Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
Vowpal Wabbit 9 is the first major release in over 6 years! There are a number of usability improvements, new reductions, bug fixes and internal improvements here. The Python package has undergone a bit of a modernization with a more understandable module structure, naming and types. Most changes should be non breaking for standard use cases. See here for the Python migration guide.
This release includes python API improvements, --cubic :::
and --interactions [:]*
speedup, deprecations, logging line limiting, bug fixes and more
This release includes no code changes but fixes the Python source distribution, and adds support for Python 3.9 binary wheels on MacOS and Windows.
Since this only affects Python, only the PyPi release channel will be updated.
All changes:
This release includes quadratic interaction speed improvements, ARM support, logging updates and more.
This release includes major features such as continuous actions, square CB, probabilistic label tree, slates, CB distributionally robust optimization, CB ADF RND, Python wheels and many bug fixes.
find_package(VowpalWabbit REQUIRED)
add_executable(my_exe main.cpp)
target_link_libraries(my_exe PRIVATE VowpalWabbit::vw)
We are at work overhauling and modernizing VW, some of the relevant changes on that front are below:
--version
now includes commit id if available at build time (#1951)