Diffusion Model Variational Lower Bound Loss

Tags: #machine learning #diffusion

Equation

$$\begin{aligned} L_\text{VLB} &= L_T + L_{T-1} + \dots + L_0 \\ \text{where } L_T &= D_\text{KL}(q(\mathbf{x}_T \vert \mathbf{x}_0) \parallel p_\theta(\mathbf{x}_T)) \\ L_t &= D_\text{KL}(q(\mathbf{x}_t \vert \mathbf{x}_{t+1}, \mathbf{x}_0) \parallel p_\theta(\mathbf{x}_t \vert\mathbf{x}_{t+1})) \text{ for }1 \leq t \leq T-1 \\ L_0 &= - \log p_\theta(\mathbf{x}_0 \vert \mathbf{x}_1) \end{aligned}$$

Latex Code

                                 \begin{aligned}
            L_\text{VLB} &= L_T + L_{T-1} + \dots + L_0 \\
            \text{where } L_T &= D_\text{KL}(q(\mathbf{x}_T \vert \mathbf{x}_0) \parallel p_\theta(\mathbf{x}_T)) \\
            L_t &= D_\text{KL}(q(\mathbf{x}_t \vert \mathbf{x}_{t+1}, \mathbf{x}_0) \parallel p_\theta(\mathbf{x}_t \vert\mathbf{x}_{t+1})) \text{ for }1 \leq t \leq T-1 \\
            L_0 &= - \log p_\theta(\mathbf{x}_0 \vert \mathbf{x}_1)
            \end{aligned}
                            

Have Fun

Let's Vote for the Most Difficult Equation!

Introduction

Equation



Latex Code

            \begin{aligned}
            L_\text{VLB} &= L_T + L_{T-1} + \dots + L_0 \\
            \text{where } L_T &= D_\text{KL}(q(\mathbf{x}_T \vert \mathbf{x}_0) \parallel p_\theta(\mathbf{x}_T)) \\
            L_t &= D_\text{KL}(q(\mathbf{x}_t \vert \mathbf{x}_{t+1}, \mathbf{x}_0) \parallel p_\theta(\mathbf{x}_t \vert\mathbf{x}_{t+1})) \text{ for }1 \leq t \leq T-1 \\
            L_0 &= - \log p_\theta(\mathbf{x}_0 \vert \mathbf{x}_1)
            \end{aligned}
        

Explanation

Related Documents

Related Videos

Discussion

Comment to Make Wishes Come True

Leave your wishes (e.g. Passing Exams) in the comments and earn as many upvotes as possible to make your wishes come true


  • Les Finch
    The anxiety of this exam is overwhelming; I hope I pass.
    2023-06-16 00:00

    Reply


    Anne Brooks reply to Les Finch
    Best Wishes.
    2023-07-11 00:00

    Reply


  • Marilyn Alexander
    Here's to passing this test, let's make it happen!
    2023-12-11 00:00

    Reply


    Steven Harris reply to Marilyn Alexander
    You can make it...
    2023-12-21 00:00

    Reply


  • Neil Richmond
    Striving to pass this upcoming test.
    2023-02-01 00:00

    Reply


    Olivia Evans reply to Neil Richmond
    You can make it...
    2023-02-05 00:00

    Reply