Recursive Model Research Articles

A profile transformation based recursive multi-bead overlapping model for robotic wire and arc additive manufacturing (WAAM)

Robotic Wire and Arc Additive Manufacturing (WAAM) is an ideal process for manufacturing large-scale or large-format parts efficiently and economically, as compared with other AM methods, and therefore finds extensive applications in diverse fields including aerospace, automotive and mould. Accurate prediction of WAAM part dimension is fundamentally dependent on the modeling accuracy of single-bead profile and its subsequent overlapping ones. This paper proposes a new recursive model, based on coordinate transformation, to predict single-layer multi-bead overlapping profile. Firstly, commonly used single-bead profile functions are reviewed, followed by detailed description of conventional and proposed recursive profile model. The properties of developed recursive model are then investigated for understanding the effects of overlapping ratio and single-bead aspect ratio. The influence of function type is also analysed from the surface quality divergence of single-layer multi-bead overlapping profile. Finally, multi-bead overlapping experimental tests are carried out to validate the feasibility of presented recursive profile model. The results show that the modified recursive model is more accurate than the conventional one for its better accountability of valley area. It is also indicated that parabola and arc function are more suitable for the robotic WAAM process. The research outcome is beneficial to improving the forming accuracy of WAAM parts, and also provides a new method for predicting geometry of other additive manufactured products.

Manipulator Actuated Integrated Position and Attitude Stabilization of Spacecraft Subject to External Disturbances

This article addresses the dynamics and control problem of integrated position and attitude stabilization via manipulator actuation for spacecraft in proximity operations subject to external disturbances. Following recursive modeling philosophy, kinematics, and dynamics are first formulated for multiple-manipulator actuated coupled position and attitude system of spacecraft in the presence of external disturbances, where two vector factorizations are proposed to ensure a compact and explicit dynamic formulation, holding the inherent skew-symmetric property of the coefficient matrices. In view of the unconspicuous cascaded-like system structure, a nonlinear control scheme is designed following backstepping philosophy to drive the joints of manipulators causing reactions to robustly stabilize the spacecraft position and attitude. Toward this end, a reference trajectory prescribing the spacecraft motion is predesigned by means of polynomial functions ensuring well-behaviored performance. Then, as a key component, a second-order dynamic filter is constructed making use of the dynamics structure to generate the command joint motion capable of manipulator actuation. The rigorous closed-loop stability and robust performance analyses are undertaken within the Lyapunov framework. Moreover, three types of self-collisions possibly happening in the motion of multiple manipulators are considered and handled by three collision detection methods, which facilitates a collision-free trajectory shaping during the aforementioned reference trajectory design phase. Finally, numerical simulations are given to demonstrate the effect and robustness of the proposed control scheme.

RESILIENCE ASSESSMENT METHODOLOGIES OF SOCIO-ECONOMIC SYSTEM IN THE CONDITIONS OF GLOBAL INSTABILITY

Purpose. The article aims to substantiate the need to analyze the resilience of a socio-economic system based on “technical”, “environmental”, and “adaptive” approaches. It characterizes the features of the evaluation of a socio-economic system’s resilience against global shocks following the identification of the main resilience parameters. Design/methodology/approach. The author of the article uses the literature review method to explain the importance of the methodological approach to the evaluation of a socio-economic system’s resilience against global shocks, which can be singled out based on economic, innovative, socio-demographic, institutional-managerial, and environmental drivers of economic development. Such scientific research methods as a theoretical-logical explanation, systematization and explanation, and semantic analysis were also applied to study the essence and evaluate the resilience of a socio-economic system. The research is carried out in the framework of institutional economic theory, national economic recovery, and national and regional economies. Findings. The conducted research proves the fact that a socio-economic system’s resilience is a multifaceted concept, while resilience consists of a lot of elements of economic, social, organizationalinstitutional, managerial, environmental, innovative nature, etc. Therefore, resilience cannot evaluated based on one or two parameters or a certain integral index. The article characterizes the measurement of resilience by the volume of a shock the system can withstand (absorb) before it becomes capable to enter a new stability phase. If a new post-shock configuration or condition deteriorates compared to the pre-shock period, a system is assessed as a low-resilience system. Therefore, the system that has managed to enter a new post-shock configuration or its development trajectory is in a better condition compared to the pre-shock period is characterized by high resilience. The article proves the objective necessity to analyze the drivers of organizational and managerial nature since the resilience level is formed under the impact of certain decisions in a socio-economic system’s management, its links to other systems, etc. When evaluating a socio-economic system’s resilience, it is also reasonable to analyze the budget resilience drivers, primarily the observance of balance (prevention of imbalances) between budgetary expenditures and revenues. Therefore, interbudgetary transfers as an essential factor of impact on the resilience, including subsidized regions, should be analyzed when evaluating a system’s resilience. Practical implications. The emphasis on the causal relationship between dependent and independent variables in the course of evaluating the resilience of a socio-economic system is substantiated. The article offers a recursive model, which is more appropriate for the evaluation of “prospective output” to reveal the system’s ability to recover and return to the pre-shock event growth trajectory. Originality/value. The research value lies in the development of a methodological approach to the evaluation of a socio-economic system’s resilience in global instability. The article provides recommendations regarding the application of a multidimensional methodology, which, on the one hand, analyzes the system’s resilience based on the system and holistic approaches and, on the other hand, describes the results of a shock and driving variables with the allocation of individual components of a socio-economic system (economic, social, environmental, managerial, and organizational-institutional, etc.).

Electricity market Reform: The perspective of price regulation and carbon neutrality

China promised to achieve carbon neutrality in 2060. However, electricity prices are still regulated, which may affect the effect of carbon neutrality, especially in China, because 70% of China’s electricity comes from thermal power generation. In this paper, a dynamic recursive computable general equilibrium model (CEEEA/CGE model) is applied to simulate the electricity market-oriented reform under the target of carbon neutrality from 2020 to 2060. The results show that the target may increase the demand for labor and capital to cope with increasing energy costs, and the reform may reduce GDP. However, power reform can significantly optimize the energy and economic structures and alleviate the fiscal deficit. Moreover, this paper finds and concludes the mechanism causing these effects (such as factor substitution, price advantage, government revenue, and structure), which provides policymakers with a new perspective of power reform.

Association of plasma microbial composition with a leaky gut in obesity-related osteoarthritis: An exploratory study

ObjectiveTo examine the plasma microbiome for differences between obese individuals with and without osteoarthritis (OA) and its association with serum lipopolysaccharide (LPS). DesignBlood samples from 70 participants with body mass index (BMI) ​≥ ​30kg/m2 and age ≥55 years, with (cases) or without (controls) hand plus knee OA, were analyzed for serum LPS and composition of the plasma microbiome. The Dirichlet-multinominal recursive partitioning model (DM-RPart) was applied to microbiome compositional data to test the hypothesis that LPS levels distinguish plasma microbiome, accounting for BMI and age. ResultsNo significant differences in alpha diversity, or compositional differences between groups at the genus level, were seen between cases and controls (p ​= ​0.11). β-Diversity was significantly associated with serum LPS levels (p ​= ​0.01). DM-RPart resulted in an optimal tree with 3 divisions: 1) based on age (split at 69 years); 2) those older than 69 were split based on BMI; 3) those with BMI <39 ​kg/m2 were split based on LPS level (at 65 EU/ml). This resulted in 4 groups (nodes 2, and 5–7). Participants in node 2 were younger and the majority had no or mild OA. Those in nodes 5 and 6 were comparable in age and BMI but node 6 had higher LPS and more severe OA. Individuals in node 7 were older, had higher BMI, and the most severe OA. ConclusionsOur results suggest a relationship between serum LPS and the plasma microbiome in a subgroup of obese individuals with hand plus knee OA that could reflect differences in intestinal permeability.

CT-based diagnostic algorithm to identify bowel and/or mesenteric injury in patients with blunt abdominal trauma.

To develop a CT-based algorithm and evaluate its performance for the diagnosis of blunt bowel and/or mesenteric injury (BBMI) in patients with blunt abdominal trauma. This retrospective study included a training cohort of 79 patients (29 with BBMI and 50 patients with blunt abdominal trauma without BBMI) and a validation cohort of 37 patients (13 patients with BBMI and 24 patients with blunt abdominal trauma without BBMI). CT examinations were blindly analyzed by two independent radiologists. For each CT sign, the kappa value, sensitivity, specificity, and accuracy were calculated. A diagnostic algorithm was built using a recursive partitioning model on the training cohort, and its performances were assessed on the validation cohort. CT signs with kappa value > 0.6 were extraluminal gas, hemoperitoneum, no or moderate bowel wall enhancement, and solid organ injury. CT signs yielding best accuracies in the training cohort were extraluminal gas (98%; 95% CI: 91-100), bowel wall defect (97%; 95% CI: 91-100), irregularity of mesenteric vessels (97%; 95% CI: 90-99), and mesenteric vessel extravasation (97%; 95% CI: 90-99). Using a recursive partitioning model, a decision tree algorithm including extraluminal gas and no/moderate bowel wall enhancement was built, achieving 86% sensitivity (95% CI: 74-99) and 96% specificity (95% CI: 91-100) in the training cohort and 92% sensitivity (95% CI: 78-97) and 88% specificity (95% CI: 74-100) in the validation cohort for the diagnosis of BBMI. An effective diagnostic algorithm was built to identify BBMI in patients with blunt abdominal trauma using only extraluminal gas and no/moderate bowel wall enhancement on CT examination. • A CT diagnostic algorithm that included extraluminal gas and no/moderate bowel wall enhancement was built for the diagnosis of surgical blunt bowel and/or mesenteric injury. • A decision tree combining only two reproducible CT signs has high diagnostic performance for the diagnosis of surgical blunt bowel and/or mesenteric injury.

Research on the Cause of Marketing Risk of New Tea Beverage Enterprises in China Based on the ISM-MICMAC Model

In order to provide an effective reference for the operation, development and investment decisions of new tea beverage enterprises, this paper investigates the influencing factors of marketing risk in the new tea beverage industry, determines 14 indicators affecting marketing risk in the new tea beverage industry by reviewing relevant literature and expert research. Then, an explanatory structural model (ISM) is constructed to reveal the logical relationship between the factors, and the cross-influence matrix multiplication method (MICMAC) is used to analyze dependency and driving force analysis. The results show five levels of the recursive structural model of marketing risk factors in China's new tea beverage industry. Based on the MICMAC driving force analysis, we believe that the more dependent influences need to be controlled by strengthening other risk factors that can have an impact on them, and that sufficient attention should be paid to the influences with higher driving forces, so as to facilitate the normal corporate marketing activities of new tea beverage companies.

Factors that influence the impact of Chronic Non-Cancer Pain on daily life: A partial least squares modelling approach

BackgroundChronic Non-Cancer Pain is pain of more than three months' duration and is not associated with an oncological condition. There is ample literature that recognises that Chronic Non-Cancer Pain impacts numerous areas of the life of the person who suffers from it. This impact is difficult to determine and quantify because Chronic Pain is a subjective experience. ObjectiveThe objective of this study was to test a recursive model of hypothesised factors that comprise the concept of Chronic Non-Cancer Pain Impact on daily life using Partial Least Squares-Structural Equation Modelling. DesignA cross-sectional study was carried out. The sample size was calculated using G*Power V.3.1.9.4 with five parameters (two-tailed, large effect size (f2 = 0.35), power of 0.95, statistical significance of 95% (α = 0.05) and 36 predictors). The minimum number of subjects was considered to be 137. MethodsA recursive model was built based on data from a sample of 395 people over 18 years of age with Chronic Non-Cancer Pain. Data collection was conducted between January and March 2020 at Pain Units and Primary Healthcare Centres belonging to the Spanish Public Health System in the province of Seville (Spain). Analyses were based on Partial Least Squares-Structural Equation Modelling. The internal consistency, convergent validity and discriminant validity of the internal measurement model were assessed. For the external measurement model, global model adjustment and structural validity were assessed. The predictive capacity of the final model was also evaluated. All analyses were performed using SmartPLS version 3.3.2 in consistent mode. ResultsFindings showed an adequate validity of the proposed model, which comprised nine factors: pain catastrophising, hopelessness due to pain, support network, proactivity, treatment compliance, self-care, mobility, resilience, and sleep. The internal validity of the model (Cronbach's alpha and rho_A > 0.70; Average Variance Extracted>0.50; standardised outer loadings>0.60; Heterotrait-Monotrait-Ratio < 0.85), goodness of fit (Standardised Root Mean Square Residuals<0.08; Geodesic and Euclidean distance p-value<0.05) and predictive power with out-of-sample values (Stone-Geisser test>0.5) were adequate. The hypothesised structure of the instrument has also been confirmed (path coefficients>0.3; R2 > 0.1; f2 > 0.2). ConclusionsThe results have shown an adequate internal consistency, convergent validity and discriminant validity of the model. Likewise, the model has shown an adequate goodness of fit, and the validity of its structure and the hypothesis have been confirmed. However, more research is needed in this regard as the possible interaction between the different factors evaluated in the model with the confounding or moderating variables that may exist.

Consumption with earnings, liquidity, and market based models

The market, earnings, and liquidity growth combine to form a proxy for wealth growth, allowing a recursive consumption model with a low risk aversion coefficient, a risk-free rate close to historical, a high equity premium, and a reasonable elasticity of intertemporal substitution. The empirical consumption model does well against major asset pricing puzzles. Tested over 118 years it is not rejected while a forward-looking consumption model using the market alone as a wealth proxy fails. Changing liquidity and earnings forecast consumption and their ‘crashes’ precede consumption declines. We also demonstrate related stock level factors have similar economic magnitude and are significant. These models are consistent to the financial intermediary economic growth literature. Such consistency across approaches adds credence to common earnings and liquidity factors as important risks to investors.

The rise and spread of female labour force participation at the US county level

ABSTRACT In 2011, Fogli and Veldkamp adopted a time–space recursive spatial econometric model to investigate whether the female labour force participation rate varies with past participation rates in their own and in contiguous US counties, based on decennial data over the period 1940–2000, but their results are problematic. The applied estimators are different from the provided descriptions, the predicted contributions of the control variables are not in line with expectations, and the coefficients of the temporal and spatiotemporal lags of the dependent variable indicate instability. This replication study demonstrates that a dynamic spatial econometric model with common factors yields more convincing results in favour of the postulated model.

Casting Defect Detection and Classification of Convolutional Neural Network Based on Recursive Attention Model

The method based on deep learning shows excellent performance in the recognition and classification of surface defects of some industrial products. The method based on deep learning has high efficiency in the identification and classification of surface defects of industrial products, and the false detection rate and missed detection rate are relatively low. However, the recognition accuracy of defect detection and classification of most industrial products needs to be improved, especially for those with similar contours and relatively large structural different casting. This paper takes casting defect detection as the goal and proposes a convolutional neural network casting defect detection and classification (RCNN-DC) algorithm based on the recursive attention model. Through this model, the casting can be better identified and detected, and casting defects can be avoided as much as possible, which is of great significance to the technological development of the industry. First, use a large amount of readily available defect-free sample data to detect anomalous defects. Next, we compare the accuracy and performance of the detection model and the general recognition model. The research results show that the test effect of the RCNN-DC casting defect detection network model is significantly better than the traditional detection model, with a classification accuracy of 96.67%. Then, we compare the RCNN-DC network with three classic popular networks, GooGleNet, ResNet-50, and AlexNet. Among them, AlexNet and ResNet-50 achieved 95.00% and 95.56% classification accuracy, respectively, while GooGleNet achieved slightly better results of 96.38%. In contrast, the accuracy of RCNN-DC is 1.67% higher than that of AlexNet, while the number of FLOPs is reduced by 17.2 times, and the accuracy is 1.09% higher than that of ResNet-50, while the number of FLOPs is reduced by 99.7 times, and the accuracy is higher than GooGleNet 0.29% while FLOPs whose number has been reduced by 36.5 times.

Determinants of Length of Stay after Neonatal Cardiac Surgery Using Path Analysis.

After neonatal cardiac surgery, families, and the health care team strive for exclusive oral feedings before hospital discharge. With the hypothesis that exclusive oral feedings would reduce the length of stay (LOS), a multidimensional path analysis was used to examine a cross-section of 280 neonates from 2009 to 2013. Buttigieg, Abela, and Pace's theoretical framework of structural and process-related determinants of LOS was modeled with hypothesis-driven correlation and directionality. The recursive path model had a good global and local fit with outcome variances of 26% for exclusive oral feeding and LOS. In the full cohort and model groups (single and biventricular), when controlling for covariances: sepsis, birth distance, necrotizing enterocolitis, genetic differences, specialty consults, the age at which neonatal cardiac surgery occurred (β = .23, p ≤ .001) and the duration of postoperative intubation (β = .47, p ≤ .001) more significantly influenced the LOS than intermediate mediation of exclusive oral feedings at discharge.

Rural development in the digital age: Does information and communication technology adoption contribute to credit access and income growth in rural China?

AbstractInformation and communication technology (ICT) plays an important role in rural livelihoods and household well‐being. Therefore, this study examines the impact of ICT adoption on farmers' decisions to access credit and the joint effects of ICT adoption and access to credit on household income using 2016 China Labour‐force Dynamics Survey data. Both recursive bivariate probit model and a selectivity‐corrected ordinary least square regression model are employed for the analysis. The results show that ICT adoption increases the probability of access to credit by 12.8% in rural China and empowers rural women and farm households in relatively less‐developed regions to access credit. ICT adoption and access to credit affect household income differently. ICT adoption significantly increases household income, while access to credit significantly reduces it, primarily because farmers do not use the acquired credit to invest in income‐generating farm and off‐farm business activities. ICT adoption has the largest positive impact on household income at the highest 90th quantile. Our findings suggest that improving rural ICT infrastructure to enhance farmers' ICT adoption and developing ICT‐based financial products to enable households to access sufficient funds can improve rural household welfare.

Fuel choice for rural Tibetan households: Impacts of access to credit

Evidence on the determinants of fuel choice by ethnic groups inhabiting special geomorphic areas is scant. Previous studies suggest that access to credit positively impacts the use of clean cooking energy. This study analyzes the effect of access to credit on fuel choice for rural Tibetan households in Lhasa, the Tibet Autonomous Region, and finds the opposite effect. We apply the recursive bivariate probit model based on a field survey dataset and find that access to credit significantly lowers the likelihood of the rural Tibetan households choosing only clean energy sources as their main fuels for cooking and heating. Further evidence demonstrates that access to credit increases the total income of rural households, as well as the number of yaks raised by those households. A by-product of this, the amount of readily available yak dung, thus also increases. This heightened use of non-clean, cash-free yak dung as a fuel overwhelms the positive effect of increased income on clean fuel adoption. We also find that the effects of access to credit vary with the household size, access to internet and the altitude of home location.

Impact of Left Ventricular End-Diastolic Pressure on the Outcomes of Patients Undergoing Percutaneous Coronary Intervention

Left ventricular end-diastolic pressure (LVEDP) is an important hemodynamic marker of left ventricular performance and affects coronary perfusion. We evaluated the association of LVEDP with patient outcomes after elective or urgent percutaneous coronary intervention (PCI). We included n=49,600 patients undergoing elective or urgent PCI. Patients were divided according to LVEDP tertile for descriptive analysis. The primary end point was in-hospital mortality. A recursive partitioning tree model for mortality was built to guide decision-making in patients with high LVEDP undergoing nonemergent PCI. Overall, n=18,099 patients had an LVEDP <13 mm Hg, n=15,416 had an LVEDP 13 to 18 mm Hg, and n=16,085 had an LVEDP >18 mm Hg. Patients in the high LVEDP tertile had a worse clinical and angiographic/procedural profile and experienced a higher incidence of in-hospital post-PCI adverse outcomes, including death (LVEDP <13 mm Hg 0.3% vs LVEDP 13 to 18 mm Hg 0.4% vs LVEDP >18 mm Hg 0.8%, p <0.001). An elevated LVEDP was an independent predictor of adverse outcomes including mortality. An LVEDP ≥26 mm Hg was identified as a marker of high mortality (1.5%) in patients who underwent elective PCI, with rates varying from 0.5% to 10.4%, based upon a clinical profile defined by hemoglobin, systolic blood pressure, renal and left ventricular function, and atrial fibrillation. In conclusion, an elevated LVEDP is observed in 1/3 of the patients who underwent elective or urgent PCI and is associated with higher rates of in-hospital adverse outcomes, including death. Patients with an LVEDP ≥26 mm Hg who underwent elective PCI had markedly higher mortality rates, suggesting that such patients may warrant further optimization before PCI.

Recursive Convex Model for Optimal Power Flow Solution in Monopolar DC Networks

This paper presents a new optimal power flow (OPF) formulation for monopolar DC networks using a recursive convex representation. The hyperbolic relation between the voltages and power at each constant power terminal (generator or demand) is represented as a linear constraint for the demand nodes and generators. To reach the solution for the OPF problem a recursive evaluation of the model that determines the voltage variables at the iteration t+1 (vt+1) by using the information of the voltages at the iteration t (vt) is proposed. To finish the recursive solution process of the OPF problem via the convex relaxation, the difference between the voltage magnitudes in two consecutive iterations less than the predefined tolerance is considered as a stopping criterion. The numerical results in the 85-bus grid demonstrate that the proposed recursive convex model can solve the classical power flow problem in monopolar DC networks, and it also solves the OPF problem efficiently with a reduced convergence error when compared with semidefinite programming and combinatorial optimization methods. In addition, the proposed approach can deal with radial and meshed monopolar DC networks without modifications in its formulation. All the numerical implementations were in the MATLAB programming environment and the convex models were solved with the CVX and the Gurobi solver.

Using Modified Delphi Study to Develop Instrument for ESG Implementation: A Case Study at an Indonesian Higher Education Institution

Most research states that implementing environmental, social, and governance (ESG) has positive impacts. However, fewer studies have discussed ESG implementation in higher education. This study aimed to develop instruments to assess the ESG atmosphere in higher education institutions. A modified Delphi approach was employed. Experts were invited from a private higher education institution in Indonesia. A deductive study, discussion, and two stages of getting consensus from panelists were conducted. The instrument was distinguished into four types for four groups of higher education stakeholders: Students, Staff, Faculty Members, and Community Members. The I-CVIs ranged from 0.80–1.00, while the minimum values of S-CVI/Ave and S-CVI/UA were 0.98 and 0.91, respectively, meaning the content validity was excellent. The final version instrument has been tested and declared valid, reliable, and ready to be used for empirical research for universities to assess their contribution to the Sustainability Development Goals (SDGs). There are also opportunities to conduct further research on the existence of recursive and non-recursive models between factors.

A Regression Tree Analysis to Identify Factors Predicting Frailty: The International Mobility in Aging Study

Introduction: Frailty is a complex geriatric syndrome with a multifaceted etiology. We aimed to identify the best combinations of risk factors that predict the development of frailty using recursive partitioning models. Methods: We analyzed reports from 1,724 community-dwelling men and women aged 65–74 years participating in the International Mobility in Aging Study (IMIAS). Frailty was measured using frailty phenotype scale that included five physical components: unintentional weight loss, weakness, slow gait, exhaustion, and low physical activity. Frailty was defined as presenting three of the above five conditions, having one or two conditions indicated prefrailty and showing none as robust. Socio-demographic, physical, lifestyle, psycho-social, and life-course factors were included in the analysis as potential predictors. Results: 21% of pre-frail and robust participants showed a worse stage of frailty in 2014 compared to 2012. In addition to functioning variables, fear of falling (FOF), income, and research site (Canada vs. Latin America vs. Albania) were significant predictors of the development of frailty. Additional significant predictors after exclusion of functioning factors included education, self-rated health, and BMI. Conclusions: In addition to obvious risk factors for frailty (such as functioning), socio-economic factors and FOFs are also important predictors. Clinical assessment of frailty should include measurement of these factors to identify high-risk individuals.

LIDER

Passage retrieval has been studied for decades, and many recent approaches of passage retrieval are using dense embeddings generated from deep neural models, called "dense passage retrieval". The state-of-the-art end-to-end dense passage retrieval systems normally deploy a deep neural model followed by an approximate nearest neighbor (ANN) search module. The model generates embeddings of the corpus and queries, which are then indexed and searched by the high-performance ANN module. With the increasing data scale, the ANN module unavoidably becomes the bottleneck on efficiency. An alternative is the learned index, which achieves significantly high search efficiency by learning the data distribution and predicting the target data location. But most of the existing learned indexes are designed for low dimensional data, which are not suitable for dense passage retrieval with high-dimensional dense embeddings. In this paper, we propose LIDER , an efficient high-dimensional L earned I ndex for large-scale DE nse passage R etrieval. LIDER has a clustering-based hierarchical architecture formed by two layers of core models. As the basic unit of LIDER to index and search data, a core model includes an adapted recursive model index (RMI) and a dimension reduction component which consists of an extended SortingKeys-LSH (SK-LSH) and a key re-scaling module. The dimension reduction component reduces the high-dimensional dense embeddings into one-dimensional keys and sorts them in a specific order, which are then used by the RMI to make fast prediction. Experiments show that LIDER has a higher search speed with high retrieval quality comparing to the state-of-the-art ANN indexes on passage retrieval tasks, e.g., on large-scale data it achieves 1.2x search speed and significantly higher retrieval quality than the fastest baseline in our evaluation. Furthermore, LIDER has a better capability of speed-quality trade-off.

Generalizing the properties of Finite Iterative Method for the Computation of the Covariance Matrix Implied by a Recursive Path Model

In this paper, we generalize the properties of the correlation matrix implied bya recursive path model using the Finite Iterative Method into the covariance case wherevariables are no more supposed to be standardized. We demonstrate that the implied co-variance matrix computed using the Finite Iterative Method is affine with respect to themodel parameters. Moreover, many other properties derive from this affinity and will be usedto simplify the computation of the first as well as the second derivatives of the UnweightedLeast Square Function used as an objective function in the estimation of the model param-eters. Illustrated and numerical examples are given to show the advantage of the proposedproperties as an alternative to the classical approximation used to compute the aforemen-tioned derivatives.