cosmit

mlsys2022style/exp.tex

 % !TEX root = main.tex
 
-\section{Comparative Evaluation and Extensions}
+\section{Experiments}
 \label{section:non-clustered}
 
 In this section, we first compare D-Cliques to alternative topologies to

mlsys2022style/setting.tex

@@ -14,10 +14,10 @@ node has
 access to a local dataset that
  follows its own local distribution $D_i$ which may differ from that of other
  nodes.
-In this work, we focus on label distribution skew: denoting by $p_i(x,y)=p_i
+In this work, we tackle label distribution skew: denoting by $p_i(x,y)=p_i
 (x|y)p_i(y)$ the
 probability of $(x,y)$ under the local distribution $D_i$ of node $i$, we
-assume that $p_i(y)$ varies across nodes. We refer to 
+assume that $p_i(y)$ may vary across nodes. We refer to 
 \cite{kairouz2019advances,quagmire} for concrete examples of problems
 with label distribution skew.