Theory Of Inference Research Articles

Inference Theory for Quasi-experimental Methods when Data are Non-stationary with Unknown Structure: Does the Lifting of Shelter-in-Place Keep Covid-19 Manageable?

Inference Theory for Quasi-experimental Methods when Data are Non-stationary with Unknown Structure: Does the Lifting of Shelter-in-Place Keep Covid-19 Manageable?

Role of Culture in Meaning Making: Bridging Semiotic Cultural Psychology and Active Inference.

This essay takes up the framework of Semiotic Cultural Psychology, which in last decade was very productive in analyzing societal phenomena. Digging into complex sensemaking mechanisms, underlying the interaction between individual and his surrounding environment, has consolidated a base of empirical data gathered from different societies. Aiming to better understand the role of culture in this interaction, the current paper proposes to bridge these findings of observable macro-processes with the ones from the Active inference theory and cognitive science. Similarities between the two frameworks, as well as possible benefits of employing them for one goal, are discussed in this paper.

A surrogate-assisted stochastic optimization inversion algorithm: Parameter identification of dams

Dynamic monitoring data plays an essential role in the structural health monitoring of dams. This study presents a surrogate-assisted stochastic optimization inversion (SASOI) algorithm, a novel technique for static and dynamic parameter identification. This algorithm is based on probabilistic finite element simulations and Bayesian inference theory. It combines the advantages of low computational cost in surrogate models and fast convergence in the Bayesian algorithm. Taking four cases of different complexity, this paper verifies the effectiveness of the SASOI algorithm and validates its practicality for large dams. Surrogate models consider several alternatives, including polynomial chaos expansion (PCE), Kriging, polynomial chaos Kriging, and support vector regression. Implementation of the SASOI algorithm on dams shows that PCE outperforms other techniques. This algorithm improves the accuracy and efficiency of the static parameter identification methods by nearly 27 times compared to the classical inversion methods. Furthermore, the accuracy of dynamic parameter identification is higher than that of static one. The SASOI algorithm is applicable to other large-scale infrastructures.

A New Version of African Vulture Optimizer for Apparel Supply Chain Management Based on Reorder Decision-Making

Supply chains may serve as an effective platform for the development of sustainability by encouraging responsible conduct throughout all chain members and stages. Agent technology may greatly aid in decision-making during supply chain management. Due to recent changes in the seasons, fashion trends, and the requirements of various religions, particularly with regard to the ordering procedure, the supply chain for clothing has become one of the most difficult duties in this area. Because of this, it is crucial to enhance process coordination throughout the whole clothing supply chain and develop a decision-making strategy that functions best in a fluid environment. The Unified Modeling Language (UML) is used in this work to define the relationship between agents and simulate the supply chain process. This research incorporates enhanced African vulture optimizer, a modified bio-inspired approach, and fuzzy inference theory to assist the supply chain agent in determining the appropriate replenishment quantity and reorder point to lower the inventory cost. According to test results, the suggested AAVO-based technique may be successful in determining a target demand ordering amount while reducing the overall cost of the supply chain due to a lowered convergence trend and algorithm accuracy.

541. In Silico Modeling by Causal Inference for Identifying Biomarkers of Sepsis

Abstract Background “Every 3 seconds, someone in the world dies of sepsis” (https://sepsistrust.org/about/). We used causal inference theory as a in silico method to identify biomarkers of sepsis. Causal Inference is a theory in Machine Learning that seeks for the root causes of an event. Methods In the study it was used transcription profile data downloaded from http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE12624. This dataset has 70 samples, being 34 sepsis and 36 non-sepsis samples. Data set contains 8,519 attributes: 7,672 genes obtained after preprocessing of the mRNA expression profile data. The method applied in the dataset was a modification in the HEISA, a local learner of two stages algorithm (Figure 1). In the first stage HEISA identifies variables that compounds the set of parents, children, parents of parents and children of children of a target. During the second stage is calculated the causal effect using do-calculus method, of the selected variables of the first stage in the target. At end of the second stage, features with causal effect greater than 0.2 is selected. After selecting the features mRNA expression, it was applied two algorithms of classification, Random Forest and K-means, in order to evaluate the ability of the selected variables of identifying the occurrence of sepsis. Figure 1- Causal inference HEISA algorithm. Results As shown in Table I, after applying the algorithm, it was select six mRNA expressions that better explains whether sepsis occurs, or not. Analyzing these genes it was possible to observe that three of them are known biomarkers, they are related to sepsis: NM_017526, NM_004649 and NM_006099. It is important to stress that the second one, Homo sapiens leptin receptor overlapping transcript (LEPROT) transcript variant 1 mRNA, is known to be inversely proportional to sepsis (its causal effect is negative). The other three biomarkers, NM_017526, NM_001274, and NM_001071 also are inversely proportional to sepsis. Their relationship with sepsis is still unknown. Regarding the classification task, using only those six mRNA expressions, the accuracy of the task of classification was 100%. Table I- Sepsis biomarkers candidates. Conclusion In a big set of 7,672 genes, only six were returned as sepsis biomarkers candidates. This is a very promising in silico discovery, made by a novel mathematical method, the Causal Inference theory. Disclosures All Authors: No reported disclosures.

Active Inference Theory: The Effect of Sport Training on Tracking Movements Control

A concept of active inference suggested by K.Friston (2010, 2011) is considered in motor control as an alternative to a concept of optimal control, although they both are based on a theory of internal models. In our study, we applied the concept of active inference for the interpretation of experimental data we obtained in the course of elite athletes' development. To that end, we have studied tracking movements in elite alpine skiers (n=20), who performed several special tests throughout the preparation period. At the same time, they did blood tests, which revealed time spans characterized by significant (p<0.01) shifts in dopamine levels in blood. Dopamine served as an indicator of changes in the athletes' movement control system; these changes were related to the execution of different training loads, which determined demands on the control system. We registered a decrease in prediction errors (i.e. difference between

Accurate Attribution and Seasonal Prediction of Climatic Anomalies Using Causal Inference Theory

Abstract Using features based on correlation or noncausal dependence metrics can lead to false conclusions. However, recent research has shown that applying causal inference theory in conjunction with Bayesian networks to large-sample-size data can accurately attribute synoptic anomalies. Focusing on the East Asian summer monsoon (EASM), this study adopts a causal inference approach with model averaging to investigate causation of interannual climate variability. We attribute the EASM variability to five winter climate phenomena; our result shows that the eastern Pacific El Niño–Southern Oscillation has the largest causal effect. We also show that the causal precursors of the EASM variability are interpretable in terms of physics. Using linear regression, these precursors can predict the EASM one season ahead, outperforming correlation-based empirical models and three climate models. This study shows that even without large-sample-size data and substantial human intervention, even laymen can implement the causal inference approach to investigate the causes of climatic anomalies and construct reliable empirical models for prediction. Significance Statement We use causal inference theory to redesign the attribution procedure fundamentally and adjust a causal inference approach to commonly used climate research data. Our study shows that the causal inference approach can exhaustively reveal the causes of climatic anomalies with little human intervention, which is impossible for correlation-based studies. According to this attribution, one can construct models with a better predictive performance than the climate and correlation-based empirical models. Therefore, our causal inference approach will tremendously help both meteorologists and laymen (e.g., stakeholders and policymakers) accurately predict climate phenomena and reveal their interpretable causes. We recommend that it become a standard practice in attribution studies and operational prediction.

Turbulent combustion statistics in a diffusion flame for space propulsion applications

The usage of direct numerical simulations for research of turbulent combustion for space propulsion applications is explored. With this goal in mind, the combustion near the injection of a fuel-rich methane–oxygen flame at 20 bar is simulated using a massively parallelized solver. The statistical properties of the relevant physical fields are examined to study interactions between turbulence and combustion. This analysis is complemented by an investigation and quantification of the error sources in direct numerical simulations of turbulent diffusion flame. A method to estimate the statistical error is derived based on the classical inference theory. In addition, critical resolution criteria are discussed using a mesh sensitivity analysis.

Popular Resistance against Israeli Territorial Expropriation: Beita as a Model

AbstractThe Israeli‐Palestinian conflict dates back to the early 1930s. The most crucial factor that prolongs it and prevents any glimmer of hope is Israel's insistence on displacing the Palestinians from their lands and implanting Israeli citizens in their place. Motivated by inference theory, this study aims at investigating the latest wave of popular civil resistance against territorial expropriation in the town of Beita. The study shows that territorial confiscation is carried out systematically by Israeli settlers, aided by the army. It also shows that Beita's nonviolent approach to resistance enhances its legitimacy domestically and internationally and encourages a wider base of grassroots participation. Beita has always employed popular types of civil resistance, such as weekly protests and night‐confusion tactics at Jabal Sabih, to defend itself and expel settlers. Despite the high price Beita has paid and the settlers’ evacuation of the outpost, the Israeli military has turned the site into a base. The conclusion is that popular civil resistance has the potential to challenge occupiers in a powerful way.

Assumptions, Hypotheses, and Antecedents

This paper is about the distinction between arguments and conditionals, and the corresponding distinction between premises and antecedents. I will also propose a further distinction between two different kinds of argument, and, correspondingly, two kinds of premise that I will call "assumption" and "hypothesis." The distinction between assumptions, hypotheses, and antecedents is easily made in artificial languages, and we are already familiar with it from our first logic courses (although not necessarily under those names, since there is no standard terminology for the distinction). After explaining their differences in artificial languages, I will argue that there are ordinary-language counterparts of these three notions, meaning that some formal properties of the artificial notions nicely capture some features of the ordinary-language counterparts and their behavior in contexts of reasoning. My next crucial claim is that these three notions often get confused in ordinary language, which leads to problems for translation into symbols. I will suggest a solution to the translation problem by pointing to some distinctive characteristics of the three notions that link them to their artificial-language counterparts. Next, I will argue that this confusion is behind some well-known philosophical problems and puzzles. I will apply the distinctions in order to explain away some famous paradoxes: the direct argument (also known as or-to-if inference), a standard argument for fatalism, and McGee's counterexample to modus ponens. As Stalnaker also solved the first two of these paradoxes by using his theory of reasonable inference, I will elucidate the similarities between our solutions, and also explain why my distinctions apply more broadly, to some cases involving indicative and counterfactuals conditionals, where reasonable inference does not apply.

Targeting keystone species helps restore the dysbiosis of butyrate-producing bacteria in nonalcoholic fatty liver disease.

The dysbiosis of the gut microbiome is one of the pathogenic factors of nonalcoholic fatty liver disease (NAFLD)and also affects the treatment and intervention of NAFLD. Among gut microbiomes, keystone species that regulate the integrity and stability of an ecological community have become the potential intervention targets for NAFLD. Here, we collected stool samples from 22 patients with nonalcoholic steatohepatitis (NASH), 25 obese patients, and 16 healthy individuals from New York for 16S rRNA gene sequencing. An algorithm was implemented to identify keystone species based on causal inference theories and dynamic intervention simulation. External validation was performed in an independent cohort from California. Eight keystone species in the gut of NAFLD, represented by Porphyromonas loveana, Alistipes indistinctus, and Dialister pneumosintes, were identified, which could efficiently restore the microbial composition of the NAFLD toward a normal gut microbiome with 92.3% recovery. These keystone species regulate intestinal amino acidmetabolism and acid-base environment to promote the growth of the butyrate-producing Lachnospiraceae and Ruminococcaceae species that are significantly reduced in NAFLD patients. Our findings demonstrate the importance of keystone species in restoring the microbial composition toward a normal gut microbiome, suggesting a novel potential microbial treatment for NAFLD.

In vitro neurons learn and exhibit sentience when embodied in a simulated game-world

Integrating neurons into digital systems may enable performance infeasible with silicon alone. Here, we develop DishBrain, a system that harnesses the inherent adaptive computation of neurons in a structured environment. Invitro neural networks from human or rodent origins are integrated with in silico computing via a high-density multielectrode array. Through electrophysiological stimulation and recording, cultures are embedded in a simulated game-world, mimicking the arcade game "Pong." Applying implications from the theory of active inference via the free energy principle, we find apparent learning within five minutes of real-time gameplay not observed in control conditions. Further experiments demonstrate the importance of closed-loop structured feedback in eliciting learning over time. Cultures display the ability to self-organize activity in a goal-directed manner in response to sparse sensory information about the consequences of their actions, which we term synthetic biological intelligence. Future applications may provide further insights into the cellular correlates of intelligence.

Optimal Model Averaging of Mixed-Data Kernel-Weighted Spline Regressions

Model averaging has a rich history dating from its use for combining forecasts from time-series models (Bates and Granger) and presents a compelling alternative to model selection methods. We propose a frequentist model averaging procedure defined over categorical regression splines (Ma, Racine, and Yang) that allows for mixed-data predictors, as well as nonnested and heteroscedastic candidate models. We demonstrate the asymptotic optimality of the proposed model averaging estimator, and develop a post-averaging inference theory for it. Theoretical underpinnings are provided, finite-sample performance is evaluated, and an empirical illustration reveals that the method is capable of outperforming a range of popular model selection criteria in applied settings. An R package is available for practitioners (Racine).

From Realistic Conflict to Relative Deprivation: Rethinking the Psychology of Modern Antisemitism

This essay traces the recent critique of realistic conflict theory as it pertains to the study of antisemitism. In doing so, it will provide an overview of the arguments comprising the debate, outline the ways in which these arguments depend on specific psychological notions, and question whether the notions involved provide sufficient depth and detail to account for antisemitic behavior. The aim of this article is two-fold. First, it seeks to demonstrate that realistic conflict theory relies on psychological premises, in this case assumptions that approximate what social psychologists call social inference theory. Since realistic conflict theory relies so heavily on social inference, it is difficult to address "real conflict" without at the same time invoking long-term prejudice. Second, the article suggests that relative deprivation theory may contribute to the field of antisemitism studies by bridging the epistemological gap between "realistic conflict" and "psychological fantasy," demonstrating how "objective" change occasions conflicting feelings of entitlement and equally conflicting perceptions of social justice.

In the Body's Eye: The computational anatomy of interoceptive inference.

A growing body of evidence highlights the intricate linkage of exteroceptive perception to the rhythmic activity of the visceral body. In parallel, interoceptive inference theories of affective perception and self-consciousness are on the rise in cognitive science. However, thus far no formal theory has emerged to integrate these twin domains; instead, most extant work is conceptual in nature. Here, we introduce a formal model of cardiac active inference, which explains how ascending cardiac signals entrain exteroceptive sensory perception and uncertainty. Through simulated psychophysics, we reproduce the defensive startle reflex and commonly reported effects linking the cardiac cycle to affective behaviour. We further show that simulated ‘interoceptive lesions’ blunt affective expectations, induce psychosomatic hallucinations, and exacerbate biases in perceptual uncertainty. Through synthetic heart-rate variability analyses, we illustrate how the balance of arousal-priors and visceral prediction errors produces idiosyncratic patterns of physiological reactivity. Our model thus offers a roadmap for computationally phenotyping disordered brain-body interaction.

Opportunities and illusions of using large samples in statistical inference

The theory of statistical inference clearly describes the benefits of large samples. The larger the sample size, the fewer standard errors of the estimated population parameters (the precision of the estimation improves) and the values of the power of statistical tests in hypothesis testing increase. Today’s easy access not only to large samples (e.g. web panels) but also to more advanced and user-friendly statistical software may obscure the potential threats faced by statistical inference based on large samples. Some researchers seem to be under the illusion that large samples can reduce both random errors, typical for any sampling technique, as well as non-random errors. Additionally, the role of a large sample size is an important aspect of the much discussed in the recent years issue of statistical significance (p-value) and the problems related to its determination and interpretation. The aim of the paper is to present and discuss the consequences of focusing solely on the advantages of large samples and ignoring any threats and challenges they pose to statistical inference. The study shows that a large-size sample collected using one of the non-random sampling techniques cannot be an alternative to random sampling. This particularly applies to online panels of volunteers willing to participate in a survey. The paper also shows that the sampling error may contain a non-random component which should not be regarded as a function of the sample size. As for the contemporary challenges related to testing hypotheses, the study discusses and exemplifies the scientific and ethical aspects of searching for statistical significance using large samples or multiple sampling.

Inference of affordances and active motor control in simulated agents.

Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of such behavior from a computational neuroscience perspective. Based on the theory, we introduce an output-probabilistic, temporally predictive, modular artificial neural network architecture, which processes sensorimotor information, infers behavior-relevant aspects of its world, and invokes highly flexible, goal-directed behavior. We show that our architecture, which is trained end-to-end to minimize an approximation of free energy, develops latent states that can be interpreted as affordance maps. That is, the emerging latent states signal which actions lead to which effects dependent on the local context. In combination with active inference, we show that flexible, goal-directed behavior can be invoked, incorporating the emerging affordance maps. As a result, our simulated agent flexibly steers through continuous spaces, avoids collisions with obstacles, and prefers pathways that lead to the goal with high certainty. Additionally, we show that the learned agent is highly suitable for zero-shot generalization across environments: After training the agent in a handful of fixed environments with obstacles and other terrains affecting its behavior, it performs similarly well in procedurally generated environments containing different amounts of obstacles and terrains of various sizes at different locations.

USV collision hazard assessment and track planning algorithm

To improve the autonomous collision avoidance capability of an unmanned surface vehicle (USV) under complex working conditions, this study proposes a local track planning algorithm for USVs based on collision hazard assessment. This algorithm uses hierarchical analysis and discrepancy method to determine the collision risk index (CRI) values of different encounter scenarios, and then introduces fuzzy inference theory to construct a quantitative collision hazard assessment model based on the principle of combining subjective and objective assessment and the pessimistic principle of class classification, which provides a decision basis for a collision avoidance plan. In response to the unexpected encounter, an improved vector field histogram algorithm is proposed to use the CRI value of the obstacle as the key parameter of the histogram, solve the restricted area by removing the grid model and threshold improvement, establish the cost function to calculate the optimal sailing interval under the rules and dynamics constraints of the Convention on International Regulations for Preventing Collisions at Sea (COLREGS), and realise the local target point by tracking local track planning during autonomous collision avoidance. Simulation and on-lake experiments demonstrate the effectiveness of the collision hazard assessment model and local track planning algorithm proposed in this paper.

High-Dimensional Granger Causality Tests with an Application to VIX and News

Abstract We study Granger causality testing for high-dimensional time series using regularized regressions. To perform proper inference, we rely on heteroskedasticity and autocorrelation consistent (HAC) estimation of the asymptotic variance and develop the inferential theory in the high-dimensional setting. To recognize the time-series data structures, we focus on the sparse-group LASSO (sg-LASSO) estimator, which includes the LASSO and the group LASSO as special cases. We establish the debiased central limit theorem for low-dimensional groups of regression coefficients and study the HAC estimator of the long-run variance based on the sg-LASSO residuals. This leads to valid time-series inference for individual regression coefficients as well as groups, including Granger causality tests. The treatment relies on a new Fuk–Nagaev inequality for a class of τ-mixing processes with heavier than Gaussian tails, which is of independent interest. In an empirical application, we study the Granger causal relationship between the VIX and financial news.

A review of Information Field Theory for Bayesian inference of random fields

Several physical problems require Bayesian inference of spatial, or spatio-temporal phenomenon – often modeled as random fields defined on a continuous domain – from a discrete set of data points. Kriging, based on Gaussian processes, is one of the commonly used tool for such inference problems. While Gaussian joint probability distributions have known closed form solutions, several physical phenomenon exhibit non-Gaussian features which are analytically intractable. In such problems, one often approximates the underlying distribution by some known, often simpler distribution (for example, a Gaussian), and infers an assigned parametric form for its moments. More rigorous analysis involves computationally expensive methods such as Markov Chain Monte Carlo (MCMC) methods. This paper presents a review of the diagrammatic perturbation theory (following Feynman diagrams used in Physics), a particular technique developed as part of Information Field Theory, for analytically estimating moments of perturbative non-Gaussian distributions.