Implicit Differentiation

Follow this topic Ask about this topic

Latest papers

10 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

dOPT: Differentiating Conic Optimization via Geometric Reduction
Sep 27, 2026Fengyu Yang, Connor W. Magoon, Tyler Watts +1Implicit Differentiation Differentiable Programming
Department of Mathematics University of North Carolina at Chapel Hill
Response Renormalization for Critical Deep Equilibrium Models
Aug 24, 2026Jose Luis Lima de Jesus SilvaImplicit Differentiation
Federal University of Bahia, Department of Geophysics Salvador, BA 40170-115, Brazil · Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA) Federal University of Bahia, Salvador, BA 40170-115, Brazil
Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation
Aug 9, 2026Lei Shu, Ying Jiang, Kui Wu +3Automatic Differentiation Differentiable Programming
Stanford University · University of California, Los Angeles · LightSpeed Studios, Tencent America +1
Amortising Trajectory Optimisation for Residual MPC via Implicit Contact Differentiation
Jul 27, 2026Daniel Layeghi, Thomas Corbères, Calum Arnott +4Trajectory Optimization Automatic Differentiation
School of Informatics, University of Edinburgh, Scotland.
Sharper Analysis of Single-Loop Methods for Bilevel Optimization
Jul 11, 2026Yubo Zhou, Jun Shu, Luo Luo +4Implicit Differentiation Optimization Convergence Analysis
School of Mathematics and Statistics, Xi’an Jiaotong University · School of Data Science, Fudan University · 3SGIT AI Lab, State Grid Corporation of China +1
Scalable Deep Unfolding of Conic Optimizers
Jun 11, 2026Alex Oshin, Rahul Vodeb Ghosh, Evangelos A. TheodorouSemidefinite Programming Implicit Differentiation
Georgia Institute of Technology
Neural Control: Adjoint Learning Through Equilibrium Constraints
May 5, 2026Dezhong Tong, Jiawen Wang, Hengyi Zhou +3Robotic Control Dynamical Systems
The Robotics Department, University of Michigan, Ann Arbor, US · The Department of Mechanical and Aerospace Engineering, University of California, Los Angeles, US
A Deep Equilibrium Network for Hyperspectral Unmixing
Apr 13, 2026Chentong Wang, Jincheng Gao, Fei Zhu +1Implicit Differentiation Hyperspectral Unmixing
Center for Applied Mathematics, KL-AAGDM, Tianjin University, Tianjin 300072, China · School of Artiﬁcial Intelligence, Northwestern Polytechnical University, Xi’an 710072, China · National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology
Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization
Apr 1, 2026Yueh-Cheng Liu, Jozef Hladký, Matthias Nießner +1Implicit Differentiation 3D Gaussian Splatting
Technical University of Munich · Computing Systems Lab, Huawei Technologies, Switzerland
On the Convergence of Single-Loop Stochastic Bilevel Optimization with Approximate Implicit Differentiation
Feb 27, 2026Yubo Zhou, Luo Luo, Guang Dai +1Stochastic Bilevel Optimization Implicit Differentiation
Xi’an Jiaotong University · Fudan University · SGIT AI Lab

Sep 27, 2026J/K move · Enter open · S save

dOPT: Differentiating Conic Optimization via Geometric Reduction

Fengyu Yang, Connor W. Magoon, Tyler Watts, Shahar Z. Kovalsky

Department of Mathematics University of North Carolina at Chapel Hill

Implicit Differentiation Differentiable Programming Constrained Optimization Differentiable Optimization

Open paper AskPDF arXiv

Optimization layers enable the incorporation of structured constraints and decision problems into learning systems. Training such systems requires differentiating through the embedded optimization problem, which can be challenging for general conic programs. We introduce dOPT, a solver-agnostic framework that, rather than differentiating the full conic formulation, reduces it at a computed primal-dual solution to an equality-constrained quadratic program that preserves the reference solution and its first-order sensitivity. The reduction captures the local first- and second-order conic geometry relevant to differentiation and remains well defined at singular configurations. Computing solution derivatives then requires a single symmetric linear solve, independently of the forward solver. We derive explicit reductions for convex NLPs, QPs, SOCPs, and SDPs. Numerical experiments validate the computed gradients and show favorable backward-pass scalability, with substantial speedups over existing differentiable conic optimization methods as problem size increases.