arXiv Machine Learning June 9, 2026 By Do Tien Hai, Trung Nguyen Mai, TrungTin Nguyen, Nhat Ho, Binh T. Nguyen, Christopher Drovandi

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps

Read the original on arXiv Machine Learning →

arXiv:2510. 12744v2 Announce Type: replace-cross Abstract: We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model selection: (i) non-identifiability of gating parameters up to common translations, (ii) intrinsic gate-expert interactions that induce coupled differential relations in the likelihood, and (iii) the tight numerator-denominator coupling in the softmax-induced conditional density.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 7

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

arXiv:2607. 03809v1 Announce Type: new Abstract: Normalising flows provide a powerful variational family for approximate inference, yet individual architectures often fail to generalise across heterogeneous posterior geometries.

By Benjamin Wiriyapong, Oktay Karakus, Can Eyupoglu, Kirill Sidorov

multimodal benchmarks

arXiv Machine Learning

Jul 7

Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models

arXiv:2607. 04360v1 Announce Type: cross Abstract: Conditional generative models have emerged as powerful tools for sampling from target conditional distributions, driving substantial advances across a wide range of scientific and applied domains.

By Shijin Gong, Baihua He, Xinyu Zhang

arXiv Machine Learning

Jul 2

Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation

arXiv:2606. 25169v2 Announce Type: replace-cross Abstract: Sampling from an unnormalized target by reversing an Ornstein-Uhlenbeck diffusion requires the score of each noise-perturbed marginal.

By Alois Duston, Tan Bui-Thanh

diffusion benchmarks

arXiv Machine Learning

Jun 25

Laplace--Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation

arXiv:2606. 25169v1 Announce Type: cross Abstract: Sampling from an unnormalized target by reversing an Ornstein--Uhlenbeck diffusion requires the score of each noise-perturbed marginal.

By Alois Duston, Tan Bui Tanh

diffusion benchmarks

arXiv Machine Learning

Jun 5

Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning

arXiv:2605. 27991v2 Announce Type: replace-cross Abstract: Gradient-flow optimization is usually viewed as an algorithmic procedure for minimizing empirical loss, with training duration selected by validation or heuristic early-stopping rules.

By Minhao Yao, Ruoyu Wang, Xihong Lin, Lin Liu, Zhonghua Liu

arXiv Machine Learning

Jul 28

A Multi-stage Constrained Optimization Framework for Data-driven Problems

arXiv:2607. 23480v1 Announce Type: new Abstract: Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable.

By Ye Shi

diffusion safety

Related stories

Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average

Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models

Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation

Laplace--Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation

Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning

A Multi-stage Constrained Optimization Framework for Data-driven Problems