3 Hits in 5.6 sec

PASTO: Strategic Parameter Optimization in Recommendation Systems – Probabilistic is Better than Deterministic [article]

Weicong Ding, Hanlin Tang, Jingshuo Feng, Lei Yuan, Sen Yang, Guangxu Yang, Jie Zheng, Jing Wang, Qiang Su, Dong Zheng, Xuezhong Qiu, Yongqi Liu (+8 others)
2021 arXiv   pre-print
In this setting with multiple and constrained goals, this paper discovers that a probabilistic strategic parameter regime can achieve better value compared to the standard regime of finding a single deterministic  ...  In addition to building accurate predictive models, it is also crucial to optimize this set of 'strategic parameters' so that primary goals are optimized while secondary guardrails are not hurt.  ...  parameter can achieve better overall rewards than single deterministic Algorithm 1 1 Probabilistic pArameter Optimization with unbiased STOchastic Gradient Approximation (PASTO) Require: Initial estimator  ... 
arXiv:2108.09076v1 fatcat:wnhgbegpabaihh6rlesgrlxq4e

Impact Assessment Framework Accounting for the Life Cycle of Volcanic Ash

Lucia Dominguez Barragan, Costanza Bonadonna
As a recommendation, a complete damage collection template for the power system is presented in Figure 4 .20.  ...  In volcanology, important advances were achieved in probabilistic and deterministic volcanic hazard assessments during the last 20-30 years (see Connor et al. [2015] for a review).  ...  A complete list of interviews is presented in the • How many clients, people and/or users were affected?  ... 
doi:10.13097/archive-ouverte/unige:141677 fatcat:ihrlkx43j5ggpantifmtt5iemu

Stochastic Frontier Models with Dependent Errors based on Normal and Exponential Margins

Francisco Javier, Blancas Peral, Angel, F Tenorio Villalón, Gómez -Déniz, Emilio, Jorge Pérez-Rodríguez
An illustration using real data from the econometric literature is provided to show the applicability of the model proposed.  ...  Accordingly, the main aim of the present paper is to enhance stochastic production frontier and stochastic cost frontier modelling by proposing a bivariate distribution for dependent errors which allows  ...  We thank the David Nazarian College of Business and Economics at California State University, Northridge for support in the form of a sabbatical grant for one of the authors.  ...