Understanding the parameter estimation of softmax gating Gaussian mixture of experts has
remained a long-standing open problem in the literature. It is mainly due to three …

Estimating the number of components in finite mixture models via the Group-Sort-Fuse
procedure Page 1 The Annals of Statistics 2021, Vol. 49, No. 6, 3043–3069 https://doi.org/10.1214/21-AOS2072 …

Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit (WPP), is a
robust variant of the Wasserstein distance. Recent work suggests that this quantity is more …

The Wasserstein distance has become increasingly important in machine learning and deep
learning. Despite its popularity, the Wasserstein distance is hard to approximate because of …

As machine learning models in critical fields increasingly grapple with multimodal data, they
face the dual challenges of handling a wide array of modalities, often incomplete due to …

Strong identifiability and optimal minimax rates for finite mixture estimation Page 1 The Annals
of Statistics 2018, Vol. 46, No. 6A, 2844–2870 https://doi.org/10.1214/17-AOS1641 © Institute …

Originally introduced as a neural network for ensemble learning, mixture of experts (MoE)
has recently become a fundamental building block of highly successful modern deep neural …

We analyze the classical EM algorithm for parameter estimation in the symmetric two-
component Gaussian mixtures in d dimensions. We show that, even in the absence of any …

We study the convergence rates of the EM algorithm for learning two-component mixed
linear regression under all regimes of signal-to-noise ratio (SNR). We resolve a long …

Dense-to-sparse gating mixture of experts (MoE) has recently become an effective
alternative to a well-known sparse MoE. Rather than fixing the number of activated experts …