aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYuchen Pei <me@ypei.me>2018-12-03 10:11:14 +0100
committerYuchen Pei <me@ypei.me>2018-12-03 10:11:14 +0100
commit23a7b0321d57e8bed5424d8637982eb9685d60ae (patch)
tree904dcd1dda00626cf97eaeae822fec4a99c1f68e
parent7d020bdb443414c054ac3624b0dd021df291e804 (diff)
minor edit
-rw-r--r--posts/2018-12-02-lime-shapley.md4
1 files changed, 2 insertions, 2 deletions
diff --git a/posts/2018-12-02-lime-shapley.md b/posts/2018-12-02-lime-shapley.md
index b6b38cb..c9ada5b 100644
--- a/posts/2018-12-02-lime-shapley.md
+++ b/posts/2018-12-02-lime-shapley.md
@@ -298,8 +298,8 @@ A bigger question is: how effective is SHAP?
Evaluating SHAP
---------------
-The quest of the SHAP paper can be decoupled into two independent components.
-The niceties of Shapley values and the choice of the coalitional game $v$.
+The quest of the SHAP paper can be decoupled into two independent components:
+the niceties of Shapley values and the choice of the coalitional game $v$.
The SHAP paper argues that Shapley values $\phi_i(v)$ are a good measurement because they
are the only values satisfying the some nice properties including the Efficiency