ML for Scientists: L10
Carol(ina) Cuesta-Lazaro
y_i = \mu_i, \alpha_i = f_{\phi_i}(x_{1:i-1})
MADE: Masked MLP
x_1
x_2
x_3
y_1
y_2
y_3
h_1
h_2
h_3
h_4
h_5
h_6
\frac{dx_t}{dt} = v^\phi_t(x_t)
x_1 = x_0 + \int_0^1 v^\phi_t(x_t) dt
\frac{\partial p(x_t)}{ \partial t} = - \nabla \left( v^\phi_t(x_t) p(x_t) \right)
In continuous time
Continuity Equation
[Image Credit: "Understanding Deep Learning" Simon J.D. Prince]
x_0 = x_1 + \int_1^0 v^\phi_t(x_t) dt
Chen et al. (2018), Grathwohl et al. (2018)
x_1 = x_0 + \int_0^1 v_\theta (x(t),t) dt
Generate
x_0
x_1
t
Evaluate Probability
Money plot - Nov 18th -> Discuss in class Nov 19th
Copy of Copy of Copy of ML For Scientists: L9
By carol cuesta
