English
Related papers

Related papers: Is Temperature Sample Efficient for Softmax Gaussi…

200 papers

Mixture-of-experts (MoE) model incorporates the power of multiple submodels via gating functions to achieve greater performance in numerous regression and classification applications. From a theoretical perspective, while there have been…

Machine Learning · Statistics 2024-06-25 Huy Nguyen , Pedram Akbarian , TrungTin Nguyen , Nhat Ho

Mixture of experts (MoE) has recently emerged as an effective framework to advance the efficiency and scalability of machine learning models by softly dividing complex tasks among multiple specialized sub-models termed experts. Central to…

Machine Learning · Statistics 2025-03-06 Huy Nguyen , Nhat Ho , Alessandro Rinaldo

Mixture of experts (MoE) model is a statistical machine learning design that aggregates multiple expert networks using a softmax gating function in order to form a more intricate and expressive model. Despite being commonly used in several…

Machine Learning · Statistics 2024-06-25 Huy Nguyen , Nhat Ho , Alessandro Rinaldo

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 fundamental theoretical challenges associated with the softmax…

Machine Learning · Statistics 2023-10-31 Huy Nguyen , TrungTin Nguyen , Nhat Ho

The softmax-contaminated mixture of experts (MoE) model is deployed when a large-scale pre-trained model, which plays the role of a fixed expert, is fine-tuned for learning downstream tasks by including a new contamination part, or prompt,…

Machine Learning · Statistics 2025-11-25 Fanqi Yan , Huy Nguyen , Dung Le , Pedram Akbarian , Nhat Ho , Alessandro Rinaldo

Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive deep-learning architectures without increasing the computational cost. Despite its popularity in real-world applications, the theoretical…

Machine Learning · Statistics 2024-02-27 Huy Nguyen , Pedram Akbarian , Fanqi Yan , Nhat Ho

Mixture-of-experts (MoE) is becoming popular due to its success in improving the model quality, especially in Transformers. By routing tokens with a sparse gate to a few experts (i.e., a small pieces of the full model), MoE can easily…

Machine Learning · Computer Science 2022-10-11 Xiaonan Nie , Xupeng Miao , Shijie Cao , Lingxiao Ma , Qibin Liu , Jilong Xue , Youshan Miao , Yi Liu , Zhi Yang , Bin Cui

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 networks for heterogeneous data analysis in several…

Machine Learning · Statistics 2024-02-12 Huy Nguyen , TrungTin Nguyen , Khai Nguyen , Nhat Ho

The sigmoid gate in mixture-of-experts (MoE) models has been empirically shown to outperform the softmax gate across several tasks, ranging from approximating feed-forward networks to language modeling. Additionally, recent efforts have…

Machine Learning · Statistics 2026-02-03 Tuan Minh Pham , Thinh Cao , Viet Nguyen , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

Mixture of Experts (MoE) models constitute a widely utilized class of ensemble learning approaches in statistics and machine learning, known for their flexibility and computational efficiency. They have become integral components in…

Machine Learning · Statistics 2025-05-26 Tuan Thai , TrungTin Nguyen , Dat Do , Nhat Ho , Christopher Drovandi

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…

Machine Learning · Statistics 2025-10-15 Do Tien Hai , Trung Nguyen Mai , TrungTin Nguyen , Nhat Ho , Binh T. Nguyen , Christopher Drovandi

Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to…

Machine Learning · Computer Science 2024-05-28 Joan Puigcerver , Carlos Riquelme , Basil Mustafa , Neil Houlsby

Mixture-of-Experts (MoE) represents an ensemble methodology that amalgamates predictions from several specialized sub-models (referred to as experts). This fusion is accomplished through a router mechanism, dynamically assigning weights to…

Machine Learning · Computer Science 2024-03-27 Jinze Zhao , Peihao Wang , Zhangyang Wang

In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE models. For each expert, we rank parameters by the magnitude…

Computation and Language · Computer Science 2025-10-08 Runxi Cheng , Yuchen Guan , Yucheng Ding , Qingguo Hu , Yongxian Wei , Chun Yuan , Yelong Shen , Weizhu Chen , Yeyun Gong

Mixture-of-Experts (MoE) architectures combine specialized predictors through a learned gate and are effective across regression and classification, but for classification with softmax multinomial-logistic gating, rigorous guarantees for…

Machine Learning · Statistics 2026-02-10 TrungKhang Tran , TrungTin Nguyen , Md Abul Bashar , Nhat Ho , Richi Nayak , Christopher Drovandi

Traditional multi-task learning (MTL) methods use dense networks that use the same set of shared weights across several different tasks. This often creates interference where two or more tasks compete to pull model parameters in different…

Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are…

Machine Learning · Computer Science 2024-05-27 Yuanhang Yang , Shiyi Qi , Wenchao Gu , Chaozheng Wang , Cuiyun Gao , Zenglin Xu

Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling. We study an iso-parameter regime where inputs exhibit latent modular structure but are…

Machine Learning · Computer Science 2026-01-22 Dong Sun , Rahul Nittala , Rebekka Burkholz

Mixture-of-Experts (MoE) architectures enable conditional computation by routing inputs to multiple expert subnetworks and are often motivated as a mechanism for scaling large language models. In this project, we instead study MoE behavior…

Machine Learning · Computer Science 2026-01-22 Adam Rokah , Daniel Veress , Caleb Caulk , Sourav Sharan

While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-20 Ye Bai , Jie Li , Wenjing Han , Hao Ni , Kaituo Xu , Zhuo Zhang , Cheng Yi , Xiaorui Wang
‹ Prev 1 2 3 10 Next ›