A certified gradient-based method for contact-rich manipulation that quantifies smoothing-induced errors via set-valued discrepancies and incorporates them into analytical reachable sets for robust affine feedback policies.
Differentiating through a cone program
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
An alternative complementarity formulation for primal-dual interior-point methods keeps linear systems spectrally bounded near the solution, enabling stable single-precision solves and differentiation for bilevel and end-to-end learning.
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.
PEAR computes regret gradients via tangent-space projection of prediction error, delivering top decision quality and efficiency on LP and QP tasks without solver differentiation.
RAYEN enforces hard convex constraints (linear, quadratic, SOC, LMI) on neural networks with negligible overhead while guaranteeing satisfaction at all times.
citing papers explorer
-
Certified Gradient-Based Contact-Rich Manipulation via Smoothing-Error Reachable Tubes
A certified gradient-based method for contact-rich manipulation that quantifies smoothing-induced errors via set-valued discrepancies and incorporates them into analytical reachable sets for robust affine feedback policies.
-
A Differentiable Interior-Point Method in Single Precision
An alternative complementarity formulation for primal-dual interior-point methods keeps linear systems spectrally bounded near the solution, enabling stable single-precision solves and differentiation for bilevel and end-to-end learning.
-
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.
-
Decision-Focused Learning via Tangent-Space Projection of Prediction Error
PEAR computes regret gradients via tangent-space projection of prediction error, delivering top decision quality and efficiency on LP and QP tasks without solver differentiation.
-
RAYEN: Imposition of Hard Convex Constraints on Neural Networks
RAYEN enforces hard convex constraints (linear, quadratic, SOC, LMI) on neural networks with negligible overhead while guaranteeing satisfaction at all times.