due to unmeasured network confounding, for example, homophily bias and contextual confounding. The second is network dependence of observations. We establish a framework that leverages a pair of negative control outcome and exposure variables (double negative controls) to non-parametrically identify causal peer…

准凸回归函数的最小二乘估计AI 解读

Abstract We develop a new approach for the estimation of a multivariate function based on the economic axioms of quasiconvexity (and monotonicity). On the computational side, we prove the existence of the quasiconvex constrained least squares estimator (LSE) and provide a characterisation of the function space to compute the LSE via a mixed-integer quadratic programme. On the theoretical side, we provide finite sample risk bounds for the LSE via a sharp oracle inequality.…

检验全局原假设的集成方法AI 解读

Abstract Testing a global null is a canonical problem in statistics and has a wide range of applications. In view of the fact that no uniformly most powerful test exists, prior and/or domain knowledge are commonly used to focus on a certain class of alternatives to improve the testing power. However, it is generally challenging to develop tests that are particularly powerful against a certain class of alternatives. In this paper, motivated by the success of ensemble learning…

中间混杂下因果中介分析的信息传递干预AI 解读

Abstract Recent approaches to causal inference have focused on causal effects defined as contrasts between the distribution of counterfactual outcomes under hypothetical interventions on the nodes of a graphical model. In this article, we develop theory for causal effects defined with respect to a different type of intervention, one which alters the information propagated through the edges of the graph. These information transfer interventions may be more useful than node…

中介路径分析中复合原假设的自适应 Bootstrap 检验AI 解读

Abstract Mediation analysis aims to assess if, and how, a certain exposure influences an outcome of interest through intermediate variables. This problem has recently gained a surge of attention due to the tremendous need for such analyses in scientific fields. Testing for the mediation effect (ME) is greatly challenged by the fact that the underlying null hypothesis (i.e. the absence of MEs) is composite. Most existing mediation tests are overly conservative and thus…

变换稀疏性中的错误发现率控制：Split KnockoffsAI 解读

Abstract Controlling the False Discovery Rate (FDR) in a variable selection procedure is critical for reproducible discoveries, and it has been extensively studied in sparse linear models. However, it remains largely open in scenarios where the sparsity constraint is not directly imposed on the parameters but on a linear transformation of the parameters to be estimated. Examples of such scenarios include total variations, wavelet transforms, fused LASSO, and trend filtering.…

贝叶斯预测决策综合AI 解读

Abstract Decision-guided perspectives on model uncertainty expand traditional statistical thinking about managing, comparing, and combining inferences from sets of models. Bayesian predictive decision synthesis (BPDS) advances conceptual and theoretical foundations, and defines new methodology that explicitly integrates decision-analytic outcomes into the evaluation, comparison, and potential combination of candidate models. BPDS extends recent theoretical and practical…

用于评估自回归过程处理效应的动态合成控制法AI 解读

Abstract Motivated by evaluating the effects of air pollution alerts on air quality, we propose the dynamic synthetic control method for micro-level data with time-varying confounders and spatial dependence under an auto-regressive model setting. We employ the empirical likelihood to define the synthetic control weights, which ensures a unique solution and permits theoretical analysis. The dynamic matching increases the feasibility of matching and enables us to assess the…

重新审视免带宽推断：样本分割方法AI 解读

Abstract The bandwidth-free tests for a multi-dimensional parameter have attracted considerable attention in econometrics and statistics literature. These tests can be conveniently implemented due to their tuning-parameter free nature and possess more accurate size as compared to the traditional heteroskedasticity and autocorrelation consistent-based approaches. However, when sample size is small/medium, these bandwidth-free tests exhibit large size distortion when both the…

摘要暂缺

Art Owen 对《通过投注估计有界随机变量均值》的讨论意见AI 解读

I congratulate the authors on some very interesting work making connections between likelihood, betting and martingales. What caught my eye was the connection to the empirical likelihood (EL) (Owen, 2001) and the dual likelihood (Mykland, 1995). The hindsight optimal λ solves 0=∑i=1t(xi−m)/(1+λT(xi−m))=0 corresponding to the observation weights wi∝1/(1+λT(xi−m)) used in EL. Two common alternatives use weights wi∝(1−λT(xi−m)) and wi∝exp(−λT(xi−m)) arising from L2 and entropy…