You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In this new version of TensorLy, the whole team has been working hard to bring you lots of improvements, from new decompositions to new functions, faster code and better documentation.
Major improvements and new features
New decompositions
We added some great new tensor decompositions, including
A new CP decomposition that supports various constraints on each mode, including monotony, non-negativity, l1/l2 regularization, smoothness, sparsity, etc!
[ Constrained parafac Constrained parafac #284, thanks to @caglayantuna and @cohenjer ]
Brand new features
We added a brand new tensordot that supports batching!
[ Adding a new Batched Tensor Dot + API simplification #309 ]
Added a convenient function to compute the gradient of the difference norm between a CP and dense tensor, #294, thanks to @aarmey
Backend refactoring
In an effort to make the TensorLy backend even more flexible and fast, we refactored the main backend as well as the tensor algebra backend. We make lots of small quality of life improvement in the process! In particular, reconstructing a tt-matrix is a lot more efficient now.
[ Backend refactoring : use a BackendManager class and use it directly as tensorly.backend's Module class #330 ]
Enhancements
Improvements to Parafac2 (convergence criteria, etc) #267, thanks to @MarieRoald
HALS convergence FIX TODO, @MarieRoald and @IsabellLehmann, #271
Ensuring consistency between the object oriented API and the functional one thanks to @yngvem, #268
Added lstsq to backend, #305, thanks to @merajhashemi
Fix documentation for case insensitive clashes between the function and class: #219
Added random-seed for TT-cross, #304 thanks to @yngvem
Fix svd sign indeterminacy #216, thanks to @merajhashemi
Rewrote vonneumann_entropy to handle multidimensional tensors. #270, thanks to @taylorpatti
Adding check for all modes fixed case and if true then to just return the initialization #325, thanks to @ParvaH
We now provide a prod function that works like math.prod for users using Python < 3.8, in tensorly.utils.prod
New backend functions
All backend now support matmul, tensor dot (#306), as well as sin, cos, flip, argsort, count_nonzero, cumsum, any, lstsq and trace.
Bug Fixes
Fixed NN-Tucker hals sparsity coefficient issue, thanks to @caglayantuna#295
Fix svd for pytorch < 1.8 #312 thanks to @merajhashemi
Fix dot and matmul in PyTorch and TF #313 thanks to @merajhashemi
Fix tl.partial_unfold #315, thanks to @merajhashemi
Fixed behaviour of diag for TensorFlow backend.
Fix tl.partial_svd : now explicitly check for NaN values, #318 thanks to @merajhashemi
fix diag function for tensorflow and pytorch backends #321, thanks to @caglayantuna
Fix singular vectors to be orthonormal #320 thanks to @merajhashemi
fix active set and hals tests #323 thanks to @caglayantuna
Add test for matmul #322 thanks to @merajhashemi
Sparse backend usage fix by @caglayantuna in #280
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
TensorLy 0.7.0 is out!
In this new version of TensorLy, the whole team has been working hard to bring you lots of improvements, from new decompositions to new functions, faster code and better documentation.
Major improvements and new features
New decompositions
We added some great new tensor decompositions, including
[ CMTF-ALS CMTF-ALS #293 thanks to @IsabellLehmann and @aarmey ]
[ Tensor Ring implementation Tensor Ring implementation #229 thanks to @merajhashemi ]
[ NN-HALS Tucker @caglayantuna @cohenjer Non-negative tucker with HALS #254 ]
[ Constrained parafac Constrained parafac #284, thanks to @caglayantuna and @cohenjer ]
Brand new features
We added a brand new
tensordot
that supports batching![ Adding a new Batched Tensor Dot + API simplification #309 ]
Normalization for Tucker factors, #283 thanks to @caglayantuna and @cohenjer!
Added a convenient function to compute the gradient of the difference norm between a CP and dense tensor, #294, thanks to @aarmey
Backend refactoring
In an effort to make the TensorLy backend even more flexible and fast, we refactored the main backend as well as the tensor algebra backend. We make lots of small quality of life improvement in the process! In particular, reconstructing a tt-matrix is a lot more efficient now.
[ Backend refactoring : use a BackendManager class and use it directly as tensorly.backend's Module class #330 ]
Enhancements
Improvements to Parafac2 (convergence criteria, etc) #267, thanks to @MarieRoald
HALS convergence FIX TODO, @MarieRoald and @IsabellLehmann, #271
Ensuring consistency between the object oriented API and the functional one thanks to @yngvem, #268
Added lstsq to backend, #305, thanks to @merajhashemi
Fix documentation for case insensitive clashes between the function and class: #219
Added random-seed for TT-cross, #304 thanks to @yngvem
Fix svd sign indeterminacy #216, thanks to @merajhashemi
Rewrote vonneumann_entropy to handle multidimensional tensors. #270, thanks to @taylorpatti
Adding check for all modes fixed case and if true then to just return the initialization #325, thanks to @ParvaH
We now provide a
prod
function that works like math.prod for users using Python < 3.8, intensorly.utils.prod
New backend functions
All backend now support
matmul
,tensor dot
(#306), as well assin
,cos
,flip
,argsort
,count_nonzero
,cumsum
,any
,lstsq
andtrace
.Bug Fixes
Fixed NN-Tucker hals sparsity coefficient issue, thanks to @caglayantuna #295
Fix svd for pytorch < 1.8 #312 thanks to @merajhashemi
Fix dot and matmul in PyTorch and TF #313 thanks to @merajhashemi
Fix tl.partial_unfold #315, thanks to @merajhashemi
Fixed behaviour of diag for TensorFlow backend.
Fix tl.partial_svd : now explicitly check for NaN values, #318 thanks to @merajhashemi
fix diag function for tensorflow and pytorch backends #321, thanks to @caglayantuna
Fix singular vectors to be orthonormal #320 thanks to @merajhashemi
fix active set and hals tests #323 thanks to @caglayantuna
Add test for matmul #322 thanks to @merajhashemi
Sparse backend usage fix by @caglayantuna in #280
This discussion was created from the release TensorLy Release 0.7.0.
Beta Was this translation helpful? Give feedback.
All reactions