中文
相关论文

相关论文: On Minimax Estimation of Parameters in Softmax-Con…

200 篇论文

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…

机器学习 · 统计学 2025-03-06 Huy Nguyen , Nhat Ho , Alessandro Rinaldo

We conduct the convergence analysis of parameter estimation in the contaminated mixture of experts. This model is motivated from the prompt learning problem where ones utilize prompts, which can be formulated as experts, to fine-tune a…

机器学习 · 计算机科学 2025-03-07 Fanqi Yan , Huy Nguyen , Dung Le , Pedram Akbarian , Nhat Ho

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…

机器学习 · 统计学 2024-06-25 Huy Nguyen , Nhat Ho , Alessandro Rinaldo

Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task.…

统计理论 · 数学 2026-02-03 Fanqi Yan , Dung Le , Trang Pham , Huy Nguyen , Nhat Ho

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…

机器学习 · 统计学 2024-06-25 Huy Nguyen , Pedram Akbarian , TrungTin Nguyen , Nhat Ho

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…

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 as in the latter model, which could limit the investigation of…

机器学习 · 统计学 2024-06-25 Huy Nguyen , Pedram Akbarian , Nhat Ho

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…

机器学习 · 统计学 2023-10-31 Huy Nguyen , TrungTin Nguyen , Nhat Ho

Mixture of experts (MoE), introduced over 20 years ago, is the simplest gated modular neural network architecture. There is renewed interest in MoE because the conditional computation allows only parts of the network to be used during each…

机器学习 · 计算机科学 2023-03-01 Yamuna Krishnamurthy , Chris Watkins , Thomas Gaertner

We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance. Our model exhibits an interpretable gating…

机器学习 · 计算机科学 2021-01-15 Melanie F. Pradier , Javier Zazo , Sonali Parbhoo , Roy H. Perlis , Maurizio Zazzi , Finale Doshi-Velez

Mixtures-of-Experts (MoE) are conditional mixture models that have shown their performance in modeling heterogeneity in data in many statistical learning approaches for prediction, including regression and classification, as well as for…

统计方法学 · 统计学 2019-07-17 Bao Tuyen Huynh , Faicel Chamroukhi

With the growing prominence of the Mixture of Experts (MoE) architecture in developing large-scale foundation models, we investigate the Hierarchical Mixture of Experts (HMoE), a specialized variant of MoE that excels in handling complex…

机器学习 · 统计学 2025-03-10 Huy Nguyen , Xing Han , Carl Harris , Suchi Saria , Nhat Ho

The Mixture-of-Experts (MoE) model uses a set of expert networks that specialize on subsets of a dataset under the supervision of a gating network. A common issue in MoE architectures is ``expert collapse'' where overlapping class…

神经与进化计算 · 计算机科学 2026-03-31 Abien Fred Agarap , Arnulfo P. Azcarraga

Mixture-of-Experts (MoE) architectures have emerged as a cornerstone of modern AI systems. In particular, MoEs route inputs dynamically to specialized experts whose outputs are aggregated through weighted summation. Despite their widespread…

机器学习 · 计算机科学 2025-10-09 Fangshuo Liao , Anastasios Kyrillidis

Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert models through an input-dependent gating mechanism. These models have become increasingly…

机器学习 · 统计学 2026-04-23 Nicola Bariletto , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges at scale due to the…

计算与语言 · 计算机科学 2023-09-12 Ted Zadouri , Ahmet Üstün , Arash Ahmadian , Beyza Ermiş , Acyr Locatelli , Sara Hooker

The softmax gating function is arguably the most popular choice in mixture of experts modeling. Despite its widespread use in practice, the softmax gating may lead to unnecessary competition among experts, potentially causing the…

机器学习 · 统计学 2024-11-05 Huy Nguyen , Nhat Ho , Alessandro Rinaldo

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…

The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small experts. The hope is that if the total parameter count of the…

机器学习 · 计算机科学 2024-09-04 Youngseog Chung , Dhruv Malik , Jeff Schneider , Yuanzhi Li , Aarti Singh

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…

机器学习 · 统计学 2024-02-12 Huy Nguyen , TrungTin Nguyen , Khai Nguyen , Nhat Ho
‹ 上一页 1 2 3 10 下一页 ›