Content deleted Content added
AzzurroLan (talk | contribs) No edit summary |
AzzurroLan (talk | contribs) |
||
Line 9:
===Mathematical Method===
A standard BSDE can be expressed as:
<math> Y_t = \xi + \int_t^T f(s, Y_s, Z_s) ds - \int_t^T Z_s dW_s </math>
where <math> Y_t </math> is the target variable, <math> \xi </math> is the terminal condition, <math> f </math> is the driver function, and <math> Z_t </math> is the process associated with the [[Brownian motion]] <math> W_t </math>. The deep BSDE method constructs neural networks to approximate the solutions for <math> Y </math> and <math> Z </math>, and utilizes [[stochastic gradient descent]] and other optimization algorithms for training<ref name="Han2018" />.
| |||