diff --git a/sgd.cabal b/sgd.cabal
--- a/sgd.cabal
+++ b/sgd.cabal
@@ -1,5 +1,5 @@
 name:               sgd
-version:            0.3.4
+version:            0.3.5
 synopsis:           Stochastic gradient descent
 description:
     Implementation of a Stochastic Gradient Descent optimization method.
@@ -25,7 +25,7 @@
 
     build-depends:
         base            >= 4        && < 5
-      , containers      >= 0.4      && < 0.5
+      , containers      >= 0.4      && < 0.6
       , vector          >= 0.10     && < 0.11
       , random          >= 1.0      && < 1.1
       , primitive       >= 0.5      && < 0.6
diff --git a/src/Numeric/SGD/Grad.hs b/src/Numeric/SGD/Grad.hs
--- a/src/Numeric/SGD/Grad.hs
+++ b/src/Numeric/SGD/Grad.hs
@@ -32,7 +32,11 @@
 import Control.DeepSeq (deepseq)
 import Control.Monad.Par (spawn_)
 #endif
+#if MIN_VERSION_containers(0,5,0)
+import qualified Data.IntMap.Strict as M
+#else
 import qualified Data.IntMap as M
+#endif
 
 import Numeric.SGD.LogSigned
 
@@ -44,7 +48,9 @@
 
 {-# INLINE insertWith #-}
 insertWith :: (a -> a -> a) -> M.Key -> a -> M.IntMap a -> M.IntMap a
-#if MIN_VERSION_containers(0,4,1)
+#if MIN_VERSION_containers(0,5,0)
+insertWith = M.insertWith
+#elif MIN_VERSION_containers(0,4,1)
 insertWith = M.insertWith'
 #else
 insertWith f k x m = 
@@ -55,11 +61,6 @@
         Just y  ->
             let z = f x y
             in  z `seq` Just z
--- insertWith f k x m = case M.lookup k m of
---     Just y  ->
---         let x' = f x y
---         in  x' `seq` M.insert k x' m
---     Nothing -> x `seq` M.insert k x m
 #endif
 
 -- | Add normal-domain double to the gradient at the given position.