Skip to content

v1.2.0 release

Latest
Compare
Choose a tag to compare
@Buyun-Liang Buyun-Liang released this 27 Jul 01:21
· 10 commits to main since this release

Version: 1.2.0 --- 2022-07-26

Description: major fixes and improvements on LBFGS.

Fixed

  • Reducing memory usage for LBFGS. Now PyGRANSO can solve problem with ~15k parameters by using 14 GB memory.
  • Update example: ortho RNN with max folding and orthonormal initialization.
  • Allow high precision for QP solver.
  • Allow part of optimization variables not showing up in objective (see SVM example).
  • Fixed Code 12: terminated with steering failure.
  • Fixed stationary failure: try different stationarity calculation, or set stationarity measure to be inf if encounter numerical issue

Added

  • Reorganize and add examples: perceptual/lp norm attack on ImageNet images. trace optimization with orthogonal constraints; unconstrained deep learning with LeNet5; logistic regression.