This repository was archived by the owner on Nov 7, 2024. It is now read-only.

Initialization of orthogonal tensors with respect to a pivot #931

Open

pragyasrivastava0805 wants to merge 6 commits into google:master

from pragyasrivastava0805:enhance-tensornetwork

Open

Initialization of orthogonal tensors with respect to a pivot #931

pragyasrivastava0805 wants to merge 6 commits into google:master from pragyasrivastava0805:enhance-tensornetwork

Conversation

@pragyasrivastava0805

Copy link

@pragyasrivastava0805 pragyasrivastava0805 commented Aug 25, 2021

created a new method in tensornetwork/linalg/initialization.py for initializing a random tensor with entries distributed according to normal distribution and performing QR Decomposition on it and returning the tensor Q so that when a tensor is contracted about a given pivot index,the result is orthogonal

@pragyasrivastava0805


 heading:changed

07f4035

@google-cla

Copy link

google-cla bot commented Aug 25, 2021

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

📝 Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here with @googlebot I signed it! and we'll verify it.

What to do if you already signed the CLA

Individual signers

It's possible we don't have your GitHub username or you're using a different email address on your commit. Check your existing CLA data and verify that your email is set on your git commits.

Corporate signers

Your company has a Point of Contact who decides which employees are authorized to participate. Ask your POC to be added to the group of authorized contributors. If you don't know who your Point of Contact is, direct the Google project maintainer to go/cla#troubleshoot (Public version).
The email used to register you as an authorized contributor must be the email used for the Git commit. Check your existing CLA data and verify that your email is set on your git commits.
The email used to register you as an authorized contributor must also be attached to your GitHub account.

i️ Googlers: Go here for more info.

@google-cla google-cla bot added the cla: no label

Aug 25, 2021

@pragyasrivastava0805 pragyasrivastava0805 mentioned this pull request

Aug 25, 2021

orthogonalization for tensors #800

Open

@pragyasrivastava0805

Copy link

Author

pragyasrivastava0805 commented Aug 26, 2021

@googlebot I have signed

@google-cla google-cla bot added cla: yes and removed cla: no labels

Aug 26, 2021

pragyasrivastava0805 added 4 commits

September 1, 2021 18:03

@pragyasrivastava0805


 Amends Added

a54b55f

@pragyasrivastava0805


 Unit-Tests Added

cbb6e1d

@pragyasrivastava0805


 Changes

29c730f

@pragyasrivastava0805


 Final

55e5d15

mganahl

mganahl reviewed

Sep 6, 2021

View reviewed changes

tensornetwork/backends/abstract_backend.py Show resolved Hide resolved

@pragyasrivastava0805


 Breaked the line

c08cd60

mganahl

mganahl suggested changes

Sep 7, 2021

View reviewed changes

Copy link

Contributor

@mganahl mganahl left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks for the PR! Sorry for the delay, I left some comments for you to fix!

tensornetwork/backends/numpy/numpy_backend.py

if ((np.dtype(dtype) is np.dtype(np.complex128)) or

(np.dtype(dtype) is np.dtype(np.complex64))):

q,r= decompositions.qr(np,np.random.randn(

*shape).astype(dtype) + 1j * np.random.randn(*shape).astype(dtype),pivot_axis,non_negative_diagonal)

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

there is an else clause missing, otherwise line 804 gets overwritten

tensornetwork/linalg/tests/initialization_test.py

for dtype in dtypes[backend]["rand"]:

tnI = tensornetwork.initialize_orthogonal_tensor_wrt_pivot(

shape,

dtype=dtype,pivot_axis,

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

that line should throw a syntax error because your passing an argument between named arguments

tensornetwork/linalg/tests/initialization_test.py

shape,

dtype=dtype,pivot_axis,

seed=seed,

backend=backend,non_negative_diagonal)

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same here

tensornetwork/linalg/tests/initialization_test.py

dtype=dtype,pivot_axis,

seed=seed,

backend=backend,non_negative_diagonal)

npI = backend_obj.initialize_orthogonal_tensor_wrt_pivot(shape, dtype=dtype, pivot_axis, seed=seed,non_negative_diagonal)

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove the function from the backend

tensornetwork/linalg/tests/initialization_test.py

def test_initialize_orthogonal_tensor_wrt_pivot(backend):

shape=(5, 10, 3, 2)

pivot_axis=1

seed = int(time.time())

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

pls use deterministic seed initialization

tensornetwork/linalg/initialization.py

return the_tensor

def initialize_orthogonal_tensor_wrt_pivot(shape=Sequence[int],dtype:Optional[Type[np.number]]=None,pivot_axis:int=-1,seed=Optional[int]=None,backend: Optional[Union[Text, AbstractBackend]] = None,non_negative_diagonal:bool=False) ->Tensor:

the_tensor=initialize_tensor("randn",shape,backend=backend,seed=seed,dtype=dtype)

q,r=linalg.qr(the_tensor,pivot_axis,non_negative_diagonal)

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

us _ instead of r (unused variable)

tensornetwork/linalg/initialization.py

the_tensor = initialize_tensor("random_uniform", shape, backend=backend,

seed=seed, boundaries=boundaries, dtype=dtype)

return the_tensor

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm wondering if we could find a less clunky name. Some possibilities that come to my mind are random_orthogonal or random_isometry @alewis?

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pls add a docstring that explains what the function is doing, what the arguments are, and what the returned values are.

tensornetwork/backends/abstract_backend.py

@@ -1044,3 +1044,6 @@ def eps(self, dtype: Type[np.number]) -> float:

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why did you add this function to the backend? I don't think we need it here

tensornetwork/backends/numpy/numpy_backend.py

float: Machine epsilon.

"""

return np.finfo(dtype).eps

def initialize_orthogonal_tensor_wrt_pivot(self,shape=Sequence[int],dtype:Optional[Type[np.number]]=None,pivot_axis:int=-1,seed=Optional[int]=None,backend: Optional[Union[Text, AbstractBackend]] = None,non_negative_diagonal: bool = False):->Tensor

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think we need this function

tensornetwork/linalg/tests/initialization_test.py

seed=seed,

backend=backend,non_negative_diagonal)

npI = backend_obj.initialize_orthogonal_tensor_wrt_pivot(shape, dtype=dtype, pivot_axis, seed=seed,non_negative_diagonal)

np.testing.assert_allclose(tnI.array, npI)

Copy link

Contributor

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

pls replace with a test that checks if the initialized tensor has the desired properties

Labels

cla: yes

2 participants

@pragyasrivastava0805 @mganahl

Initialization of orthogonal tensors with respect to a pivot #931

Are you sure you want to change the base?

Initialization of orthogonal tensors with respect to a pivot #931

Uh oh!

Conversation

@pragyasrivastava0805 pragyasrivastava0805 commented Aug 25, 2021

Uh oh!

google-cla bot commented Aug 25, 2021

What to do if you already signed the CLA

Individual signers

Corporate signers

Uh oh!

pragyasrivastava0805 commented Aug 26, 2021

Uh oh!

Uh oh!

@mganahl mganahl left a comment

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

@mganahl mganahl Sep 7, 2021

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants