# Dictionary Learning under Symmetries via Group Representations

arXiv: https://arxiv.org/abs/2305.19557 · HTML: https://mlsanity.com/paper/2305.19557/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 56 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 14 of 14)

- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [SE-Sync: A Certifiably Correct Algorithm for Synchronization over the Special Euclidean Group](https://mlsanity.com/paper/1612.07386/) (2016)
- [Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction](https://mlsanity.com/paper/1802.05451/) (2018)
- [Convolutional Dictionary Learning: A Comparative Review and New Algorithms](https://mlsanity.com/paper/1709.02893/) (2017)
- [Convolutional Dictionary Learning via Local Processing](https://mlsanity.com/paper/1705.03239/) (2017)
- [Estimation under group actions: recovering orbits from invariants](https://mlsanity.com/paper/1712.10163/) (2017)
- [Multireference Alignment using Semidefinite Programming](https://mlsanity.com/paper/1308.5256/) (2013)
- [Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model](https://mlsanity.com/paper/2004.00041/) (2020)
- [Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM](https://mlsanity.com/paper/2107.01305/) (2021)
- [The sample complexity of multi-reference alignment](https://mlsanity.com/paper/1707.00943/) (2017)
- [Group Invariant Dictionary Learning](https://mlsanity.com/paper/2007.07550/) (2020)
- [Symmetric Tensor Nuclear Norms](https://mlsanity.com/paper/1605.08823/) (2016)
- [Sparse Multi-Reference Alignment : Phase Retrieval, Uniform Uncertainty Principles and the Beltway Problem](https://mlsanity.com/paper/2106.12996/) (2021)
- [On learning with shift-invariant structures](https://mlsanity.com/paper/1812.01115/) (2018)

## Built on by (most cited first, 1 of 1)

- [Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning](https://mlsanity.com/paper/2411.00173/) (2024)

## Abstract (arXiv)

The dictionary learning problem can be viewed as a data-driven process to learn a suitable transformation so that data is sparsely represented directly from example data. In this paper, we examine the problem of learning a dictionary that is invariant under a pre-specified group of transformations. Natural settings include Cryo-EM, multi-object tracking, synchronization, pose estimation, etc. We specifically study this problem under the lens of mathematical representation theory. Leveraging the power of non-abelian Fourier analysis for functions over compact groups, we prescribe an algorithmic recipe for learning dictionaries that obey such invariances. We relate the dictionary learning problem in the physical domain, which is naturally modelled as being infinite dimensional, with the associated computational problem, which is necessarily finite dimensional. We establish that the dictionary learning problem can be effectively understood as an optimization instance over certain matrix orbitopes having a particular block-diagonal structure governed by the irreducible representations of the group of symmetries. This perspective enables us to introduce a band-limiting procedure which obtains dimensionality reduction in applications. We provide guarantees for our computational ansatz to provide a desirable dictionary learning outcome. We apply our paradigm to investigate the dictionary learning problem for the groups SO(2) and SO(3). While the SO(2)-orbitope admits an exact spectrahedral description, substantially less is understood about the SO(3)-orbitope. We describe a tractable spectrahedral outer approximation of the SO(3)-orbitope, and contribute an alternating minimization paradigm to perform optimization in this setting. We provide numerical experiments to highlight the efficacy of our approach in learning SO(3)-invariant dictionaries, both on synthetic and on real world data.