Merge pull request #21552 from sbrodehl:patch-1

PiperOrigin-RevId: 210392464

1 files changed, 4 insertions, 5 deletions

diff --git a/tensorflow/contrib/optimizer_v2/adam.py b/tensorflow/contrib/optimizer_v2/adam.py
index 631d4f44df..04b1552b61 100644
--- a/tensorflow/contrib/optimizer_v2/adam.py
+++ b/tensorflow/contrib/optimizer_v2/adam.py
@@ -40,15 +40,14 @@ class AdamOptimizer(optimizer_v2.OptimizerV2):
 
     Initialization:
 
-    $$m_0 := 0 (Initialize initial 1st moment vector)$$
-    $$v_0 := 0 (Initialize initial 2nd moment vector)$$
-    $$t := 0 (Initialize timestep)$$
-
+    $$m_0 := 0 \text{(Initialize initial 1st moment vector)}$$
+    $$v_0 := 0 \text{(Initialize initial 2nd moment vector)}$$
+    $$t := 0 \text{(Initialize timestep)}$$
     The update rule for `variable` with gradient `g` uses an optimization
     described at the end of section2 of the paper:
 
     $$t := t + 1$$
-    $$lr_t := \text{learning_rate} * \sqrt{(1 - beta_2^t) / (1 - beta_1^t)}$$
+    $$lr_t := \text{learning\_rate} * \sqrt{1 - beta_2^t} / (1 - beta_1^t)$$
 
     $$m_t := beta_1 * m_{t-1} + (1 - beta_1) * g$$
     $$v_t := beta_2 * v_{t-1} + (1 - beta_2) * g * g$$