Regret gradients in DFL are the tangent-space projection of prediction error scaled by curvature, enabling efficient direct computation without differentiating through solvers.
Dif- ferentiating through a cone program
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Two algorithms derived from Blahut-Arimoto optimality conditions recover the true channel parameters and optimal input distribution from output observations, while naive maximum-likelihood estimation fails.
citing papers explorer
-
Decision-Focused Learning via Tangent-Space Projection of Prediction Error
Regret gradients in DFL are the tangent-space projection of prediction error scaled by curvature, enabling efficient direct computation without differentiating through solvers.
-
Parameter Estimation of Mutual Information Maximized Channels
Two algorithms derived from Blahut-Arimoto optimality conditions recover the true channel parameters and optimal input distribution from output observations, while naive maximum-likelihood estimation fails.