English
Related papers

Related papers: The Legendre Transform in Modern Optimization

200 papers

An $\mathcal{O}(N(\log N)^2/\log\!\log N)$ algorithm for computing the discrete Legendre transform and its inverse is described. The algorithm combines a recently developed fast transform for converting between Legendre and Chebyshev…

Numerical Analysis · Mathematics 2015-10-06 Nicholas Hale , Alex Townsend

Using convex integration we give a constructive proof of the well-known fact that every continuous curve in a contact $3$-manifold can be approximated by a Legendrian curve.

Differential Geometry · Mathematics 2017-03-29 Norbert Hungerbühler , Thomas Mettler , Micha Wasem

Learning from point sets is an essential component in many computer vision and machine learning applications. Native, unordered, and permutation invariant set structure space is challenging to model, particularly for point set…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Mohammad Shifat E Rabbi , Naqib Sad Pathan , Shiying Li , Yan Zhuang , Abu Hasnat Mohammad Rubaiyat , Gustavo K Rohde

We introduce the Legendre bundle, a geometric structure encoding the essential duality of dually flat (Hessian) manifolds, and demonstrate that both exponential families in information geometry and a natural class of quantum field theories…

Differential Geometry · Mathematics 2026-04-07 N. C. Combe , P. G. Combe , H. K. Nencka

The Logical Execution Time (LET) programming model has recently received considerable attention, particularly because of its timing and dataflow determinism. In LET, task computation appears always to take the same amount of time (called…

Systems and Control · Electrical Eng. & Systems 2024-03-11 Sen Wang , Dong Li , Ashrarul H. Sifat , Shao-Yu Huang , Xuanliang Deng , Changhee Jung , Ryan Williams , Haibo Zeng

Loss functions serve as the foundation of supervised learning and are often chosen prior to model development. To avoid potentially ad hoc choices of losses, statistical decision theory describes a desirable property for losses known as…

Machine Learning · Statistics 2023-11-30 Kevin Lam , Christian Walder , Spiridon Penev , Richard Nock

In this work, we consider nonconvex composite problems that involve inf-convolution with a Legendre function, which gives rise to an anisotropic generalization of the proximal mapping and Moreau-envelope. In a convex setting such problems…

Optimization and Control · Mathematics 2019-03-29 Emanuel Laude , Tao Wu , Daniel Cremers

While variance reduction methods have shown great success in solving large scale optimization problems, many of them suffer from accumulated errors and, therefore, should periodically require the full gradient computation. In this paper, we…

Machine Learning · Computer Science 2022-10-05 Kazusato Oko , Shunta Akiyama , Tomoya Murata , Taiji Suzuki

Levy-Loewner evolution (LLE) is a generalization of the Schramm-Loewner evolution (SLE) where the branching is possible in a course of growth process. We consider a class of radial Levy-Loewner evolutions for which sets of points of the…

Mathematical Physics · Physics 2019-02-26 Igor Loutsenko , Oksana Yermolayeva

We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods.…

Machine Learning · Computer Science 2019-05-17 Mikhail Khodak , Maria-Florina Balcan , Ameet Talwalkar

The task of finding a consistent relationship between a quantum Hamiltonian and a classical Lagrangian is of utmost importance for basic, but ubiquitous techniques like canonical quantization and path integrals. Nonconvex kinetic energies…

Mesoscale and Nanoscale Physics · Physics 2025-09-01 C. Koliofoti , M. A. Javed , R. -P. Riwar

This paper focuses on computing the convex conjugate (also known as the Legendre-Fenchel conjugate or c-transform) that appears in Euclidean Wasserstein-2 optimal transport. This conjugation is considered difficult to compute and in…

Machine Learning · Computer Science 2025-10-07 Brandon Amos

The Liouville equation is well known to be linearizable by a point transformation. It has an infinite dimensional Lie point symmetry algebra isomorphic to a direct sum of two Virasoro algebras. We show that it is not possible to discretize…

Mathematical Physics · Physics 2015-06-22 Decio Levi , Luigi Martina , Pavel Winternitz

The Newton method is a powerful optimization algorithm, valued for its rapid local convergence and elegant geometric properties. However, its theoretical guarantees are usually limited to convex problems. In this work, we ask whether…

Optimization and Control · Mathematics 2025-10-01 Alexander Shestakov , Sushil Bohara , Samuel Horváth , Martin Takáč , Slavomír Hanzely

In some previous papers, a Legendre duality between Lagrangian and Hamiltonian Mechanics has been developed. The (\rho,\eta)-tangent application of the Legendre bundle morphism associated to a Lagrangian L or Hamiltonian H is presented.…

Mathematical Physics · Physics 2011-08-30 Constantin M. Arcuş

While systems analysis has been studied for decades in the context of control theory, it has only been recently used to improve the convergence of Denoising Diffusion Probabilistic Models. This work describes a novel improvement to Third-…

Machine Learning · Statistics 2024-09-16 Benjamin Sterling , Mónica F. Bugallo

Kendall transformation is a conversion of an ordered feature into a vector of pairwise order relations between individual values. This way, it preserves ranking of observations and represents it in a categorical form. Such transformation…

Machine Learning · Computer Science 2023-08-15 Miron Bartosz Kursa

The Euler characteristic transform (ECT) is a simple to define yet powerful representation of shape. The idea is to encode an embedded shape using sub-level sets of a a function defined based on a given direction, and then returning the…

Computational Geometry · Computer Science 2023-10-17 Elizabeth Munch

Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Nefeli Andreou , Xi Wang , Victoria Fernández Abrevaya , Marie-Paule Cani , Yiorgos Chrysanthou , Vicky Kalogeiton

Acceleration is a celebrated cornerstone of convex optimization, enabling gradient-based algorithms to converge sublinearly in the condition number. A major open question is whether an analogous acceleration phenomenon is possible for…

Probability · Mathematics 2026-04-01 Jason M. Altschuler , Sinho Chewi , Matthew S. Zhang