Milestone 2 second tt ode working version backward gradient descent #18
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…eter scale (Tensor of shape ()) of distribution Normal(loc: 0.0, scale: 0.0) to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values: 0.0
…eter scale (Tensor of shape ()) of distribution Normal(loc: 0.0, scale: 0.0) to satisfy the constraint GreaterThan(lower_bound=0.0), but found invalid values: 0.0
…tructured experiment class
…eavily depended on h and not stable when changing it, needs more experimentation and next step should be rk45
…et, not tested yet
…s - too slow - just to isolate stucking issue
…is exploding gradient problem led to underflow exception during the ode solve forward phase
…ckward schema through the ode trajectory . Forward is torch-rk45 integrate and backward is builtin pytorch backrop
…hts are updated , W and P are fixed
…not updated via GD
…my anode extension , updated by Gradient descent and the builtin backward mechanism of pytorch
…egrate for forward pass, and backward is implemented implicited via pytorch backward gradient descent (Adam)
Experiments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is the second working version (Milestone 2)
Forward pass is using TT structure from dlra ( written by david) . Backward is via pytorch gradient descent