Why do you scale your MSE by 1/(x_centred**2).sum(dim=-1, keepdim=True).sqrt() ? In particular, I’m confused about why you have the square root. Shouldn’t it just be 1/(x_centred**2).sum(dim=-1, keepdim=True)?
1/(x_centred**2).sum(dim=-1, keepdim=True).sqrt()
1/(x_centred**2).sum(dim=-1, keepdim=True)
Why do you scale your MSE by
1/(x_centred**2).sum(dim=-1, keepdim=True).sqrt()? In particular, I’m confused about why you have the square root. Shouldn’t it just be1/(x_centred**2).sum(dim=-1, keepdim=True)?