-
Notifications
You must be signed in to change notification settings - Fork 1.9k
VW Reductions Workflows
This graph does not display the first possible reduction (which is not a part of the CB workflow), audit_regressor. audit_regressor's valid downstream reductions include any reduction that takes in a single-line example (nodes with incoming black lines).Additionally, this graph only displays valid reduction chains that will not result in program exceptions.
The valid entry nodes have not been marked as they haven't yet been mapped out.
Most reductions will attempt to force data to flow into required reductions; for all example multi-line examples must pass through the csldf reduction. However, these checks are not comprehensive, and several known gaps exist in their coverage.
The following reductions do not perform any validity checks
- audit_regressor
- expreplay_c
- warm_cb
Additionally, Search can bypass the csldf reduction if the cs_active option was provided.
Search -> explore_eval
and Search -> cbifyldf
workflows are technically allowed, but are meaningless.
- Home
- First Steps
- Input
- Command line arguments
- Model saving and loading
- Controlling VW's output
- Audit
- Algorithm details
- Awesome Vowpal Wabbit
- Learning algorithm
- Learning to Search subsystem
- Loss functions
- What is a learner?
- Docker image
- Model merging
- Evaluation of exploration algorithms
- Reductions
- Contextual Bandit algorithms
- Contextual Bandit Exploration with SquareCB
- Contextual Bandit Zeroth Order Optimization
- Conditional Contextual Bandit
- Slates
- CATS, CATS-pdf for Continuous Actions
- Automl
- Epsilon Decay
- Warm starting contextual bandits
- Efficient Second Order Online Learning
- Latent Dirichlet Allocation
- VW Reductions Workflows
- Interaction Grounded Learning
- CB with Large Action Spaces
- CB with Graph Feedback
- FreeGrad
- Marginal
- Active Learning
- Eigen Memory Trees (EMT)
- Element-wise interaction
- Bindings
-
Examples
- Logged Contextual Bandit example
- One Against All (oaa) multi class example
- Weighted All Pairs (wap) multi class example
- Cost Sensitive One Against All (csoaa) multi class example
- Multiclass classification
- Error Correcting Tournament (ect) multi class example
- Malicious URL example
- Daemon example
- Matrix factorization example
- Rcv1 example
- Truncated gradient descent example
- Scripts
- Implement your own joint prediction model
- Predicting probabilities
- murmur2 vs murmur3
- Weight vector
- Matching Label and Prediction Types Between Reductions
- Zhen's Presentation Slides on enhancements to vw
- EZExample Archive
- Design Documents
- Contribute: