Take a look at the image below from [Off Convex](http://www.offconvex.org/2016/03/22/saddlepoints/). In a convex function (rightmost image), there is only one local minimum, which is also the global minimum. But in a non-convex function (leftmost), there may be multiple local minima and often joining two local minima is a saddle point. If you are approaching from a higher point, the gradient is comparatively flatter, and you risk getting stuck there, especially if you are moving only in one direction. [![Diagrammatic representation of a saddle point][1]][1] Now the thing is, whether you are optimizing using [mini-batch] or stochastic gradient descent, the underlying non-convex function is the same, and the gradient is a property of the this function. When doing mini-batch, you consider many samples at a time and take the gradient step averaged over all of them. This reduces variance. But if the average gradient direction is still pointing in the same direction as the saddle point, then you still risk getting stuck there. The analogy is, if you're taking 2 steps forward and 1 step back, averaging over those, you ultimately end up taking 1 step forward. If you perform SGD instead, you take all the steps one after the other, but if you're still moving in a single direction, you can reach the saddle point and find that the gradient on all sides is fairly flat and the step size is too small to go over this flat part. This doesn't have anything to do with whether you considered a bunch of points at once, or one by one in random order. [1]: https://i.sstatic.net/VqQnf.png [mini-batch]: http://sebastianruder.com/optimizing-gradient-descent/index.html#minibatchgradientdescent Take a look at the visualization [here](http://sebastianruder.com/optimizing-gradient-descent/index.html#visualizationofalgorithms). Even with SGD, the fluctuations occur only along one dimension, with the steps getting smaller and smaller, until it converges at the saddle point. In this case, the mini-batch method would just reduce the amount of fluctuation but would not be able to change its direction. The way methods like momentum, ADAGRAD, Adam etc are able to break out of this, is by considering the past gradients. Consider momentum, $$ v_t = \gamma v_{t-1} + \eta \nabla_{theta} J(\theta) $$ which adds a portion of the last gradient, $v_{t-1}$. In case you've just been going back and forth in one direction, essentially changing signs, it ends up dampening your progress. While if there has consistently been positive progress in one direction, it ends up building up and going down that way.