diff --git a/main.tex b/main.tex index 1ec92e26832d65a096b11df46f1046f298580ea5..682998c66160e8a46d4b5c33c5fd4c243ff733a0 100644 --- a/main.tex +++ b/main.tex @@ -467,7 +467,7 @@ Figure~\ref{fig:d-cliques-cifar10-convolutional} shows convergence speeds for al \section{Related Work} \label{section:related-work} -%\aurelien{TODO: where to place TornadoAggregate and related refs?} +\aurelien{TODO: where to place TornadoAggregate and related refs?} \paragraph{Dealing with non-IID data in server-based FL.} Dealing with non-IID data in server-based FL has @@ -500,7 +500,7 @@ the rows and columns of $W$ do not exactly sum to $1$ (due to finite precision), these small differences get amplified by the proposed updates and make the algorithm diverge.} -%\aurelien{emphasize that they only do small scale experiments} +\aurelien{emphasize that they only do small scale experiments} % non-IID known to be a problem for fully decentralized FL. cf Jelasity paper % D2 and other recent papers on modifying updates: Quasi-Global Momentum, @@ -516,7 +516,7 @@ algorithm \cite{lian2017d-psgd} beyond removing some neighbor contributions that would otherwise bias the direction of the gradient. -%\aurelien{add personalized models - or merge all that in specific paragraph} +\aurelien{add personalized models - or merge all that in specific paragraph} % An originality of our approach is to focus on the effect of topology % level without significantly changing the original simple and efficient D-SGD