Questions tagged [sampling]

Sampling is a process used in statistical analysis in which a predetermined number of observations are taken from a larger population. You can use this tag for asking questions related to sampling from a population

You can read more about sampling here

4 questions

votes

0 answers

Minimum sampling for maximising the prediction accuracy

Suppose that I'm training a machine learning model to predict people's age by a picture of their faces. Lets say that I have a dataset of people from 1 year olds to 100 year olds. But I want to choose just 9 (arbitrary) ages out of this 100 age…

bayesian-optimization thompson-sampling sampling

asked Aug 22 '22 at 13:02

noone

vote

1 answer

Is the re-parameterization trick necessary in the policy gradient method?

If we want to learn a stochastic policy with the policy gradient method, we have to sample from the distribution to get an action. Wouldn't this lead to the same issue that variational autoencoders face without the reparameterization trick, where…

reinforcement-learning backpropagation policy-gradients sampling reparameterization-trick

asked Apr 04 '23 at 12:45

Sam

vote

1 answer

Why is ancestral sampling used in autoregressive models?

I have been reading about autoregressive models. Based on what I've read, it seems to me that all autoregressive models use ancestral sampling. For instance, this paper says the following in Abstract: We introduce a deep, generative autoencoder…

machine-learning sampling

asked Jun 24 '21 at 11:29

The Pointer

votes

1 answer

Is there a way to further fine tune image alignment homography after using Spatial Transformer Networks?

I'm using a Spatial Transformer Networks (STN) to align an image by optimization using L1 loss between prediction and target, they works great for large mismatch, but not so much for small misalignment. For example, in this image below you could see…

convolutional-neural-networks sampling

asked Apr 22 '22 at 08:52

Ryan