We often think of Momentum as a means of dampening oscillations and
speeding up the iterations, leading to faster convergence. But it has other interesting behavior. It allows a
larger range of step-sizes to be used, and creates its own oscillations. What is going on?
Before diving in: if you haven’t encountered t-SNE before, here’s what you need to know about the math behind it.
The goal is to take a set of points in a high-dimensional space and find a faithful representation of those points
in a lower-dimensional space, typically the 2D plane. The algorithm is non-linear and adapts to the underlying
data, performing different transformations on different regions. Those differences can be a major source of
confusion.
This is the first paragraph of the article. Test a long — dash -- here it is.
Test for owner's possessive. Test for "quoting a passage." And another sentence. Or two. Some flopping fins; for
diving.
Here's a test of an inline equation c = a^2 + b^2. Also with configurable katex standards just
using inline '$' signs: $$x^2$$ And then there's a block equation:
We can also cite external publications. . We should also be testing footnotes
This will become a hoverable footnote. This will become a hoverable footnote. This will become a
hoverable footnote. This will become a hoverable footnote. This will become a hoverable footnote. This will
become a hoverable footnote. This will become a hoverable footnote. This will become a hoverable footnote.
. There are multiple footnotes, and they appear in the appendixGiven I have coded them
right. Also, here's math in a footnote: c = \sum_0^i{x}. Also, a citation. Box-ception! as well.