English
Related papers

Related papers: Conservative set valued fields, automatic differen…

200 papers

We analyze the constant step size subgradient method on nonsmooth, nonconvex functions. We identify geometric assumptions on the objective function under which i) its domain admits a partition (stratification) into smooth manifolds (strata)…

Optimization and Control · Mathematics 2026-04-21 Evgenii Chzhen , Sholom Schechtman

We propose a categorical semantics of gradient-based machine learning algorithms in terms of lenses, parametrised maps, and reverse derivative categories. This foundation provides a powerful explanatory and unifying framework: it…

Machine Learning · Computer Science 2021-07-14 G. S. H. Cruttwell , Bruno Gavranović , Neil Ghani , Paul Wilson , Fabio Zanasi

These lecture notes for a graduate course cover generalized derivative concepts useful in deriving necessary optimality conditions and numerical algorithms for nondifferentiable optimization problems in inverse problems, imaging, and…

Optimization and Control · Mathematics 2022-03-16 Christian Clason

We consider smooth stochastic convex optimization problems in the context of algorithms which are based on directional derivatives of the objective function. This context can be considered as an intermediate one between derivative-free…

Optimization and Control · Mathematics 2020-09-22 Pavel Dvurechensky , Eduard Gorbunov , Alexander Gasnikov

We propose a class of very simple modifications of gradient descent and stochastic gradient descent. We show that when applied to a large variety of machine learning problems, ranging from logistic regression to deep neural nets, the…

Machine Learning · Computer Science 2019-04-30 Stanley Osher , Bao Wang , Penghang Yin , Xiyang Luo , Farzin Barekat , Minh Pham , Alex Lin

Automatic differentiation (AD) in reverse mode (RAD) is a central component of deep learning and other uses of large-scale optimization. Commonly used RAD algorithms such as backpropagation, however, are complex and stateful, hindering deep…

Programming Languages · Computer Science 2018-10-03 Conal Elliott

In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external…

Machine Learning · Computer Science 2016-01-06 John Schulman , Nicolas Heess , Theophane Weber , Pieter Abbeel

Calibration of large-scale differential equation models to observational or experimental data is a widespread challenge throughout applied sciences and engineering. A crucial bottleneck in state-of-the art calibration methods is the…

Optimization and Control · Mathematics 2021-02-23 Jon Cockayne , Andrew B. Duncan

State-of-the-art fully intrinsic networks for non-rigid shape matching often struggle to disambiguate the symmetries of the shapes leading to unstable correspondence predictions. Meanwhile, recent advances in the functional map framework…

Computer Vision and Pattern Recognition · Computer Science 2022-04-29 Nicolas Donati , Etienne Corman , Maks Ovsjanikov

The goal and the main result of the paper is to provide a complete description of the field of rational differential invariants of one class of second order ordinary differential equations with scalar control parameter with respect to Lie…

Analysis of PDEs · Mathematics 2015-06-26 D. S. Gritsenko , O. M. Kiriukhin

We develope a difference calculus analogous to the differential geometry by translating the forms and exterior derivatives to similar expressions with difference operators, and apply the results to fields theory on the lattice [Ref. 1]. Our…

High Energy Physics - Lattice · Physics 2007-05-23 M. Lorente

Discrete gradient methods are a powerful tool for the time discretization of dynamical systems, since they are structure-preserving regardless of the form of the total energy. In this work, we discuss the application of discrete gradient…

Numerical Analysis · Mathematics 2026-01-06 Philipp L. Kinon , Riccardo Morandin , Philipp Schulze

A method for machine learning and serving of discrete field theories in physics is developed. The learning algorithm trains a discrete field theory from a set of observational data on a spacetime lattice, and the serving algorithm uses the…

Computational Physics · Physics 2024-11-04 Hong Qin

We show how complexity theory can be introduced in machine learning to help bring together apparently disparate areas of current research. We show that this new approach requires less training data and is more generalizable as it shows…

Machine Learning · Computer Science 2019-10-10 Santiago Hernández-Orozco , Hector Zenil , Jürgen Riedel , Adam Uccello , Narsis A. Kiani , Jesper Tegnér

Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply "autodiff", is a family of techniques similar to but more…

Symbolic Computation · Computer Science 2018-07-18 Atilim Gunes Baydin , Barak A. Pearlmutter , Alexey Andreyevich Radul , Jeffrey Mark Siskind

A systematic digital-discrete method for obtaining continuous functions with smoothness to a certain order (C^(n)) from sample data is designed. This method is based on gradually varied functions and the classical finite difference method.…

Numerical Analysis · Mathematics 2010-10-19 Li Chen

The discrete gradient methods are integrators designed to preserve invariants of ordinary differential equations. From a formal series expansion of a subclass of these methods, we derive conditions for arbitrarily high order. We derive…

Numerical Analysis · Mathematics 2022-01-19 Sølve Eidnes

Nonconservative evolution problems describe irreversible processes and dissipative effects in a broad variety of phenomena. Such problems are often characterised by a conservative part, which can be modelled as a Hamiltonian term, and a…

Numerical Analysis · Mathematics 2025-05-12 Damiano Lombardi , Cecilia Pagliantini

Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed, they break the…

Machine Learning · Computer Science 2020-06-11 Quentin Berthet , Mathieu Blondel , Olivier Teboul , Marco Cuturi , Jean-Philippe Vert , Francis Bach

Particle filters flexibly represent multiple posterior modes nonparametrically, via a collection of weighted samples, but have classically been applied to tracking problems with known dynamics and observation likelihoods. Such generative…

Machine Learning · Computer Science 2024-04-16 Ali Younis , Erik Sudderth