English
Related papers

Related papers: Orthogonal Invariance and Identifiability

200 papers

Over the past decades, the concept "partial smoothness" has been playing as a powerful tool in several fields involving nonsmooth analysis, such as nonsmooth optimization, inverse problems and operation research, etc. The essence of partial…

Optimization and Control · Mathematics 2025-04-21 Ziqi Qin , Jingwei Liang

Identifiability means that iterates generated by optimization algorithms are eventually confined to an identifiable set. This property is computationally useful because minimizing a nonsmooth function near a critical point reduces to…

Optimization and Control · Mathematics 2026-05-05 Hanju Wu , Yue Xie

Diverse optimization algorithms correctly identify, in finite time, intrinsic constraints that must be active at optimality. Analogous behavior extends beyond optimization to systems involving partly smooth operators, and in particular to…

Optimization and Control · Mathematics 2019-02-05 Adrian S. Lewis , Calvin Wylie

One of basic difficulties of machine learning is handling unknown rotations of objects, for example in image recognition. A related problem is evaluation of similarity of shapes, for example of two chemical molecules, for which direct…

Machine Learning · Computer Science 2018-01-04 Jarek Duda

Identifiability, and the closely related idea of partial smoothness, unify classical active set methods and more general notions of solution structure. Diverse optimization algorithms generate iterates in discrete time that are eventually…

Optimization and Control · Mathematics 2024-06-24 Adrian Lewis , Tonghua Tian

Numerical solutions of differential equations are usually not smooth functions. However, they should resemble the smoothness of the corresponding real solutions in one way or another. In two of our recent papers, a kind of spacial…

Numerical Analysis · Mathematics 2012-07-13 Tong Sun

Symmetry -- invariance to certain operators -- is a fundamental concept in many branches of physics. We propose ways to measure symmetric properties of vertices, and their surroundings, in networks. To be stable to the randomness inherent…

Disordered Systems and Neural Networks · Physics 2008-06-29 Petter Holme

In this article, we investigate how the entrywise application of a non-linear function to symmetric orthogonally invariant random matrix ensembles alters the spectral distribution. We treat also the multivariate case where we apply…

Spectral Theory · Mathematics 2024-12-12 Roland Speicher , Alexander Wendel

In this paper, our focus lies on the study of the second-order variational analysis of orthogonally invariant matrix functions. It is well-known that an orthogonally invariant matrix function is an extended-real-value function defined on…

Optimization and Control · Mathematics 2025-03-06 Jiahuan He , Chao Kan , Wen Song

The maximum (or minimum) generalized eigenvalue of symmetric positive semidefinite matrices that depend on optimization variables often appears as objective or constraint functions in structural topology optimization when we consider…

Optimization and Control · Mathematics 2024-05-09 Akatsuki Nishioka , Yoshihiro Kanno

Orbifold equivalence is a notion of symmetry that does not rely on group actions. Among other applications, it leads to surprising connections between hitherto unrelated singularities. While the concept can be defined in a very general…

Quantum Algebra · Mathematics 2017-08-29 Andreas Recknagel , Paul Weinreb

Critical points of an invariant function may or may not be symmetric. We prove, however, that if a symmetric critical point exists, those adjacent to it are generically symmetry breaking. This mathematical mechanism is shown to carry…

Machine Learning · Computer Science 2024-08-27 Yossi Arjevani

A large number matrix optimization problems are described by orthogonally invariant norms. This paper is devoted to the study of variational analysis of the orthogonally invariant norm cone of symmetric matrices. For a general orthogonally…

Optimization and Control · Mathematics 2023-02-14 Yule Zhang , Jihong Zhang , Liwei Zhang

A class of parametric functions formed by alternating compositions of multivariate polynomials and rectification style monomial maps is studied (the layer-wise exponents are treated as fixed hyperparameters and are not optimized). For this…

Optimization and Control · Mathematics 2026-02-13 Shravan Mohan

A general invariant manifold theorem is needed to study the topological classes of smooth dynamical systems. These classes are often invariant under renormalization. The classical invariant manifold theorem cannot be applied, because the…

Dynamical Systems · Mathematics 2019-08-20 M. Martens , L. Palmisano

Symmetry plays a crucial role in understanding the properties of mathematical structures and optimization problems. Recent work has explored this phenomenon in the context of neural networks, where the loss function is invariant under…

Machine Learning · Computer Science 2025-06-04 Irmi Schneider

Many contemporary applications in signal processing and machine learning give rise to structured non-convex non-smooth optimization problems that can often be tackled by simple iterative methods quite effectively. One of the keys to…

Optimization and Control · Mathematics 2020-06-29 Jiajin Li , Anthony Man-Cho So , Wing-Kin Ma

We study convolutional neural networks with monomial activation functions. Specifically, we prove that their parameterization map is regular and is an isomorphism almost everywhere, up to rescaling the filters. By leveraging on tools from…

Machine Learning · Computer Science 2025-03-04 Vahid Shahverdi , Giovanni Luca Marchetti , Kathlén Kohn

The Eigendecomposition of quadratic forms (symmetric matrices) guaranteed by the spectral theorem is a foundational result in applied mathematics. Motivated by a shared structure found in inferential problems of recent interest---namely…

Machine Learning · Computer Science 2018-02-26 Mikhail Belkin , Luis Rademacher , James Voss

Model reparametrization, which follows the change-of-variable rule of calculus, is a popular way to improve the training of neural nets. But it can also be problematic since it can induce inconsistencies in, e.g., Hessian-based flatness…

Machine Learning · Computer Science 2023-10-24 Agustinus Kristiadi , Felix Dangel , Philipp Hennig
‹ Prev 1 2 3 10 Next ›