User Sam

7 votes

1 answer

776 views

Subscript notation in expectations (variational autoencoder)

asked Mar 14, 2021 at 17:09

4 votes

1 answer

674 views

How does a gradient pass through argmax in classification?

asked Feb 25, 2023 at 7:34

3 votes

2 answers

163 views

Asymptotic normality in central limit theorem

asked Apr 18, 2023 at 6:37

3 votes

1 answer

205 views

Decoder of variational autoecnoder

asked Mar 12, 2021 at 14:39

2 votes

1 answer

45 views

The role of variance of the distribution plays in Bayesian inference

asked Sep 13, 2023 at 0:06

2 votes

1 answer

71 views

Is it possible to just use one policy in a self-play setting?

asked Feb 10, 2020 at 4:48

2 votes

1 answer

271 views

Gaussian process on hyperparameter tuning

asked Oct 27, 2021 at 5:49

1 vote

0 answers

159 views

which non parametric test to use for anomalous NN model outputs

asked Mar 1, 2022 at 12:55

1 vote

0 answers

312 views

Why is KL divergence used as a measure of closeness in variational inference?

asked Mar 25, 2022 at 1:50

1 vote

0 answers

47 views

Gaussian process for hyperparameter search

asked Feb 9, 2021 at 3:11

1 vote

0 answers

14 views

Problem with high learning rate in model training

asked Apr 27 at 15:00

1 vote

0 answers

48 views

Why are LLMs generative models [duplicate]

asked Sep 1, 2023 at 17:30

1 vote

1 answer

537 views

Regarding the objective of PPO training in instructGPT

asked Feb 27, 2023 at 10:10

0 votes

1 answer

742 views

Are embedding in GPT models trainable model parameters? [closed]

asked Sep 4, 2023 at 21:52

0 votes

0 answers

26 views

What is the value of the probability mass of a rational random variable talking the value of any rational number in a given range [duplicate]

asked Oct 4, 2023 at 20:49

0 votes

0 answers

14 views

On showing indepdedence of a collider in graphical model

asked Mar 7 at 9:55

0 votes

0 answers

39 views

Why Bayesian optimization in its simplest form only works for low dimensional optimization? [duplicate]

asked Oct 27, 2021 at 5:33

0 votes

0 answers

25 views

Objective of maximal margin classifier with quadratic decision boundary

asked Aug 25, 2022 at 17:06

0 votes

0 answers

47 views

Distribution shift, model shift and training error

asked Feb 3, 2023 at 15:53

Stack Exchange Network

19 Questions

Subscript notation in expectations (variational autoencoder)

How does a gradient pass through argmax in classification?

Asymptotic normality in central limit theorem

Decoder of variational autoecnoder

The role of variance of the distribution plays in Bayesian inference

Is it possible to just use one policy in a self-play setting?

Gaussian process on hyperparameter tuning

which non parametric test to use for anomalous NN model outputs

Why is KL divergence used as a measure of closeness in variational inference?

Gaussian process for hyperparameter search

Problem with high learning rate in model training

Why are LLMs generative models [duplicate]

Regarding the objective of PPO training in instructGPT

Are embedding in GPT models trainable model parameters? [closed]

What is the value of the probability mass of a rational random variable talking the value of any rational number in a given range [duplicate]

On showing indepdedence of a collider in graphical model

Why Bayesian optimization in its simplest form only works for low dimensional optimization? [duplicate]

Objective of maximal margin classifier with quadratic decision boundary

Distribution shift, model shift and training error