local allReduceSGD = require 'distlearn.AllReduceSGD'(tree)
-- Make sure all the nodes start with the same parameter values
allReduceSGD.synchronizeParameters(params)
for _ = 1,epochs do
   for _ = 1,steps
      -- Compute your gradients as normal
      local grads = computeYourGrads(...)
      -- Sum and normalize them
      allReduceSGD.sumAndNormalizeGradients(grads)
      -- Do your SGD as normal
      SGD(params, grads)
   end
   -- Before validating we should make sure all nodes have
   -- the exact same parameter values
   allReduceSGD.synchronizeParameters(params)
   -- Validate...
end

-- Use a tau of 10 and an alpha of 0.2
local allReduceEA = require 'distlearn.AllReduceEA'(tree, 10, 0.2)
-- Make sure all the nodes start with the same parameter values
allReduceEA.synchronizeParameters(params)
for _ = 1,epochs do
   for _ = 1,steps
      -- Compute your gradients as normal
      local grads = computeYourGrads(...)
      -- Do your SGD as normal
      SGD(params, grads)
      -- Average the params
      allReduceEA.averageParameters(params)
   end
   -- Make sure the center's haven't drifted too far due to
   -- floating point precision error build up
   allReduceEA.synchronizeCenter(params)
   -- Validate...
end