[HTML][HTML] Mean field analysis of neural networks: A central limit theorem
J Sirignano, K Spiliopoulos - Stochastic Processes and their Applications, 2020 - Elsevier
We rigorously prove a central limit theorem for neural network models with a single hidden
layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) …
layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) …
Mean field analysis of neural networks: A law of large numbers
J Sirignano, K Spiliopoulos - SIAM Journal on Applied Mathematics, 2020 - SIAM
Machine learning, and in particular neural network models, have revolutionized fields such
as image, text, and speech recognition. Today, many important real-world applications in …
as image, text, and speech recognition. Today, many important real-world applications in …
Counterparty contagion in context: Contributions to systemic risk
JC Staum - Available at SSRN 1963459, 2012 - papers.ssrn.com
This article surveys models of counterparty contagion and their application in systemic risk
management, emphasizing the network of counterparty relationships. It addresses how …
management, emphasizing the network of counterparty relationships. It addresses how …
Particle systems with singular interaction through hitting times: application in systemic risk modeling
S Nadtochiy, M Shkolnikov - 2019 - projecteuclid.org
We propose an interacting particle system to model the evolution of a system of banks with
mutual exposures. In this model, a bank defaults when its normalized asset value hits a …
mutual exposures. In this model, a bank defaults when its normalized asset value hits a …
[HTML][HTML] Convergence, fluctuations and large deviations for finite state mean field games via the master equation
We show the convergence of finite state symmetric N-player differential games, where
players control their transition rates from state to state, to a limiting dynamics given by a finite …
players control their transition rates from state to state, to a limiting dynamics given by a finite …
[图书][B] Concentration risk in credit portfolios
E Lütkebohmert - 2008 - books.google.com
Modeling and management of credit risk are the main topics within banks and other lending
institutions. Historical experience shows that, in particular, concentration of risk in credit …
institutions. Historical experience shows that, in particular, concentration of risk in credit …
-player games and mean-field games with absorption
L Campi, M Fischer - 2018 - projecteuclid.org
We introduce a simple class of mean-field games with absorbing boundary over a finite time
horizon. In the corresponding N-player games, the evolution of players' states is described …
horizon. In the corresponding N-player games, the evolution of players' states is described …
Default clustering in large portfolios: Typical events
We develop a dynamic point process model of correlated default timing in a portfolio of firms,
and analyze typical default profiles in the limit as the size of the pool grows. In our model, a …
and analyze typical default profiles in the limit as the size of the pool grows. In our model, a …
A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data Perspective
Enterprise financial risk analysis aims at predicting the future financial risk of enterprises.
Due to its wide and significant application, enterprise financial risk analysis has always been …
Due to its wide and significant application, enterprise financial risk analysis has always been …
Large portfolio asymptotics for loss from default
We prove a law of large numbers for the loss from default and use it for approximating the
distribution of the loss from default in large, potentially heterogeneous portfolios. The density …
distribution of the loss from default in large, potentially heterogeneous portfolios. The density …