what 'computer scientist' uses wordpress for their blog. Though, I don't have a blog, so...
If you do get one at some time, and find you enjoy Wordpress, I warmly recommend WP Engine.
The relativistic discriminator: a key element missing from standard GAN
11–20 of 33 posts
Re: The relativistic discriminator: a key element missing from standard GAN
#12This is just confusing misuse of the word "relativistic", being based as it is on _relative_ probability and having little to do with philosophical relativism and nothing to do with physics relativity.
I almost doubt there exists a single noun in the English language that is not yet the name of some git package, platform, programming language, or text-editor.
Re: The relativistic discriminator: a key element missing from standard GAN
#13This is just confusing misuse of the word "relativistic", being based as it is on _relative_ probability and having little to do with philosophical relativism and nothing to do with physics relativity.
I agree -- though I'm not sure how to make the right name for this technique. Maybe "relative-probability GAN" is the best. I also wondered before clicking what a relativistic GAN would be: maybe as the activity of a neuron becomes larger and larger, it becomes harder and harder for it to continue? But that's already true of sigmoidal activation functions.
I was excited to see how the fabric of space and time was being used to generate adversarial examples. =)
Re: The relativistic discriminator: a key element missing from standard GAN
#14This is just confusing misuse of the word "relativistic", being based as it is on _relative_ probability and having little to do with philosophical relativism and nothing to do with physics relativity.
"Relative probability" is only correct for standard GAN, not for other GANs which don't estimate a probability.
My first name was "Critic's difference" since it's literally C(x_r)-C(x_f) so its the difference in critics, but it felt really unclear, it doesn't give the reader any sense of what it is about. Relativism/Relativistic is better since it's to say that it really doesn't matter if the data looks real, what matters if how realistic is real data relative to fake data (and vice versa). The frame of reference is important here.
Re: The relativistic discriminator: a key element missing from standard GAN
#15This is just confusing misuse of the word "relativistic", being based as it is on _relative_ probability and having little to do with philosophical relativism and nothing to do with physics relativity.
It is not quite relative but regularised by another GAN...
Re: The relativistic discriminator: a key element missing from standard GAN
#16This is just confusing misuse of the word "relativistic", being based as it is on _relative_ probability and having little to do with philosophical relativism and nothing to do with physics relativity.
Same... I was expecting a perspective on GANs inspired by differential geometry or something.
Re: The relativistic discriminator: a key element missing from standard GAN
#17This is just confusing misuse of the word "relativistic", being based as it is on _relative_ probability and having little to do with philosophical relativism and nothing to do with physics relativity.
"Relative probability" is only correct for standard GAN, not for other GANs which don't estimate a probability. My first name was "Critic's difference" since it's literally C(x_r)-C(x_f) so its the difference in critics, but it felt really unclear, it doesn't give the reader any sense of what it is about. Relativism/Relativistic is better since it's to say that it really doesn't matter if the data looks real, what ma…
It's not even probability in standard GAN is it? Since you are taking the difference before the sigmoid. It can't really be interpreted as probability until it the range is clamped. Critic's difference or Critical Difference would be a better term perhaps.
Re: The relativistic discriminator: a key element missing from standard GAN
#18what 'computer scientist' uses wordpress for their blog. Though, I don't have a blog, so...
I don't see any sense in attacking the credibility by the choice of the blogging infrastructure - the author wanted to convey a message, present his findings and he achieved that. This should be the only thing that counts.
I guess the best (even if in a totally opposite field) argument against opinionated choice of web-technologies would be the website of Berkshire Hathaway [1]. They invest in highly sophisticated companies but still use the website that always provided the service they demanded.
Re: The relativistic discriminator: a key element missing from standard GAN
#19what 'computer scientist' uses wordpress for their blog. Though, I don't have a blog, so...
Dan Luu doesn't even use a blog engine. https://danluu.com/
Re: The relativistic discriminator: a key element missing from standard GAN
#20Earlier quoted context omitted.
"Relative probability" is only correct for standard GAN, not for other GANs which don't estimate a probability. My first name was "Critic's difference" since it's literally C(x_r)-C(x_f) so its the difference in critics, but it felt really unclear, it doesn't give the reader any sense of what it is about. Relativism/Relativistic is better since it's to say that it really doesn't matter if the data looks real, what ma…
It's not even probability in standard GAN is it? Since you are taking the difference before the sigmoid. It can't really be interpreted as probability until it the range is clamped. Critic's difference or Critical Difference would be a better term perhaps.
It's logits or log odds or the logarithm of the odds, i.e. log(odds(p)) = log(p / (1 - p)): https://en.wikipedia.org/wiki/Logit
Since sigmoid(C(x_r)) = p(x_r is real) and C(x_f) = p(x_f is real), the sigmoid of the difference expresses some probability that that x_r looks more real than x_f or vice versa (depending on whether it is C(x_r) - C(x_f) or C(x_f) - C(x_r)). Not sure whether there is a probabilistic interpretation of the difference, but it looks so simple that there maybe is one. I couldn't find one in the paper.