Imagen de Portada

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rezaei, Parham, Farnia, Farzan, Li, Cheuk Ting
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?
por: Nia, Bahar Dibaei, et al.
Publicado: (2026)

DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
por: Jafari, Donya, et al.
Publicado: (2026)

PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs
por: Hu, Xiaoyan, et al.
Publicado: (2024)

An Interpretable Evaluation of Entropy-based Novelty of Generative Models
por: Zhang, Jingwei, et al.
Publicado: (2024)

On the Hardness of Sampling from Mixture Distributions via Langevin Dynamics
por: Cheng, Xiwei, et al.
Publicado: (2024)

Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error
por: Farnia, Farzan, et al.
Publicado: (2026)

Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
por: Zhang, Jingwei, et al.
Publicado: (2024)

A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models
por: Hu, Xiaoyan, et al.
Publicado: (2024)

SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
por: Jalali, Mohammad, et al.
Publicado: (2025)

Clus-UCB: A Near-Optimal Algorithm for Clustered Bandits
por: Gore, Aakash, et al.
Publicado: (2025)

Conditional Vendi Score: An Information-Theoretic Approach to Diversity Evaluation of Prompt-based Generative Models
por: Jalali, Mohammad, et al.
Publicado: (2024)

Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms
por: Tatlı, Meltem, et al.
Publicado: (2025)

Certified Adversarial Robustness via Partition-based Randomized Smoothing
por: Goli, Hossein, et al.
Publicado: (2024)

Sparse Domain Transfer via Elastic Net Regularization
por: Zhang, Jingwei, et al.
Publicado: (2024)

Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms
por: Tatlı, Meltem, et al.
Publicado: (2025)

Stability and Generalization in Free Adversarial Training
por: Cheng, Xiwei, et al.
Publicado: (2024)

Do Vendi Scores Converge with Finite Samples? Truncated Vendi Score for Finite-Sample Convergence Guarantees
por: Ospanov, Azim, et al.
Publicado: (2024)

The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning
por: Wu, Youqi, et al.
Publicado: (2026)

On the Inductive Biases of Demographic Parity-based Fair Learning Algorithms
por: Lei, Haoyu, et al.
Publicado: (2024)

A UCB Bandit Algorithm for General ML-Based Estimators
por: Liu, Yajing, et al.
Publicado: (2026)

Mixture of Diverse Size Experts
por: Sun, Manxi, et al.
Publicado: (2024)

Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis
por: Paschalidis, Phevos, et al.
Publicado: (2024)

PromptSplit: Revealing Prompt-Level Disagreement in Generative Models
por: Lotfian, Mehdi, et al.
Publicado: (2026)

Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability
por: Ye, Zhuorui, et al.
Publicado: (2024)

pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning
por: Lei, Haoyu, et al.
Publicado: (2025)

Replicable Bandits with UCB based Exploration
por: Deb, Rohan, et al.
Publicado: (2026)

On the Distributed Evaluation of Generative Models
por: Wang, Zixiao, et al.
Publicado: (2023)

Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
por: Najafi, Amir, et al.
Publicado: (2024)

When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
por: Wu, Youqi, et al.
Publicado: (2025)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
por: Li, Long-Fei, et al.
Publicado: (2024)

Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation
por: Lei, Haoyu, et al.
Publicado: (2025)

PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models
por: Hu, Xiaoyan, et al.
Publicado: (2025)

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

An Information Theoretic Approach to Interaction-Grounded Learning
por: Hu, Xiaoyan, et al.
Publicado: (2024)

Truncated LinUCB for Stochastic Linear Bandits
por: Song, Yanglei, et al.
Publicado: (2022)

Mixture Compressor for Mixture-of-Experts LLMs Gains More
por: Huang, Wei, et al.
Publicado: (2024)

Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
por: Flynn, Hamish, et al.
Publicado: (2023)

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
por: Oskouie, Haniyeh Ehsani, et al.
Publicado: (2022)

Extended UCB Policies for Multi-armed Bandit Problems
por: Liu, Keqin, et al.
Publicado: (2011)

Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits
por: Bui, Ha Manh, et al.
Publicado: (2024)