Implicit Differentiation

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 167% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 45

All topics

Learn-Then-Differentiate Gradient Estimation
Sep 30, 2026Nifei Lin, Qingkai Zhang, L. Jeff HongGradient Implicit Differentiation
Research Institute for Interdisciplinary Sciences, School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai 200433, China · Department of Decision Analytics and Operations, City University of Hong Kong, Hong Kong, China · Department of Industrial and Systems Engineering, University of Minnesota, Minneapolis, Minnesota 55455
dOPT: Differentiating Conic Optimization via Geometric Reduction
Sep 27, 2026Fengyu Yang, Connor W. Magoon, Tyler Watts +1Convex Optimization Differentiable Optimization
Department of Mathematics University of North Carolina at Chapel Hill
A unified framework for global and local interpretability using adaptive derivative-ordered random explanation
Sep 15, 2026Lemen Chao, Ming Lei, Anran FangInterpretability Feature Importance
School of Information Resource Management, Renmin University of China, Beijing, 100872, People’s Republic of China. · Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, 100872, People’s Republic of China.
Recovering Governing Dynamics from Distributed Observations via Exact Spline Merging
Sep 15, 2026Naveen MysoreSpatiotemporal Fields Splines
University of California, Santa Barbara · Dyssonance AI
Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative
Sep 14, 2026Amartya Mukherjee, Tristan Milne, Kry Yik-Chau Lui +2Score-Based Diffusion Model Outliers
Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario, Canada N2L 3G1 · Royal Bank of Canada, 1 Place Ville Marie, Montreal, Quebec, H3C 3A9
Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete Representations
Sep 14, 2026Mohammed Ahnouch, Lotfi ElaachackMultilingual Safety Representation-Level Misalignment
Université Paris 1 Paris, France · Faculty of Science and Technology of Tangier Abdelmalek Essaadi University Tangier, Morocco
Critical initialization destabilizes higher input derivatives in wide scalar-input networks
Sep 10, 2026Prashant Singh, Pranav SinghTwo-Layer Neural Networks Mean-Field Limit
Department of Mathematics, Indian Institute of Technology Ropar, Rupnagar, Punjab, 140001, India
Structured Extrema Errors in Classical Surrogates for Viscous Burgers: A Physics-Consistent Interpretation
Sep 7, 2026Youssef OubariSurrogate Models One-Dimensional Viscous Burgers Equation
IMT Atlantique, France
Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design
Sep 2, 2026Runlin Shi, Bojian Yin, Guoqi LiRotary Position Embedding Transformer Architectures
Institute of Automation, Chinese Academy of Sciences, Beijing, China
Hard-ReLU Gradient Descent Selects an Event-Free Sensitivity Limit
Aug 31, 2026Xiaoyang Li, Runni ZhouGradient Local Curvature
College of Medicine and Biological Information Engineering Northeastern University, Shenyang, China
Derivative Computation in PINNs: Automatic Differentiation, Finite Differences and Beyond
Aug 11, 2026Maciej J. Mikulski, Tadeusz UhlParametric Physics-Informed Neural Network Implicit Differentiation
AGH University of Krakow
Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation
Aug 9, 2026Lei Shu, Ying Jiang, Kui Wu +3Differentiable Physics Adjoint Matching
Stanford University · University of California, Los Angeles · LightSpeed Studios, Tencent America +1
LC-Implicit-QAOA: Active-Workspace-Capped Exact Objective-and-Gradient Evaluation for Training over Bounded QUBO Light Cones
Aug 6, 2026Chih-Chung HsuQuantum Approximate Optimization Algorithm Quadratic Unconstrained Binary Optimization
Institute of Smart Industry and Green Energy, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Amortising Trajectory Optimisation for Residual MPC via Implicit Contact Differentiation
Jul 27, 2026Daniel Layeghi, Thomas Corbères, Calum Arnott +4Robust Trajectory Implicit Differentiation
School of Informatics, University of Edinburgh, Scotland.
Optimizing Regret
Jul 21, 2026Irene AldridgeRegret Policy Gradient
Risk AI Center
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
Jul 16, 2026Paul Darm, Cem Alpturk, Kenneth Ulrich +3Shapley Additive Explanations Prompt Optimization
University of Strathclyde, Glasgow, United Kingdom · Weir, Malmö, Sweden · Weir, Glasgow, United Kingdom
Attention-Based Segmentation of WMHs and Differentiation of Vascular vs. Demyelinating Lesions
Jul 9, 2026Aina Tur-Serrano, Gabriel Moyà-Alcover, Francisco J. Perales LópezImplicit Differentiation
UGiVIA Research Group, Dpt. of Mathematics and Computer Science, Universitat de les Illes Balears, Palma de Mallorca, 07122, Spain
Physically-Relevant Information Learning in High-Dimensional Time-Derivatives Spaces
Jul 6, 2026Domiziano Doria, Matteo Becchi, Giovanni M. PavanImplicit Differentiation Molecular Dynamics
Department of Applied Science and Technology, Politecnico di Torino, Torino 10129, Italy
An AI-Assisted Solution to the Signed BAR Conjecture: Uniqueness in the Harrison--Reiman Class and a Completely- $\mathcal{S}$ Class Obstruction
Jul 3, 2026Yiping Lu, Youheng ZhuMatrix Adjoint Matching
Department of Industrial Engineering and Management Sciences, McCormick School of Engineering, Northwestern University.
Reflected Schrödinger Bridge Matching
Jul 3, 2026Marcus Häggbom, Viktor Nilsson, Pierre Nyquist +1Schrödinger Bridges Generative Models
SEB Group and Department of Mathematics KTH Royal Institute of Technology Stockholm, Sweden · Department of Mathematical Sciences Chalmers University of Technology and University of Gothenburg and Department of Mathematics KTH Royal Institute of Technology
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
Jun 25, 2026Qicheng Zhao, Yu Li, Qi Sun +1Residual Conditional Diffusion Model Diffusion Models
Zhejiang University, Hangzhou, China
A Zeroth-Order Deep Learning Method for Fully Nonlinear Parabolic Partial Differential Equations with Unknown Coefficients
Jun 23, 2026Yanwei Jia, Du Ouyang, Huyên Pham +1Partial Differential Equations Nonlinear Operators
Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin, New Territories, Hong Kong SAR · Department of Mathematical Sciences Tsinghua University Beijing, Beijing 100084, China · CMAP Ecole Polytechnique Route de Saclay, Palaiseau 91128, France +1
Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Jun 18, 2026Jianing Guo, Fangzheng Chen, Zihao Mao +12Multimodal Action Distributions Conditional Flow Matching
Beihang University · PKU-Psibot Lab · The Chinese University of Hong Kong +3
DiffMath: Symbol- and Graph-Aware Latent Diffusion Transformer for Handwritten Mathematical Expression Generation
Jun 18, 2026Wei Pan, Xuhan Zheng, Yilin Shi +5Symbol-Implicit Differentiation
South China University of Technology · Huawei Technologies Co., Ltd.
Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks
Jun 13, 2026Abdeladhim TahimiParametric Physics-Informed Neural Network Implicit Differentiation
CECA, Universidade Federal de Alagoas (UFAL), Rio Largo, Alagoas, 57100-000, Brazil
Deep Unfolded Latent Optimally Partitioned-l2/l1 Networks for Data-driven Block-Sparse Recovery
Jun 10, 2026Takanobu Furuhashi, Hidekata Hontani, Qibin Zhao +1Deep Unfolding Networks Sparsity
Nagoya Institute of Technology · RIKEN Center for Advanced Intelligence Project
Integral Formulation of QENDy for Robust Nonlinear System Identification
Jun 10, 2026Nikhil Saran, Sushant Pokhriyal, Stefan Klus +2System Identification Nonlinear Dynamics
Department of Mathematics and Statistics at the University of South Florida · Institute of Engineering and Technology, JK Lakshmipat University, Jaipur, India · School of Mathematical & Computer Sciences at the Heriot–Watt University, Edinburgh +1
Symmetric Hermite quadrature-based balanced truncation for learning linear dynamical systems from derivative data
May 29, 2026Sean Reiter, Steffen W. R. WernerReduced-Order Models Dynamical Systems
Courant Institute School of Mathematics, Computing, and Data Science, New York University, New York, NY 10012, USA. · Department of Mathematics, Division of Computational Modeling and Data Analytics, and National Security Institute, Virginia Tech, Blacksburg, VA 24061, USA.
Hermite-NGP: Gradient-Augmented Hash Encoding for Learning PDEs
May 23, 2026Jinjin He, Zhiqi Li, Sinan Wang +1Neural Partial Differential Equation Solvers Partial Differential Equations
Georgia Institute of Technology, Atlanta, GA, USA.
On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
May 20, 2026Yue Zhang, Zhiyi Dong, Tommaso Cesari +1Reasoning Trajectory Thoughts
University of Ottawa, Ottawa, Canada
Structured Jacobian Construction for Motion Optimization with High-Order Time Derivatives in Multi-Link Systems
May 15, 2026Taiki Ishigaki, Ko Ayusawa, Eiichi YoshidaJacobian Implicit Differentiation
Tokyo University of Science · National Institute of Advanced Industrial Science and Technology
Universal Approximation of Nonlinear Operators and Their Derivatives
May 14, 2026Filippo de FeoNonlinear Operators Neural Approximations
Institut für Mathematik, Technische Universität Berlin.
Lie Group Formulation of Recursive Dynamics Algorithms of Higher Order for Floating-Base Robots
May 7, 2026Ahmed Ali, Chiara Gabellieri, Antonio FranchiLie Group Lagrangian Methods
Robotics and Mechatronics Department, Electrical Engineering, Mathematics, and Computer Science (EEMCS) Faculty, University of Twente, 7500 AE Enschede, The Netherlands. · Department of Computer, Control and Management Engineering, Sapienza University of Rome, 00185 Rome, Italy.
Tuning Derivatives for Causal Fairness in Machine Learning
May 7, 2026Filip Edström, Guilherme W. F. Barros, Tetiana Gorbach +1Algorithmic Fairness Causal Inferences
Department of Statistics, Umeå School of Business, Economics and Statistics, Umeå University, Umeå, 901 87, Sweden. · Integrated Science Lab, Department of Physics, Ume˚a University, Ume˚a, 901 87, Sweden. · Department of Statistics, Ume˚a School of Business, Economics and Statistics, Ume˚a University, Ume˚a, 901 87, Sweden.
Exact Higher-Order Derivatives for SE(3) via Analytical/AD Methods
May 4, 2026Frank O. KuehnelImplicit Differentiation Lie Group
Sigma Point Labs, Denver, CO, USA
Additive Atomic Forests for Symbolic Function and Antiderivative Discovery
May 1, 2026Reda BelaicheSymbolic Regression Symbol-
Université Paris-Est Créteil, Vitry-sur-Seine, France
Closed Form Relations and Higher-Order Approximations of First and Second Derivatives of the Tangent Operator on SE(3)
Apr 24, 2026Andreas MuellerLie Group Tangent Space
Institute of Robotics, Johannes Kepler University Linz, Austria
Python library supporting Discrete Variational Formulations and training solutions with Collocation-based Robust Variational Physics Informed Neural Networks (DVF-CRVPINN)
Apr 16, 2026Tomasz Służalec, Marcin Łoś, Askold Vilkha +1Variational Formulation Neural Network
AGH University of Krakow, Poland
Model Predictive Path Integral PID Control for Learning-Based Path Following
Mar 31, 2026Teruki Kato, Koshi Oishi, Seigo ItoModel Predictive Path Integral Model Predictive Control
Toyota Central R&D Labs., Inc., Nagakute 480-1192, Japan
Stochastic Dimension Zeroth-Order Estimator: Stable and Memory-Efficient Training of PINNs
Mar 25, 2026Zhangyong Liang, Huanhuan GaoZeroth-Order Partial Differential Equations
National Center for Applied Mathematics, Tianjin University, Tianjin 300072, China. · School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130025, China
Pseudo-differential-enhanced physics-informed neural networks
Feb 16, 2026Andrew GracykParametric Physics-Informed Neural Network Neural Network
Department of Mathematics, Purdue University, West Lafayette, IN 47907, United States
Robust and Efficient MuJoCo-based Model Predictive Control via Web of Affine Spaces Derivatives
Dec 24, 2025Chen Liang, Daniel RakitaModel Predictive Control Mujoco
Department of Computer Science, Yale University, New Haven, CT 06520, USA
Shoot from the HIP: Hessian Interatomic Potentials without derivatives
Sep 25, 2025Andreas Burger, Luca Thiede, Nikolaj Rønne +5Hessian Interatomic Potentials
University of Toronto · Vector Institute for Artificial Intelligence · Technical University of Denmark +4
Highly-Efficient Differentiable Simulation for Robotics
Sep 11, 2024Quentin Le Lidec, Louis Montaut, Yann de Mont-Marin +3Rigid-Body Dynamics Differentiable Physics
Inria, Ecole normale sup´erieure CNRS, PSL Research University 75005 Paris, France
An Overview of Formulae for the Higher-Order Kinematics of Lower-Pair Chains with Applications in Robotics and Mechanism Theory
Sep 10, 2023Andreas MuellerKinematic Chain Kinematics
JKU Johannes Kepler University, Linz, Austria

Sep 30, 2026, stat.COJ/K move · Enter open · S save

Learn-Then-Differentiate Gradient Estimation

Nifei Lin, Qingkai Zhang, L. Jeff Hong

Research Institute for Interdisciplinary Sciences, School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai 200433, China · Department of Decision Analytics and Operations, City University of Hong Kong, Hong Kong, China · Department of Industrial and Systems Engineering, University of Minnesota, Minneapolis, Minnesota 55455

Gradient Implicit Differentiation Kernel Ridge Regression Neural Network

Open paper AskPDF arXiv

Learn-then-differentiate (LTD) estimates gradients by fitting a model to simulation outputs and differentiating it. We develop a unified framework explaining what LTD differentiates and how accurately it estimates gradients. For models with a weighted representation, LTD differentiates a learned representation of the underlying probability measure. We then show how accuracy guarantees for fitted models translate into guarantees for gradients and higher-order derivatives, with rates approaching the standard Monte Carlo rate under suitable smoothness conditions. The framework recovers established results for kernel regression, local polynomial regression, and kernel ridge regression, and yields further guarantees for multiple kernel learning and smooth neural networks. These results provide a common foundation for understanding and analyzing LTD across learning methods.

Momentum

Related topics

Latest papers 45