Accept–Reject Methods

Martino, Luca; Luengo, David; Mı́guez, Joaquı́n

doi:10.1007/978-3-319-72634-2_3

Cited by 10 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used these proposal samples to train a density estimator, for which we used a neural spline flow (NSF) . Next, we created a mixture composed of the NSF and the prior with weights 0.9 and 0.1, respectively, as a proposal distribution g(θ) for rejection sampling (Martino et al, 2018). Rejection sampling relies on finding a constant M such that f (θ) ≤ M g(θ) for all values of θ: To find this constant, we initialized M = 1, sampled θ ∼ g(θ), and updated M = 1.2f (θ)/g(θ) if f (θ)/g(θ) > M .…”

Section: B1 Reference Posteriorsmentioning

confidence: 99%

Benchmarking Simulation-Based Inference

Lueckmann,

Boelts,

Greenberg

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. However, a public benchmark with appropriate performance metrics for such 'likelihood-free' algorithms has been lacking. This has made it difficult to compare algorithms and identify their strengths and weaknesses. We set out to fill this gap: We provide a benchmark with inference tasks and suitable performance metrics, with an initial selection of algorithms including recent approaches employing neural networks and classical Approximate Bayesian Computation methods. We found that the choice of performance metric is critical, that even state-of-the-art algorithms have substantial room for improvement, and that sequential estimation improves sample efficiency. Neural network-based approaches generally exhibit better performance, but there is no uniformly best algorithm. We provide practical advice and highlight the potential of the benchmark to diagnose problems and improve algorithms. The results can be explored interactively on a companion website.All code is open source, making it possible to contribute further benchmark tasks and inference algorithms.

show abstract

Section: B1 Reference Posteriorsmentioning

confidence: 99%

Benchmarking Simulation-Based Inference

Lueckmann,

Boelts,

Greenberg

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To ensure a representative sample and mitigate selection bias, we employed a random participant sampling technique following Dornyei and Csizer’s (2012), as described by Martino et al (2018). This non-probability recruitment method balanced convenience sampling with efforts to achieve a representative sample by selecting participants with critical characteristics.…”

Section: Methodsmentioning

confidence: 99%

Understanding the Role of Teacher-Student Relationships in Students’ Online Learning Engagement: Mediating Role of Academic Motivation

Akram,

2024

Percept Mot Skills

View full text Add to dashboard Cite

Strengthening online learning outcomes requires the establishment of strong student-teacher relationships to engage students actively in learning activities. Teacher-student relationships are also pivotal factors for enhancing academic motivation for online learning engagement. Generally, however, research on online teaching remains underdeveloped. We aimed, in this study, to investigate the complex interplay in higher education in Pakistan between teacher-student relationships, academic motivation, and online learning engagement. We used Self-Determination Theory to frame an exploration of the impact of positive teacher-student relationships as mediated by intrinsic or extrinsic academic motivation on students’ engagement in online learning activities. We administered a student self-report questionnaire to 437 participants from diverse universities in Sindh province. Using Structural Equation Modeling, we confirmed a model fit in which there were positive correlations between teacher-student relationships and students’ online learning engagement; and between students’ intrinsic and extrinsic academic motivations and their on line learning engagement. Our findings emphasized the need for communication, personalized support, and a sense of belonging in virtual education. Moreover, our findings revealed the mediating role of students’ intrinsic and extrinsic academic motivation in teacher-student relationships, highlighting the nuanced dynamics of academic motivation in the virtual learning environment, with intrinsic motivation having the greatest mediating impact in the relationship between teacher-student relationships and on line learning engagement. Our study’s practical implications include a need for professional educators to foster positive teacher-student relationships and integrate student motivational elements into online course design.

show abstract

“…The step function h * (u) can be used to formulate a rejection sampler to take exact draws from p(u) (Martino et al, 2018). By construction, h * (u) ≥ P(A u ) for all u ∈ [0, 1], so that rejection sampling can be carried out by Algorithm 1.…”

Section: Step Functionmentioning

confidence: 99%

Direct Sampling with a Step Function

Raim¹

2022

Preprint

View full text Add to dashboard Cite

The direct sampling method proposed by Walker et al. (JCGS 2011) can generate draws from weighted distributions possibly having intractable normalizing constants. The method may be of interest as a useful tool in situations which require drawing from an unfamiliar distribution. However, the original algorithm can have difficulty producing draws in some situations. The present work restricts attention to a univariate setting where the weight function and base distribution of the weighted target density meet certain criteria. Here, a variant of the direct sampler is proposed which uses a step function to approximate the density of a particular augmented random variable on which the method is based. Knots for the step function can be placed strategically to ensure the approximation is close to the underlying density. Variates may then be generated reliably while largely avoiding the need for manual tuning or rejections. A rejection sampler based on the step function allows exact draws to be generated from the target with lower rejection probability in exchange for increased computation. Several applications of the proposed sampler illustrate the method: generating draws from the Conway-Maxwell Poisson distribution, a Gibbs sampler which draws the dependence parameter in a random effects model with conditional autoregression structure, and a Gibbs sampler which draws the degrees-of-freedom parameter in a regression with t-distributed errors.

show abstract

Accept–Reject Methods

Cited by 10 publications

References 33 publications

Benchmarking Simulation-Based Inference

Benchmarking Simulation-Based Inference

Understanding the Role of Teacher-Student Relationships in Students’ Online Learning Engagement: Mediating Role of Academic Motivation

Direct Sampling with a Step Function

Contact Info

Product

Resources

About