feat(policies): add a permutation-equivariant deep-set policy - #14
Open
ZacKienzle2 wants to merge 1 commit into
Open
feat(policies): add a permutation-equivariant deep-set policy#14ZacKienzle2 wants to merge 1 commit into
ZacKienzle2 wants to merge 1 commit into
Conversation
Hedge a multi-asset book with a shared per-asset encoder, an order-invariant mean-pooled summary, and a per-asset head, so the map is equivariant under asset relabelling and the parameter count is independent of the asset count. Pairs with MultiAssetFeatures. Tests pin the equivariance, the asset-count-independent parameter count, the output shape, input validation, and that the policy trains a correlated two-asset hedge that beats not hedging.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
A permutation-equivariant multi-asset hedging policy in the Deep Sets family (roadmap Horizon 4, policy frontier; pure machine-learning focus).
MultiAssetFeatures. Exported fromdeephedginganddeephedging.policies.Tests
Permutation equivariance, asset-count-independent parameter count, output shape, input validation, and a training-integration test showing the policy learns a correlated two-asset hedge that beats not hedging by more than forty percent of tail risk.
Gates
ruff, ruff format, pyright (strict, 0 errors), fast suite green (185 passed), slow training test passes.