Spaces:

DineshAI
/

G4ve69pimc

Running

App Files Files Community

G4ve69pimc / pages

30.6 kB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

DineshAI's picture

Add Theorem 4 noise-direction audit

2c9c6fc verified 13 days ago

claim-1-scaling
Update logbook: Repro - Optimal Regularization for Performative Learning (G4ve69pimc) 17 days ago
claim-2-mitigation
Update logbook: Repro - Optimal Regularization for Performative Learning (G4ve69pimc) 17 days ago
claim-2-overparam-deterministic-equivalent
Claim [2]: reproduce Theorem 3 deterministic equivalent in the over-parameterized regime (p>n) -- concentration, dimension-free self-averaging, and the parameter-free self-consistent equation matched to <0.07%; full source shown 13 days ago
claim-4-noise-direction
Add Theorem 4 noise-direction audit 13 days ago
claim-performative-reg
Reproduce performative regularization: Thm 1 risk min at lambda*=b̄, sim opt lambda tracks b̄ (slope 0.93), performativity-aware lambda cuts risk 19x 13 days ago
conclusion
Update logbook: Repro - Optimal Regularization for Performative Learning (G4ve69pimc) 17 days ago
methods-environment
Update logbook: Repro - Optimal Regularization for Performative Learning (G4ve69pimc) 17 days ago
negative-controls
Update logbook: Repro - Optimal Regularization for Performative Learning (G4ve69pimc) 17 days ago
index.md

1.15 kB
Update logbook: Repro - Optimal Regularization for Performative Learning (G4ve69pimc) 17 days ago