论文检索

Abstract We derive confidence intervals (CIs) and confidence sequences (CSs) for the classical problem of estimating a bounded mean. Our approach generalizes and improves on the celebrated Chernoff method, yielding the best closed-form "empirical-Bernstein" CSs and CIs (converging exactly to the oracle Bernstein width) as well as non-closed-form "betting" CSs and CIs. Our method combines new composite nonnegative (super)martingales with Ville's maximal inequality, with…

摘要暂缺

鞅后验分布AI 解读

Abstract The prior distribution is the usual starting point for Bayesian uncertainty. In this paper, we present a different perspective that focuses on missing observations as the source of statistical uncertainty, with the parameter of interest being known precisely given the entire population. We argue that the foundation of Bayesian inference is to assign a distribution on missing observations conditional on what has been observed. In the i.i.d. setting with an observed…

Huk、Pacchiardi、Dutta 与 Steel 对《鞅后验分布》的讨论AI 解读

We congratulate the authors for this thought-provoking paper. The recursive definition of the predictive distributions through a bivariate copula (Section 4) depends on a hyperparameter ρ, which the authors tune by minimising the prequential log-score −∑i=1nlogpi−1(yi) (Section 4.5.2). The prequential framework nicely connects with the predictive resampling approach used later. However, other strictly proper scoring rules (Gneiting & Raftery, 2007) could be used in place of…

用于稀疏贝叶斯推断的快速异步 MCMC 采样器AI 解读

Abstract We propose a very fast approximate Markov chain Monte Carlo sampling framework that is applicable to a large class of sparse Bayesian inference problems. The computational cost per iteration in several regression models is of order O(n(s+J)), where n is the sample size, s is the underlying sparsity of the model, and J is the size of a randomly selected subset of regressors. This cost can be further reduced by data sub-sampling when stochastic gradient Langevin…

网络上的平稳不可分离时空协方差函数AI 解读

Abstract The advent of data science has provided an increasing number of challenges with high data complexity. This paper addresses the challenge of space-time data where the spatial domain is not a planar surface, a sphere, or a linear network, but a generalised network (termed a graph with Euclidean edges). Additionally, data are repeatedly measured over different temporal instants. We provide new classes of stationary nonseparable space-time covariance functions where…

Draper 与 Guo 对《鞅后验分布》的讨论AI 解读

We have two comments motivated by this interesting paper. The idea, introduced early in the paper, that ‘the object of interest is fully defined once all the observations have been viewed’ is almost exactly 100 years old: it was a cornerstone of the remarkable paper by Fisher (1922) and has been referred to for many decades as Fisher consistency. We are surprised that the authors did not make this connection. Theorem (Draper & Guo, 2023) Under the conditions detailed above,…

对《鞅后验分布》的致谢动议附议与讨论AI 解读

Let me first congratulate the authors for an interesting, thought provoking and inspiring article, with many fine examples. However, I wonder whether the specific setup has sufficient generality to cover interesting cases, and I should have liked to see the ideas in this paper confronted with some different situations. Firstly, let me remind everyone of the standard Bayesian setup, where we have observablesX,Y⁠, a parameter Θ of interest that in principle should be added to…

David Rossell对《鞅后验分布》的讨论意见AI 解读

Congratulations on a thought-provoking piece. Building Bayesian inference from a (likelihood, predictive) pair, rather than a (likelihood, prior), enriches the paradigm and provides new ways to think about, formulate, and solve problems. A few respectful remarks. First, although the authors never claim this, it is worth emphasising that the framework is not prior-free. There is a posterior and a likelihood, hence the prior is proportional to their ratio. The key is that said…

Kolyan Ray 与 Botond Szabo 对“鞅后验分布”的讨论AI 解读

We congratulate the authors for their thought-provoking article, which includes proposing a copula-based update for the predictive density and establishing its frequentist consistency under relatively mild assumptions. In this contribution, we further explore the frequentist properties of (Bayesian) predictive densities and illustrate through a simple example that, similarly to the posterior distribution, the predictive distribution can also be inconsistent. One therefore…

Isadora Antoniano Villalobos 对《鞅后验分布》的讨论AI 解读

I thank the authors for their refreshing ideas, providing many insights and intuitions on the process of statistical learning. For years, Bayesians have considered two levels of uncertainty, the likelihood and the prior. By shifting the focus to the predictive distribution as a single expression of uncertainty about a future observation (given data), the sequential nature of statistical learning is made explicit, together with some of its limitations. If each observation…

Mena Chavez 对《鞅后验分布》的讨论AI 解读

I congratulate the authors for introducing a novel approach for Bayesian inference, which avoids directly using the posterior distribution, often not available or computationally expensive. In addition to opening several lines of thinking about the foundations of Bayesian statistics, their proposal unveils many interesting directions to be explored and applied within the world of statistics. With an infinite population and the epistemic view of uncertainty (see, e.g.…

Wijayatunga对《鞅后验分布》的讨论意见AI 解读

Statistical uncertainty in (an estimate of) a parameter of a probability distribution is due to missing (unseen) observations (when it is estimated), as authors have noted. We can think that an estimate of the parameter has the maximal uncertainty when no observation is used for it, and no uncertainty when all possible observations are used for it. For example, in Bayesian sense, for a Bernoulli parameter, Beta distribution with parameter values α=1 and β=1 represents the…

布莱克·莫亚对《鞅后验分布》的讨论意见AI 解读

I would like to congratulate the authors on an expository and intuitive representation of statistical uncertainty. To assist in the further investigation of predictive resampling techniques, I have developed a software package for R (R Core Team, 2022) which implements some of the algorithms presented here as well as from subsequent work (Moya & Walker, 2023). The CopRe package (Moya, 2022), named for the copula resampling technique described in Section 4, can be installed…

贾琦顾与郭胜尹对《鞅后验分布》的讨论AI 解读

We congratulate the authors for their thought-provoking paper, especially in the three aspects as follows. Instead of imposing a prior π(θ) on the parameter θ of a likelihood function fθ(y)⁠, where both π and fθ are elicited subjectively, the authors proposed the framework of martingale posterior to directly model the predictive p(yn+1:∞∣y1:n) for which only the prior predictive p(y) needs to be specified. As a result, Bayesian inference can be conducted on any parameter (or…

Catalano、Fasano 与 Rebaudo 对《鞅后验分布》的讨论AI 解读

We congratulate the authors for an insightful foundational contribution to the statistical literature. This work builds on well-established methodologies, such as predictive inference, Doob’s theorem, and conditional independent sequences, providing a unifying framework and a novel understanding of Bayesian uncertainty. A central role is played by the predictive characterisation of the random parameter in terms of observable (yet unobserved) quantities, which are regarded as…

Pietro Rigo 对《鞅后验分布》的讨论AI 解读

This paper is really interesting and offers a number of intriguing hints. Here, I just make a few isolated remarks without any claim of being exhaustive. I would give more emphasis to the Ionescu-Tulcea theorem (ITT). This theorem is quoted only in passing, but it is the cornerstone of this paper. By ITT, the distribution of Y1:∞=(Y1,Y2,…) is completely determined by the assignment of {Pn:n≥0}⁠, where P0(⋅)=P(Y1∈⋅) and Pn(⋅)=P(Yn+1∈⋅∣Y1:n)⁠. Exploiting ITT has at least two…

Bertrand Clarke 对《鞅后验分布》的讨论AI 解读

To see the effect of the paper on statistical practice, consider the following hypothetical dialogue between a Quantitative Scientist (QS) and a Predictive Statistician (PS). QS: I’ve been thinking about the data generating mechanism and what we can safely assume pre-experimentally. PS: Actually, I’m more interested in what you think your n+1 data point would be. If you were going to predict your n+1 measurement, how would you do it? QS: I’d guess what the true model is and…

Ascolani、Lijoi与Prünster对《鞅后验分布》的讨论AI 解读

We would like to congratulate the authors on their fine and insightful contribution, which provides an original perspective on Bayesian inference and opens up new exciting research directions. The key point is a novel interpretation of the role of prediction: in a Bayesian framework all the uncertainty lies in the unobserved data Yn+1,∞ and, once they are imputed through the predictive distributions, inference is straightforward. Therefore, prediction rules, besides allowing…

对《鞅后验分布》的致谢提议与讨论AI 解读

Philip Dawid; Proposal of Vote of Thanks for “Martingale Posterior Distributions” by Edwin Fong, Chris Holmes and Stephen G. Walker, Journal of the Royal Statis

Ben Swallow对《鞅后验分布》的讨论意见AI 解读

Fong et al. (2023) present an interesting and novel approach to conducting Bayesian posterior estimation utilising a joint predictive distribution over missing potential observations and justify how this approach of generating one-step-ahead predictive distributions naturally aligns with the Bayesian likelihood-prior paradigm. The authors mention time series and hierarchical data as areas of potential future development. However, one of the major topics in Bayesian…

高维矩阵值时间序列的双向动态因子模型AI 解读

Abstract In this article, we introduce a two-way dynamic factor model (2w-DFM) for high-dimensional matrix-valued time series and study some of the basic theoretical properties in terms of identifiability and estimation accuracy. The proposed model aims to capture separable and low-dimensional effects of row and column attributes and their correlations across rows, columns, and time points. Complementary to other dynamic factor models for high-dimensional data, the 2w-DFM…

超越尖锐零假设的随机化推断：有界零假设与个体处理效应分位数AI 解读

Abstract Randomisation inference (RI) is typically interpreted as testing Fisher’s ‘sharp’ null hypothesis that all unit-level effects are exactly zero. This hypothesis is often criticised as restrictive and implausible, making its rejection scientifically uninteresting. We show, however, that many randomisation tests are also valid for a ‘bounded’ null hypothesis under which the unit-level effects are all non-positive (or all non-negative) but are otherwise heterogeneous.…

Maxway CRT：提高 model-X 推断的稳健性AI 解读

Abstract The model-X conditional randomisation test (CRT) is a flexible and powerful testing procedure for testing the hypothesis X⫫Y∣Z. However, it requires perfect knowledge of X∣Z and may lose its validity when there is an error in modelling X∣Z. This problem is even more severe when Z is of high dimensionality. In response to this, we propose the Maxway CRT, which learns the distribution of Y∣Z and uses it to calibrate the resampling distribution of X to gain robustness…