# Rolling Average vs Gradient Descent with Softmax & Cross Entropy

## Rolling Average vs Gradient Descent with Softmax & Cross Entropy

Edited by author.
Last edit: 06:49, 27 July 2021

If each Guess Factor bin is considered as an output unit before Softmax (logit), and loss is Cross Entropy, then the gradient of each logit is then:

qi - 1, if bin is hit
qi, otherwise

Where qi is the output of the ith unit after Softmax (estimated probability)

If gradients are not applied on logits as normal, but instead applied on qi itself, then:

qi := qi - η * (qi - 1) = (1 - η) * qi + η * 1, if bin i hit
qi := qi - η * qi = (1 - η) * qi + η * 0, otherwise

Which is essentially rolling average, where η (learning rate) equals to the α (decay rate) in exponential moving average.

Anyway this analog isn't how rolling average works, as logits don't equal to qi at all. But what if we replace rolling average with gradient descent? I suppose it could learn even faster, as the outputs farther from real value get higher decay rate...

Xor (talk)05:49, 27 July 2021

Then one step further, you don't use VCS any more, instead add the logits of velocity bins, accel bins and distance bins, etc., all together. This structure is essentially estimating the probability as a multiplication of probability when e.g. velocity is high and distance is close.

If the movement profile relating to velocity, distance, etc. is independent, this approach will be mostly the same as traditional segmented VCS, with more data points.

Note that this approach is essentially a neural network without hidden units, or multiclass logistic regression.

Xor (talk)06:15, 27 July 2021