Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

stochastic optimisation (noisy gradients due to data-subsampling) for ALL models #14

Open
thangbui opened this issue Mar 28, 2017 · 0 comments
Open

stochastic optimisation (noisy gradients due to data-subsampling) for ALL models #14

thangbui opened this issue Mar 28, 2017 · 0 comments
Labels
todo

Comments

@thangbui
Copy link
Owner

Make sure that the gradients are correct and the variance becomes smaller when the batch size gets larger.

For each model, write an example use case.
@thangbui thangbui added the todo label Mar 28, 2017
thangbui added a commit that referenced this issue Mar 28, 2017
@thangbui
#14: AEP GPR/C done, see updated examples
6fee08c
thangbui added a commit that referenced this issue Mar 28, 2017
@thangbui
#14: added DGPR/C example, not sure why Adam works much worse than LB…
1acaf84 
…FGS, to investigate
thangbui added a commit that referenced this issue Mar 29, 2017
@thangbui
#14 SGPR/C + SDGPR/C AEP done
f4ca58e
thangbui added a commit that referenced this issue Mar 29, 2017
@thangbui
#14 added some test code for GPLVM AEP
edf8994
thangbui added a commit that referenced this issue Apr 14, 2017
@thangbui
stochastic gradients for AEP GPSSMs #14, with moment matching and sim…
c40102f 
…ple monte carlo #6, noise due to data subsampling dominates noise due to sample-based log tilted computation
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
todo
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@thangbui