Image de couverture de livre

Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yan, Fanqi, Le, Dung, Pham, Trang, Nguyen, Huy, Ho, Nhat
Format:	Preprint
Publié:	2026
Sujets:	Statistics Theory Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts
par: Yan, Fanqi, et autres
Publié: (2024)

On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
par: Yan, Fanqi, et autres
Publié: (2025)

Fast Model Selection and Stable Optimization for Softmax-Gated Multinomial-Logistic Mixture of Experts Models
par: Tran, TrungKhang, et autres
Publié: (2026)

Rethinking Multinomial Logistic Mixture of Experts with Sigmoid Gating Function
par: Pham, Tuan Minh, et autres
Publié: (2026)

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2023)

Mixture of Experts Meets Prompt-Based Continual Learning
par: Le, Minh, et autres
Publié: (2024)

Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2024)

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2023)

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
par: Boudart, Pierre, et autres
Publié: (2026)

Convergence Rates for Softmax Gating Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2025)

On Parameter Estimation in Deviated Gaussian Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2024)

Model Selection for Gaussian-gated Gaussian Mixture of Experts Using Dendrograms of Mixing Measures
par: Thai, Tuan, et autres
Publié: (2025)

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps
par: Hai, Do Tien, et autres
Publié: (2025)

Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2023)

Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm
par: Boudart, Pierre, et autres
Publié: (2025)

On Least Square Estimation in Softmax Gating Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2024)

Minimax Statistical Estimation under Wasserstein Contamination
par: Chao, Patrick, et autres
Publié: (2023)

On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions
par: Nguyen, Huy, et autres
Publié: (2024)

Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective
par: Yan, Fanqi, et autres
Publié: (2025)

Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
par: Nguyen, Huy, et autres
Publié: (2024)

Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression
par: Ni, Yijin, et autres
Publié: (2026)

RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts
par: Truong, Tuan, et autres
Publié: (2025)

Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
par: Nguyen, Huy, et autres
Publié: (2024)

Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts
par: Tran, TrungKhang, et autres
Publié: (2026)

Quadratic Gating Mixture of Experts: Statistical Insights into Self-Attention
par: Akbarian, Pedram, et autres
Publié: (2024)

Generalization and Scaling Laws for Mixture-of-Experts Transformers
par: Mayaki, Mansour Zoubeirou a
Publié: (2026)

Bayesian Mixture-of-Experts: Towards Making LLMs Know What They Don't Know
par: Li, Albus Yizhuo
Publié: (2025)

Minimax Regret Learning for Data with Heterogeneous Subgroups
par: Mo, Weibin, et autres
Publié: (2024)

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
par: Han, Xing, et autres
Publié: (2024)

A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
par: Nguyen, Viet, et autres
Publié: (2026)

Robust Estimation Under Heterogeneous Corruption Rates
par: Chaudhuri, Syomantak, et autres
Publié: (2025)

On Bayesian Softmax-Gated Mixture-of-Experts Models
par: Bariletto, Nicola, et autres
Publié: (2026)

High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch
par: Liautaud, Paul, et autres
Publié: (2026)

One-Prompt Strikes Back: Sparse Mixture of Experts for Prompt-based Continual Learning
par: Le, Minh, et autres
Publié: (2025)

Convergence Rates for Latent Mixing Measures in Infinite Homoscedastic Location-Scale Mixture Models
par: Bariletto, Nicola, et autres
Publié: (2026)

Minimax Rate-Optimal Algorithms for High-Dimensional Stochastic Linear Bandits
par: Liu, Jingyu, et autres
Publié: (2025)

Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
par: Genans, Ferdinand, et autres
Publié: (2025)

Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity
par: Banerjee, Imon, et autres
Publié: (2022)

Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
par: Cai, T. Tony, et autres
Publié: (2026)

Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
par: Zucker, Shai, et autres
Publié: (2025)