paper-with-me

홈 › Papers

Conjugation Invariant Learning with Neural Networks

2021-09-29 · Aaron Yi Rui Low, Subhroshekhar Ghosh, Yong Sheng Soh

Machine learning under the constraint of symmetries, given by group invariances or equivariances, has emerged as a topic of active interest in recent years. Natural settings for such applications include the multi-reference alignment and cryo electron microscopy, multi-object tracking, spherical images, and so on. A fundamental paradigm among such symmetries is the action of a group by symmetries, which often pertains to change of basis or relabelling of objects in pure and applied mathematics. Thus, a naturally significant class of functions consists of those that are intrinsic to the problem, in the sense of being independent of such base change or relabelling; in other words invariant under the conjugation action by a group. In this work, we investigate such functions, known as class functions, leveraging tools from group representation theory. A fundamental ingredient in our approach are given by the so-called irreducible characters of the group, which are canonical tracial class functions related to its irreducible representations. Such functions form an orthogonal basis for the class functions, extending ideas from Fourier analysis to this domain, and accord a very explicit structure. Exploiting a tensorial structure on representations, which translates into a multiplicative algebra structure for irreducible characters, we propose to efficiently approximate class functions using polynomials in a small number of such characters. Thus, our approach provides a global, non-linear coordinate system to describe functions on the group that is intrinsic in nature, in the sense that it is independent of local charts, and can be easily computed in concrete models. We demonstrate that such non-linear approximation using a small dictionary can be effectively implemented using a deep neural network paradigm. This allows us to learn a class function efficiently from a dataset of its outputs.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object TrackingObject Tracking

Similar Papers 제목 키워드 기반

Guidelines for the estimation and reporting of plasmid conjugation rates

2023-03-01 · Olivia Kosterlitz, Jana S. Huisman

Conjugation is a central characteristic of plasmid biology and an important mechanism of horizontal gene transfer in bacteria. However, there is little consensus on how to accurately estimate and report plasmid conjugati…

Sampling using $SU(N)$ gauge equivariant flows

2020-08-12 · Denis Boyda, Gurtej Kanwar, Sébastien Racanière, Danilo Jimenez Rezende 외

We develop a flow-based sampling algorithm for $SU(N)$ lattice gauge theories that is gauge-invariant by construction. Our key contribution is constructing a class of flows on an $SU(N)$ variable (or on a $U(N)$ variable…

Japanese Predicate Conjugation for Neural Machine Translation

2018-05-25 · NAACL 2018 6 · Michiki Kurosawa, Yukio Matsumura, Hayahide Yamagishi, Mamoru Komachi

Neural machine translation (NMT) has a drawback in that can generate only high-frequency words owing to the computational costs of the softmax function in the output layer. In Japanese-English NMT, Japanese predicate c…

Machine TranslationNMTTranslation

KoParadigm: A Korean Conjugation Paradigm Generator

2020-04-28 · Kyubyong Park

Korean is a morphologically rich language. Korean verbs change their forms in a fickle manner depending on tense, mood, speech level, meaning, etc. Therefore, it is challenging to construct comprehensive conjugation para…

A Galois theorem for machine learning: Functions on symmetric matrices and point clouds via lightweight invariant features

2024-05-13 · Ben Blum-Smith, Ningyuan Huang, Marco Cuturi, Soledad Villar

In this work, we present a mathematical formulation for machine learning of (1) functions on symmetric matrices that are invariant with respect to the action of permutations by conjugation, and (2) functions on point clo…