Cover Image

Statistical Advantages of Perturbing Cosine Router in Mixture of Experts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Huy, Akbarian, Pedram, Pham, Trang, Nguyen, Trang, Zhang, Shujian, Ho, Nhat
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
by: Nguyen, Huy, et al.
Published: (2024)

Quadratic Gating Mixture of Experts: Statistical Insights into Self-Attention
by: Akbarian, Pedram, et al.
Published: (2024)

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2023)

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2023)

Mixture of Experts Meets Prompt-Based Continual Learning
by: Le, Minh, et al.
Published: (2024)

Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts
by: Yan, Fanqi, et al.
Published: (2024)

Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity
by: Yan, Fanqi, et al.
Published: (2026)

On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
by: Yan, Fanqi, et al.
Published: (2025)

Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective
by: Yan, Fanqi, et al.
Published: (2025)

On Parameter Estimation in Deviated Gaussian Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2024)

Convergence Rates for Softmax Gating Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2025)

On Least Square Estimation in Softmax Gating Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2024)

A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
by: Nguyen, Viet, et al.
Published: (2026)

Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2023)

Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2024)

Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning
by: Nguyen, Trang, et al.
Published: (2024)

Rethinking Multinomial Logistic Mixture of Experts with Sigmoid Gating Function
by: Pham, Tuan Minh, et al.
Published: (2026)

On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions
by: Nguyen, Huy, et al.
Published: (2024)

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
by: Han, Xing, et al.
Published: (2024)

On Bayesian Softmax-Gated Mixture-of-Experts Models
by: Bariletto, Nicola, et al.
Published: (2026)

RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts
by: Truong, Tuan, et al.
Published: (2025)

One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
by: Le, Minh, et al.
Published: (2025)

On DeepSeekMoE: Statistical Benefits of Shared Experts and Normalized Sigmoid Gating
by: Nguyen, Huy, et al.
Published: (2025)

CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition
by: Pham, Quang, et al.
Published: (2024)

Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder
by: Nguyen, Duy A., et al.
Published: (2023)

Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts
by: Le, Minh, et al.
Published: (2025)

Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
by: Le, Minh, et al.
Published: (2024)

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition
by: Nguyen, Nam V., et al.
Published: (2025)

Sliced Wasserstein with Random-Path Projecting Directions
by: Nguyen, Khai, et al.
Published: (2024)

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps
by: Hai, Do Tien, et al.
Published: (2025)

Robust Explainer Recommendation for Time Series Classification
by: Nguyen, Thu Trang, et al.
Published: (2023)

Optimal Transport Aggregation for Distributed Mixture-of-Experts
by: Chamroukhi, Faïcel, et al.
Published: (2023)

Tree-Sliced Wasserstein Distance: A Geometric Perspective
by: Tran, Viet-Hoang, et al.
Published: (2024)

Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures
by: Nguyen-Nhat, Minh-Khoi, et al.
Published: (2025)

Model Selection for Gaussian-gated Gaussian Mixture of Experts Using Dendrograms of Mixing Measures
by: Thai, Tuan, et al.
Published: (2025)

Lightspeed Geometric Dataset Distance via Sliced Optimal Transport
by: Nguyen, Khai, et al.
Published: (2025)

Expert Merging in Sparse Mixture of Experts with Nash Bargaining
by: Nguyen, Dung V., et al.
Published: (2025)

Load Balancing Mixture of Experts with Similarity Preserving Routers
by: Omi, Nabil, et al.
Published: (2025)

Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances
by: Nguyen, Khai, et al.
Published: (2025)

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
by: Lv, Ang, et al.
Published: (2025)