Merge changes from github.

PiperOrigin-RevId: 194997009

1 files changed, 8 insertions, 12 deletions

diff --git a/tensorflow/contrib/optimizer_v2/adam.py b/tensorflow/contrib/optimizer_v2/adam.py
index 42b7f92a76..d538ad0fb0 100644
--- a/tensorflow/contrib/optimizer_v2/adam.py
+++ b/tensorflow/contrib/optimizer_v2/adam.py
@@ -40,23 +40,19 @@ class AdamOptimizer(optimizer_v2.OptimizerV2):
 
     Initialization:
 
-    ```
-    m_0 <- 0 (Initialize initial 1st moment vector)
-    v_0 <- 0 (Initialize initial 2nd moment vector)
-    t <- 0 (Initialize timestep)
-    ```
+    $$m_0 := 0 (Initialize initial 1st moment vector)$$
+    $$v_0 := 0 (Initialize initial 2nd moment vector)$$
+    $$t := 0 (Initialize timestep)$$
 
     The update rule for `variable` with gradient `g` uses an optimization
     described at the end of section2 of the paper:
 
-    ```
-    t <- t + 1
-    lr_t <- learning_rate * sqrt(1 - beta2^t) / (1 - beta1^t)
+    $$t := t + 1$$
+    $$lr_t := \text{learning_rate} * \sqrt{(1 - beta_2^t) / (1 - beta_1^t)}$$
 
-    m_t <- beta1 * m_{t-1} + (1 - beta1) * g
-    v_t <- beta2 * v_{t-1} + (1 - beta2) * g * g
-    variable <- variable - lr_t * m_t / (sqrt(v_t) + epsilon)
-    ```
+    $$m_t := beta_1 * m_{t-1} + (1 - beta_1) * g$$
+    $$v_t := beta_2 * v_{t-1} + (1 - beta_2) * g * g$$
+    $$variable := variable - lr_t * m_t / (\sqrt{v_t} + \epsilon)$$
 
     The default value of 1e-8 for epsilon might not be a good default in
     general. For example, when training an Inception network on ImageNet a