Stability of stochastic gradient descent

One paper that, in my opinion, will be more influential than the garbage constantly published on many paid journals, is “Train faster, generalize better: Stability of stochastic gradient descent”, written¬†by Moritz Hardt at Google. The authors published it on Arxiv, … Continue reading

Dimensionality reduction in one slide (part 2)

Extracting knowledge from large datasets with large number of variables is always tricky. Dimensionality reduction helps in analyzing high dimensional data, still maintaining most of the information hidden behind complexity. Here are some methods that you must try before further … Continue reading

Dimensionality reduction in one slide (Part 1)

  Extracting knowledge from large datasets with large number of variables is always tricky. Dimensionality reduction helps in analyzing high dimensional data, still maintaining most of the information hidden behind complexity. Here are some methods that you must try before … Continue reading