I am reading Ian Goodfellow's book about deep learning and when it introduces exponential distribution, it says "In the context of deep learning, we often want to have a probability distribution with a sharp point at x=0." I don't understand why the probability distribution should have this character, does it help to train the model? The book is Goodfellow's Deep Learning

  • $\begingroup$ Neither density is differentiable at the cusp point ($0$ for the first, $\mu$ for the second). You can see the sharpness from a plot. Why this is useful in deep learning, I have no idea. I can't really help you there. But also, I take issue with the author's use of the word "mass." $\endgroup$ – Taylor Apr 26 '17 at 3:57
  • $\begingroup$ @Taylor "mass" is standard terminology in probability. $\endgroup$ – nth Apr 26 '17 at 4:38
  • $\begingroup$ @Taylor I think "mass" is a typo. The correct one should be "density" because Laplace distribution is a continuous probability distribution. $\endgroup$ – apepkuss Sep 11 '17 at 15:48
  • 1
    $\begingroup$ cf the relationship between lasso and pinning some coefficient estimates at exactly 0. $\endgroup$ – Sycorax Sep 11 '17 at 15:52
  • 1
    $\begingroup$ In what context is the distribution used? $\endgroup$ – Miguel Oct 30 '17 at 17:47

These two distribution have a connection with deep learning via regularisation. In deep learning we are often concerned with regularising the parameters of a neural network because neural networks tend to overfit and we want to improve ability of the model to generalise to new data.

From a Bayesian perspective, fitting a regularised model can be interpreted as computing the maximum a posteriori (MAP) estimate given a specific prior distribution over the weights $w_i$. In particular,

  • the $L^2$ (a.k.a. weight decay) norm corresponds to a Gaussian prior on the weights $w$, and
  • the $L^1$ norm corresponds to an isotropic Laplace prior over the weights $w$.

The $L^1$ norm (a.k.a. the Laplace prior on weights) by virtue of it's sharpness encourages sparsity (many zeros) in $w$ for reasons explained here: Why L1 norm for sparse models . This type of regularisation can be quite desirable. The connection between the Laplacian distribution and the $L^1$ norm is explained in more detail here: Why is Lasso penalty equivalent to the double exponential (Laplace) prior?

Most of what I have mentioned here is discussed in more detail in the same "Deep Learning" book in section 5.6.1 and section 7.1.2.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.