# Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model

arXiv: https://arxiv.org/abs/2004.00041 · HTML: https://mlsanity.com/paper/2004.00041/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [A theoretical perspective on mode collapse in variational inference](https://mlsanity.com/paper/2410.13300/) (2024)
- [Average-Case Complexity of Tensor Decomposition for Low-Degree Polynomials](https://mlsanity.com/paper/2211.05274/) (2022)
- [Sparse Multi-Reference Alignment : Phase Retrieval, Uniform Uncertainty Principles and the Beltway Problem](https://mlsanity.com/paper/2106.12996/) (2021)
- [Learning with latent group sparsity via heat flow dynamics on networks](https://mlsanity.com/paper/2201.08326/) (2022)
- [Dictionary Learning under Symmetries via Group Representations](https://mlsanity.com/paper/2305.19557/) (2023)
- [Diagonally-Weighted Generalized Method of Moments Estimation for Gaussian Mixture Modeling](https://mlsanity.com/paper/2507.20459/) (2025)
- [Minimax-optimal estimation for sparse multi-reference alignment with collision-free signals](https://mlsanity.com/paper/2312.07839/) (2023)
- [Learning under Latent Group Sparsity via Diffusion on Networks](https://mlsanity.com/paper/2507.15097/) (2025)
- [Rarity Determines Minimax Rates of Semantic Entropy From Weak Pairwise Judgments With a Known Channel](https://mlsanity.com/paper/2610.17971/) (2026)

## Abstract (arXiv)

We study the non-convex optimization landscape for maximum likelihood estimation in the discrete orbit recovery model with Gaussian noise. This model is motivated by applications in molecular microscopy and image processing, where each measurement of an unknown object is subject to an independent random rotation from a rotational group. Equivalently, it is a Gaussian mixture model where the mixture centers belong to a group orbit. We show that fundamental properties of the likelihood landscape depend on the signal-to-noise ratio and the group structure. At low noise, this landscape is "benign" for any discrete group, possessing no spurious local optima and only strict saddle points. At high noise, this landscape may develop spurious local optima, depending on the specific group. We discuss several positive and negative examples, and provide a general condition that ensures a globally benign landscape. For cyclic permutations of coordinates on ℝd (multi-reference alignment), there may be spurious local optima when d ≥ 6, and we establish a correspondence between these local optima and those of a surrogate function of the phase variables in the Fourier domain. We show that the Fisher information matrix transitions from resembling that of a single Gaussian in low noise to having a graded eigenvalue structure in high noise, which is determined by the graded algebra of invariant polynomials under the group action. In a local neighborhood of the true object, the likelihood landscape is strongly convex in a reparametrized system of variables given by a transcendence basis of this polynomial algebra. We discuss implications for optimization algorithms, including slow convergence of expectation-maximization, and possible advantages of momentum-based acceleration and variable reparametrization for first- and second-order descent methods.