[HN Gopher] The physics principle of diffusion inspired modern A... ___________________________________________________________________ The physics principle of diffusion inspired modern AI art Author : howsilly Score : 25 points Date : 2023-01-05 20:40 UTC (2 hours ago) (HTM) web link (www.quantamagazine.org) (TXT) w3m dump (www.quantamagazine.org) | manmal wrote: | Can anybody explain what is meant by ,,gradient" in this context? | Is this a way of speeding up the search for a desirable | improvement of a pixel (or cluster) in each pass? | PartiallyTyped wrote: | They refer to score models, where the score is the density of | the input. | | Imagine you have a huuuuge landscape, with peaks and valleys. | This landscape defines the density of the distribution. Now, | imagine that you have a bunch of samples drawn from the | distribution, this is the dataset. | | Sampling an image is a mixture of dirac delta functions (or a | mixture of Gaussian with variance approaching zero). | | We can increase the variance to smoothen the landscape. This | sort of builds an empirical estimate of the true landscape. | | The height of this landscape is "the score". | | It turns out that we can actually compute an approximation of | the gradient of the score. | | The gradient of the score always points towards where the score | (aka density) will increase, and you essentially apply | gradients to "walk" towards a high density region. | | This idea is actually very similar to using gradients to create | poisoned inputs that are falsely predicted. | | I am being a bit handwavey here, we don't _just_ increase the | variance, but this is a decent enough approximation of what's | happening and what the gradient refers to in this case. | | For all intents and purposes, you can think of the gradient as | a vector pointing towards the direction that the density of the | dataset increases. | wildpeaks wrote: | I think they refer to Gradient Descent: | https://en.wikipedia.org/wiki/Gradient_descent | hypertele-Xii wrote: | Is this a submarine ad for Coca-Cola? ___________________________________________________________________ (page generated 2023-01-05 23:00 UTC)