Papers for

statistical machine learning teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Sample sizes grow exponentially to estimate rotation in overcomplete ICA

Identifiable but Hard to Estimate: Rotation in Equally Spaced Overcomplete ICA

Abstract: How many observations are needed to estimate a common rotation in two-dimensional overcomplete independent component analysis? We study equally spaced mixing columns with known source count, common source law, and column norm. For a fixed non-Gaussian fourth-order Gram-Charlier source law, the rotation is identifiable modulo the column spacing. Yet the sample size for fixed relative angular accuracy grows exponentially with the source count. We characterize this sample size, up to absolute constants, by the reciprocal of the squared Hellinger distance between two rotations separated by half the column spacing. An explicit radially weighted phase estimator attains this scale uniformly over the rotation family, using the observation radius to prevent cancellation in the mean of an angular harmonic. We also determine the exact exponential decay rate of single-observation total variation for the same pair. This gives bounds on the sample size exponent; its exact value remains open. Finally, a noisy binary-source example shows how an exact zero line of the observed characteristic function can have an exponentially small normal derivative.

Mon 9 NovMachine LearningInformation Theory
The gist
The paper looks at how hard it is to figure out the right rotation in a certain math problem called overcomplete independent component analysis (ICA), when sources are spaced evenly. The authors found that although the rotation can be identified, the number of observations needed to estimate it accurately grows exponentially as more sources are involved. They provide mathematical ways to understand this growth and propose an estimator that works consistently. They also explore how noise affects the problem and why some features make estimation even harder.
Open → 2611.11852v1

Rapid convergence of Glauber dynamics in Ising models with large spin majority

Rapid mixing within a phase for Ising models

Abstract: We study Glauber dynamics for Ising measures conditioned to have a sufficiently large majority of $+1$ spins. Under a sparse spectral width condition on the interaction matrix, we derive a Poincaré inequality for the conditioned measures from a magnetization drift condition, and a modified logarithmic Sobolev inequality from a stronger, entropy weighted condition. As applications, we obtain approximate posterior sampling in total variation distance for $\mathbb{Z}_2$ synchronization at high enough signal-to-noise ratio using $O(n\log n)$ Glauber updates from a spectral initialization. For ferromagnetic Ising models on random $d$-regular graphs, we prove rapid phase ordering down to inverse temperatures of order $1/d$, extending the temperature range of Gheissari, Sly, and Sohn (2025). Finally, we extend these inequalities to unconditioned Ising measures under an inward drift condition outside the conditioned region. This yields $O(n\log n)$ mixing of Glauber dynamics for the Sherrington-Kirkpatrick model at every fixed inverse temperature when the external field is sufficiently large.

Fri 16 OctData Structures and Algorithms
The gist
This work looks at how quickly a certain process called Glauber dynamics mixes or settles down in Ising models, which are mathematical ways to study interacting spins (values that can be +1 or -1). The authors focus on cases where there is already a large majority of +1 spins, showing conditions under which the system mixes rapidly within this phase. They also extend their results to important models like the Sherrington-Kirkpatrick model when an external field is large enough. These findings help improve methods for sampling and understanding spin systems in statistical physics and related data problems.
Open → 2610.23777v1