Free Webinar: Alexandre Antonov - Neural Networks with Asymptotics Control
Webinar
Thursday, April 16, 2020 - 05:00 PM
Until: Thursday, April 16, 2020 - 07:00 PM
(Adjusted for timezone: Europe/London)
Categories
Details
PLEASE NOTE THAT THIS WEBINAR WILL START ON THURSDAY, 16 APRIL, 2020, AT 5:00pm ***LONDON TIME***
TITLE: Neural Networks with Asymptotics Control
ABSTRACT:
Artificial Neural Networks (ANNs) have recently been proposed as accurate and fast approximators in various derivatives pricing applications. ANNs typically excel in fitting functions they approximate at the input parameters they are trained on, and often are quite good in interpolating between them. However, for standard ANNs, their extrapolation behavior – an important aspect for financial applications – cannot be controlled due to complex functional forms typically involved. We overcome this significant limitation and develop a new type of neural networks that incorporate large-value asymptotics, when known, allowing explicit control over extrapolation.
This new type of asymptotics-controlled ANNs is based on two novel technical constructs, a multi-dimensional spline interpolator with prescribed asymptotic behavior, and a custom ANN layer that guarantees zero asymptotics in chosen directions. Asymptotics control brings a number of important benefits to ANN applications in finance such as well-controlled behavior under stress scenarios, graceful handling of regime switching, and improved interpretability.
BIOGRAPHY
A 20 year Numerix veteran, Dr. Antonov is a Chief Analyst at Danske Bank in Copenhagen. Dr. Antonov received his PhD degree from the Landau Institute for Theoretical Physics. His activity is concentrated on modeling and numerical methods for interest rates, cross currency, hybrid, credit and CVA and FVA. Dr. Antonov is a published author for multiple publications in mathematical finance, including Risk magazine and a frequent speaker at financial conferences. He was named Risk Magazine's 2016 Quant of the Year. Most recently he served as a Director at Standard Chartered in London.
LINKS TO PAPERS AND ANIMATIONS
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3544698
ZOOM INFORMATION
Topic: Neural Networks with Asymptotics Control
Time: Apr 16,[masked]:00 PM London
Join Zoom Meeting
https://zoom.us/j/490656208?pwd=dVk0dlBMT3FDK2JGSlp5c0o4MjcxZz09
Meeting ID:[masked]
Password:[masked]
One tap mobile
[masked],,[masked]# United Kingdom
[masked],,[masked]# United Kingdom
Dial by your location
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] US
[masked] US
[masked] US (Chicago)
[masked] US (Houston)
[masked] US (San Jose)
[masked] US (New York)
[masked] US (San Jose)
Meeting ID:[masked]
Password:[masked]
Find your local number: https://zoom.us/u/adKZjPF50X
For more information, visit https://www.meetup.com/thalesians/events/269859850/
PLEASE NOTE THAT THIS WEBINAR WILL START ON THURSDAY, 16 APRIL, 2020, AT 5:00pm ***LONDON TIME***
TITLE: Neural Networks with Asymptotics Control
ABSTRACT:
Artificial Neural Networks (ANNs) have recently been proposed as accurate and fast approximators in various derivatives pricing applications. ANNs typically excel in fitting functions they approximate at the input parameters they are trained on, and often are quite good in interpolating between them. However, for standard ANNs, their extrapolation behavior – an important aspect for financial applications – cannot be controlled due to complex functional forms typically involved. We overcome this significant limitation and develop a new type of neural networks that incorporate large-value asymptotics, when known, allowing explicit control over extrapolation.
This new type of asymptotics-controlled ANNs is based on two novel technical constructs, a multi-dimensional spline interpolator with prescribed asymptotic behavior, and a custom ANN layer that guarantees zero asymptotics in chosen directions. Asymptotics control brings a number of important benefits to ANN applications in finance such as well-controlled behavior under stress scenarios, graceful handling of regime switching, and improved interpretability.
BIOGRAPHY
A 20 year Numerix veteran, Dr. Antonov is a Chief Analyst at Danske Bank in Copenhagen. Dr. Antonov received his PhD degree from the Landau Institute for Theoretical Physics. His activity is concentrated on modeling and numerical methods for interest rates, cross currency, hybrid, credit and CVA and FVA. Dr. Antonov is a published author for multiple publications in mathematical finance, including Risk magazine and a frequent speaker at financial conferences. He was named Risk Magazine's 2016 Quant of the Year. Most recently he served as a Director at Standard Chartered in London.
LINKS TO PAPERS AND ANIMATIONS
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3544698
ZOOM INFORMATION
Topic: Neural Networks with Asymptotics Control
Time: Apr 16,[masked]:00 PM London
Join Zoom Meeting
https://zoom.us/j/490656208?pwd=dVk0dlBMT3FDK2JGSlp5c0o4MjcxZz09
Meeting ID:[masked]
Password:[masked]
One tap mobile
[masked],,[masked]# United Kingdom
[masked],,[masked]# United Kingdom
Dial by your location
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] United Kingdom
[masked] US
[masked] US
[masked] US (Chicago)
[masked] US (Houston)
[masked] US (San Jose)
[masked] US (New York)
[masked] US (San Jose)
Meeting ID:[masked]
Password:[masked]
Find your local number: https://zoom.us/u/adKZjPF50X
For more information, visit https://www.meetup.com/thalesians/events/269859850/