paper-with-me

홈 › Papers

Mixture of Raytraced Experts

2025-07-16 · Andrea Perin, Giacomo Lagomarsini, Claudio Gallicchio, Giuseppe Nuti arxiv

We introduce a Mixture of Raytraced Experts, a stacked Mixture of Experts (MoE) architecture which can dynamically select sequences of experts, producing computational graphs of variable width and depth. Existing MoE architectures generally require a fixed amount of computation for a given sample. Our approach, in contrast, yields predictions with increasing accuracy as the computation cycles through the experts' sequence. We train our model by iteratively sampling from a set of candidate experts, unfolding the sequence akin to how Recurrent Neural Networks are trained. Our method does not require load-balancing mechanisms, and preliminary experiments show a reduction in training epochs of 10\% to 40\% with a comparable/higher accuracy. These results point to new research directions in the field of MoEs, allowing the design of potentially faster and more expressive models. The code is available at https://github.com/nutig/RayTracing

📄 PDF Abstract BibTeX arXiv:2507.12419

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generative Adversarial Networks for Non-Raytraced Global Illumination on Older GPU Hardware

2021-10-22 · Jared Harris-Dewey, Richard Klein

We give an overview of the different rendering methods and we demonstrate that the use of a Generative Adversarial Networks (GAN) for Global Illumination (GI) gives a superior quality rendered image to that of a rasteris…

GPU

Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction

2024-06-24 · Bruce Rushing

Mixture of experts is a prediction aggregation method in machine learning that aggregates the predictions of specialized experts. This method often outperforms Bayesian methods despite the Bayesian having stronger induct…

Mixture-of-Experts

Learning Factored Representations in a Deep Mixture of Experts

2013-12-16 · David Eigen, Marc'Aurelio Ranzato, Ilya Sutskever

Mixtures of Experts combine the outputs of several "expert" networks, each of which specializes in a different part of the input space. This is achieved by training a "gating" network that maps each input to a distributi…

Mixture-of-Experts

Horseshoe Mixtures-of-Experts (HS-MoE)

2026-01-14 · Nick Polson, Vadim Sokolov arxiv

Horseshoe mixtures-of-experts (HS-MoE) models provide a Bayesian framework for sparse expert selection in mixture-of-experts architectures. We combine the horseshoe prior's adaptive global-local shrinkage with input-depe…

Tighter Risk Bounds for Mixtures of Experts

2024-10-14 · Wissam Akretche, Frédéric LeBlanc, Mario Marchand

In this work, we provide upper bounds on the risk of mixtures of experts by imposing local differential privacy (LDP) on their gating mechanism. These theoretical guarantees are tailored to mixtures of experts that utili…