Understand Jensen’s Inequality and Attention Mechanism in Deep Learning – Deep Learning Tutorial

By | March 7, 2021

Attention mechanism is an important method to improve the performance of deep learning model. However, there are two basic forms. They are:

\(s_i = \sum_{j=1}^nf(a_{ij}w_{ij}) \)    (1)


\(s_i = \sum_{j=1}^na_{ij}f(w_{ij})\)    (2)

where \(a_{ij}\) is the attention weight of word \(w_{ij}\).

Which form is better? Equation (1) or (2)?

We can find the answer from Jensen’s Inequality.

Jensen’s Inequality

As to convex functions, Jensen’s Inequality is:

Jensen’s Inequality

Here is the full text:


The illustrative example looks like:

Jensen’s Inequality example

As to deep learning, the loss function is a convex function, in order to get the minimum value by SGD. We can use Equation (1).

In order to determine a function is convex or not, we can compute the second derivative of it.

Leave a Reply

Your email address will not be published. Required fields are marked *