Using a discrete dynamical system model for a networked social system, we consider the problem of learning a class of local interaction functions in such networks. Our focus is on learning local functions which are based on pairwise disjoint coalitions formed from the neighborhood of each node. Our work considers both active query and PAC learning models. We establish bounds on the number of queries needed to learn the local functions under both models. We also establish a complexity result regarding efficient consistent learners for such functions. Our experimental results on synthetic and real social networks demonstrate how the numbermore »
Bounds and Complexity Results for Learning CoalitionBased Interaction Functions in Networked Social Systems
Using a discrete dynamical system model for a networked social system, we consider the problem of learning a class of local interaction functions in such networks. Our focus is on learning local functions which are based on pairwise disjoint coalitions formed from the neighborhood of each node. Our work considers both active query and PAC learning models. We establish bounds on the number of queries needed to learn the local functions under both models.We also establish a complexity result regarding efficient consistent learners for
such functions. Our experimental results on synthetic and real social networks demonstrate how the number of queries depends on the structure of the underlying network and number of coalitions.
 Award ID(s):
 1916670
 Publication Date:
 NSFPAR ID:
 10203860
 Journal Name:
 Proceedings of the AAAI Conference on Artificial Intelligence
 Volume:
 34
 Page Range or eLocationID:
 31383145
 ISSN:
 21595399
 Sponsoring Org:
 National Science Foundation
More Like this


Using a discrete dynamical system model for a networked social system, we consider the problem of learning a class of local interaction functions in such networks. Our focus is on learning local functions which are based on pairwise disjoint coalitions formed from the neighborhood of each node. Our work considers both active query and PAC learning models. We establish bounds on the number of queries needed to learn the local functions under both models.We also establish a complexity result regarding efficient consistent learners for such functions. Our experimental results on synthetic and real social networks demonstrate how the number ofmore »

Using synchronous dynamical systems (SyDSs) as a formal model for networked social systems, we study the problem of inferring users’ choices in such systems. We observe that SyDSs with deterministic and probabilistic threshold functions as local functions can capture users’ choices in the context of contagion propagation in social networks. We use an active query mechanism where a user interacts with a system by submitting queries, and the responses to the queries are used to infer the local functions. We develop methods that provide provably efficient query sets for inferring both deterministic and probabilistic forms of threshold functions. We alsomore »

Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)The Neuronix highperformance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from lowend consumer grade devices such as the Nvidia GTX 970 to higherend devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely computeintensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3]more »

Bach, Francis ; Blei, David ; Scholkopf, Bernhard (Ed.)This paper investigates the asymptotic behaviors of gradient descent algorithms (particularly accelerated gradient descent and stochastic gradient descent) in the context of stochastic optimization arising in statistics and machine learning, where objective functions are estimated from available data. We show that these algorithms can be computationally modeled by continuoustime ordinary or stochastic differential equations. We establish gradient flow central limit theorems to describe the limiting dynamic behaviors of these computational algorithms and the largesample performances of the related statistical procedures, as the number of algorithm iterations and data size both go to infinity, where the gradient flow central limit theoremsmore »