English
Related papers

Related papers: One-step differentiation of iterative algorithms

200 papers

In this paper we propose two proximal gradient algorithms for fractional programming problems in real Hilbert spaces, where the numerator is a proper, convex and lower semicontinuous function and the denominator is a smooth function, either…

Optimization and Control · Mathematics 2016-02-01 Radu Ioan Bot , Ernö Robert Csetnek

In this paper, we investigate the trade-off between convergence rate and computational cost when minimizing a composite functional with proximal-gradient methods, which are popular optimisation tools in machine learning. We consider the…

Machine Learning · Computer Science 2012-10-23 Pierre Machart , Sandrine Anthoine , Luca Baldassarre

We introduce a class of first-order methods for smooth constrained optimization that are based on an analogy to non-smooth dynamical systems. Two distinctive features of our approach are that (i) projections or optimizations over the entire…

Optimization and Control · Mathematics 2025-04-15 Michael Muehlebach , Michael I. Jordan

We show how to increase the order of one-dimensional discrete gradient numerical integrator without losing its advantages, such as exceptional stability, exact conservation of the energy integral and exact preservation of the trajectories…

Computational Physics · Physics 2010-08-24 Jan L. Cieśliński , Bogusław Ratkiewicz

In this paper we propose a new inexact dual decomposition algorithm for solving separable convex optimization problems. This algorithm is a combination of three techniques: dual Lagrangian decomposition, smoothing and excessive gap. The…

Optimization and Control · Mathematics 2013-02-11 Quoc Tran Dinh , Ion Necoara , Moritz Diehl

When an inverse problem is solved by a gradient-based optimization algorithm, the corresponding forward and adjoint problems, which are introduced to compute the gradient, can be also solved iteratively. The idea of iterating at the same…

Numerical Analysis · Mathematics 2025-01-23 Marcella Bonazzoli , Houssem Haddar , Tuan Anh Vu

We present two improvements to arithmetic in the Jacobian of global function fields based on the approach of Hess. The first reduces the number of expensive reduction steps by optimizing for typical inputs rather than worst-case behavior,…

Number Theory · Mathematics 2026-05-18 Vincent Macri , Michael Jacobson , Renate Scheidler

Practical optimization problems may contain different kinds of difficulties that are often not tractable if one relies on a particular optimization method. Different optimization approaches offer different strengths that are good at…

Neural and Evolutionary Computing · Computer Science 2024-07-08 Ankur Sinha , Dhaval Pujara , Hemant Kumar Singh

This paper explores a method for solving constrained optimization problems when the derivatives of the objective function are unavailable, while the derivatives of the constraints are known. We allow the objective and constraint function to…

Optimization and Control · Mathematics 2024-02-20 Melody Qiming Xuan , Jorge Nocedal

We explore probability modelling of discretization uncertainty for system states defined implicitly by ordinary or partial differential equations. Accounting for this uncertainty can avoid posterior under-coverage when likelihoods are…

Methodology · Statistics 2016-10-25 Oksana A. Chkrebtii , David A. Campbell , Ben Calderhead , Mark A. Girolami

For a real function, automatic differentiation is such a standard algorithm used to efficiently compute its gradient, that it is integrated in various neural network frameworks. However, despite the recent advances in using complex…

Machine Learning · Computer Science 2021-01-19 Chu Guo , Dario Poletti

We propose a differentiable successive halving method of relaxing the top-k operator, rendering gradient-based optimization possible. The need to perform softmax iteratively on the entire vector of scores is avoided by using a…

Machine Learning · Computer Science 2020-10-30 Michał Pietruszka , Łukasz Borchmann , Filip Graliński

Kaltofen has proposed a new approach in [Kaltofen 1992] for computing matrix determinants. The algorithm is based on a baby steps/giant steps construction of Krylov subspaces, and computes the determinant as the constant term of a…

Symbolic Computation · Computer Science 2011-12-13 Gilles Villard

We use a rank one Gaussian perturbation to derive a smooth stochastic approximation of the maximum eigenvalue function. We then combine this smoothing result with an optimal smooth stochastic optimization algorithm to produce an efficient…

Optimization and Control · Mathematics 2014-03-05 Alexandre d'Aspremont , Noureddine El Karoui

Predict and optimize is an increasingly popular decision-making paradigm that employs machine learning to predict unknown parameters of optimization problems. Instead of minimizing the prediction error of the parameters, it trains…

Machine Learning · Computer Science 2024-02-05 Grigorii Veviurko , Wendelin Böhmer , Mathijs de Weerdt

Automated code generation allows for a separation between the development of a model, expressed via a domain specific language, and lower level implementation details. Algorithmic differentiation can be applied symbolically at the level of…

Programming Languages · Computer Science 2024-09-27 James R. Maddison

We introduce a class of unconditionally energy stable, high order accurate schemes for gradient flows in a very general setting. The new schemes are a high order analogue of the minimizing movements approach for generating a time discrete…

Numerical Analysis · Mathematics 2020-02-11 Alexander Zaitzeff , Selim Esedoglu , Krishna Garikipati

Iteration methods based on barycentric rational interpolation are derived that exhibit accelerating orders of convergence. For univariate root search, the derivative-free methods approach quadratic convergence and the first-derivative…

Numerical Analysis · Mathematics 2020-11-11 Sebastian Cassel

Bayesian inference plays an important role in advancing machine learning, but faces computational challenges when applied to complex models such as deep neural networks. Variational inference circumvents these challenges by formulating…

Machine Learning · Statistics 2018-08-03 Mohammad Emtiyaz Khan , Didrik Nielsen

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical…

Machine Learning · Computer Science 2024-07-03 Antony Vijesh , Shreyas S R