English
Related papers

Related papers: Improving Gradient Computation for Differentiable …

200 papers

Shape optimization approaches to inverse design offer low-dimensional, physically-guided parameterizations of structures by representing them as combinations of shape primitives. However, on discretized rectilinear simulation grids,…

Computational Engineering, Finance, and Science · Computer Science 2023-11-13 Sean Hooten , Peng Sun , Liron Gantz , Marco Fiorentino , Raymond G. Beausoleil , Thomas Van Vaerenbergh

Variational Physics-Informed Neural Networks often suffer from poor convergence when using stochastic gradient-descent-based optimizers. By introducing a Least Squares solver for the weights of the last layer of the neural network, we…

Numerical Analysis · Mathematics 2025-03-20 Carlos Uriarte , Manuela Bastidas , David Pardo , Jamie M. Taylor , Sergio Rojas

Queuing network control is essential for managing congestion in job-processing systems such as service systems, communication networks, and manufacturing processes. Despite growing interest in applying reinforcement learning (RL)…

Machine Learning · Computer Science 2024-09-06 Ethan Che , Jing Dong , Hongseok Namkoong

This paper formulates optimal control problems for rigid bodies in a geometric manner and it presents computational procedures based on this geometric formulation for numerically solving these optimal control problems. The dynamics of each…

Optimization and Control · Mathematics 2008-05-07 Taeyoung Lee , Melvin Leok , N. Harris McClamroch

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters by chaining derivatives backwards through the…

Machine Learning · Statistics 2015-04-03 Dougal Maclaurin , David Duvenaud , Ryan P. Adams

We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm such as stochastic gradient descent. These procedures mirror…

Machine Learning · Statistics 2017-12-13 Luca Franceschi , Michele Donini , Paolo Frasconi , Massimiliano Pontil

Differentiable programming, enabled by automatic differentiation (AD), provides a robust framework for gradient-based optimization in computational plasma physics. While optimization is often only used towards design, we demonstrate that it…

Plasma Physics · Physics 2026-03-13 A. S. Joglekar , A. G. R. Thomas , A. L. Milder , K. G. Miller , J. P. Palastro , D. H. Froula

Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a…

Machine Learning · Computer Science 2022-11-30 Erwan Fouillen , Claire Boyer , Maxime Sangnier

Before autonomous systems can be deployed in safety-critical applications, we must be able to understand and verify the safety of these systems. For cases where the risk or cost of real-world testing is prohibitive, we propose a…

Robotics · Computer Science 2024-04-05 Charles Dawson , Anjali Parashar , Chuchu Fan

Autonomous optimization refers to the design of feedback controllers that steer a physical system to a steady state that solves a predefined, possibly constrained, optimization problem. As such, no exogenous control inputs such as setpoints…

Optimization and Control · Mathematics 2020-10-08 Adrian Hauswirth , Saverio Bolognani , Gabriela Hug , Florian Dörfler

A broad class of hybrid quantum-classical algorithms known as "variational algorithms" have been proposed in the context of quantum simulation, machine learning, and combinatorial optimization as a means of potentially achieving a quantum…

Quantum Physics · Physics 2021-04-09 Aram Harrow , John Napp

We consider non-differentiable dynamic optimization problems such as those arising in robotics and subspace tracking. Given the computational constraints and the time-varying nature of the problem, a low-complexity algorithm is desirable,…

Optimization and Control · Mathematics 2019-02-20 Rishabh Dixit , Amrit Singh Bedi , Ruchi Tripathi , Ketan Rajawat

The performance of gradient-based optimization methods, such as standard gradient descent (GD), greatly depends on the choice of learning rate. However, it can require a non-trivial amount of user tuning effort to select an appropriate…

Machine Learning · Computer Science 2025-10-14 Nikola Surjanovic , Alexandre Bouchard-Côté , Trevor Campbell

How can neural networks be trained on large-volume temporal data efficiently? To compute the gradients required to update parameters, backpropagation blocks computations until the forward and backward passes are completed. For temporal…

Computer Vision and Pattern Recognition · Computer Science 2021-07-13 Mateusz Malinowski , Dimitrios Vytiniotis , Grzegorz Swirszcz , Viorica Patraucean , Joao Carreira

Rigid body interactions are fundamental to numerous scientific disciplines, but remain challenging to simulate due to their abrupt nonlinear nature and sensitivity to complex, often unknown environmental factors. These challenges call for…

Machine Learning · Computer Science 2025-07-28 Amaury Wei , Olga Fink

Planning contact interactions is one of the core challenges of many robotic tasks. Optimizing contact locations while taking dynamics into account is computationally costly and, in environments that are only partially observable, executing…

Robotics · Computer Science 2020-04-20 Alina Kloss , Maria Bauza , Jiajun Wu , Joshua B. Tenenbaum , Alberto Rodriguez , Jeannette Bohg

With the development of state-of-art deep reinforcement learning, we can efficiently tackle continuous control problems. But the deep reinforcement learning method for continuous control is based on historical data, which would make…

Robotics · Computer Science 2016-12-02 Xi Xiong , Jianqiang Wang , Fang Zhang , Keqiang Li

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy…

Machine Learning · Computer Science 2022-06-06 Héber H. Arcolezi , Jean-François Couchot , Denis Renaud , Bechara Al Bouna , Xiaokui Xiao

Supervised learning in deep neural networks is commonly performed using error backpropagation. However, the sequential propagation of errors during the backward pass limits its scalability and applicability to low-powered neuromorphic…

Machine Learning · Computer Science 2023-08-22 Florian Bacho , Dominique Chu

Differential equations in general and neural ODEs in particular are an essential technique in continuous-time system identification. While many deterministic learning algorithms have been designed based on numerical integration via the…

Machine Learning · Computer Science 2021-10-18 Lenart Treven , Philippe Wenk , Florian Dörfler , Andreas Krause