Imagen de Portada

Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yao, Yunzhen, He, Lie, Gastpar, Michael
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Non-Asymptotic Analysis of Efficiency in Conformalized Regression
por: Yao, Yunzhen, et al.
Publicado: (2025)

PILAF: Optimal Human Preference Sampling for Reward Modeling
por: Feng, Yunzhen, et al.
Publicado: (2025)

zip2zip: Inference-Time Adaptive Tokenization via Online Compression
por: Geng, Saibo, et al.
Publicado: (2025)

Block-Sample MAC-Bayes Generalization Bounds
por: Frey, Matthias, et al.
Publicado: (2026)

The Conditional Regret-Capacity Theorem for Batch Universal Prediction
por: Bondaschi, Marco, et al.
Publicado: (2025)

Batch Universal Prediction
por: Bondaschi, Marco, et al.
Publicado: (2024)

Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity
por: Muslimani, Calarina, et al.
Publicado: (2024)

Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization
por: Yao, Yunzhen, et al.
Publicado: (2026)

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
por: Huang, Weizhong, et al.
Publicado: (2025)

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
por: Feng, Yunzhen, et al.
Publicado: (2025)

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models
por: An, Tai, et al.
Publicado: (2025)

Information Theoretic Perspective on Representation Learning
por: Pereg, Deborah, et al.
Publicado: (2026)

Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning
por: Ghosh, Udita, et al.
Publicado: (2025)

Which Algorithms Have Tight Generalization Bounds?
por: Gastpar, Michael, et al.
Publicado: (2024)

Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference
por: Mukherji, Rishav, et al.
Publicado: (2023)

DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
por: He, Yunzhen, et al.
Publicado: (2025)

Sampling Foundational Transformer: A Theoretical Perspective
por: Nguyen, Viet Anh, et al.
Publicado: (2024)

The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective
por: Muehlebach, Michael, et al.
Publicado: (2025)

Random Projections and Natural Sparsity in Time-Series Classification: A Theoretical Analysis
por: Marco-Blanco, Jorge, et al.
Publicado: (2025)

Sparsity Forcing: Reinforcing Token Sparsity of MLLMs
por: Chen, Feng, et al.
Publicado: (2025)

Multi-Task Learning for Sparsity Pattern Heterogeneity: Statistical and Computational Perspectives
por: Behdin, Kayhan, et al.
Publicado: (2022)

The Fundamental Limits of Least-Privilege Learning
por: Stadler, Theresa, et al.
Publicado: (2024)

Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards
por: Metcalf, Katherine, et al.
Publicado: (2024)

Learning Parametric Distributions from Samples and Preferences
por: Jourdan, Marc, et al.
Publicado: (2025)

Batch Normalization Decomposed
por: Nachum, Ido, et al.
Publicado: (2024)

Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences
por: Liu, Ziang, et al.
Publicado: (2024)

Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors
por: Shehab, Mohamad Louai, et al.
Publicado: (2025)

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
por: Deng, Junze, et al.
Publicado: (2025)

Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
por: Yao, Xinhao, et al.
Publicado: (2024)

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
por: Zhang, Yue, et al.
Publicado: (2026)

Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspective
por: Zeulin, Nikita, et al.
Publicado: (2026)

Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
por: Wang, Jiuqi, et al.
Publicado: (2026)

Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
por: Arnob, Samin Yeasar, et al.
Publicado: (2025)

Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity
por: Zhao, Jinze, et al.
Publicado: (2024)

Model Collapse Demystified: The Case of Regression
por: Dohmatob, Elvis, et al.
Publicado: (2024)

A Sparsity Principle for Partially Observable Causal Representation Learning
por: Xu, Danru, et al.
Publicado: (2024)

Active Preference Optimization for Sample Efficient RLHF
por: Das, Nirjhar, et al.
Publicado: (2024)

Strong Model Collapse
por: Dohmatob, Elvis, et al.
Publicado: (2024)

Sparsity via Hyperpriors: A Theoretical and Algorithmic Study under Empirical Bayes Framework
por: Li, Zhitao, et al.
Publicado: (2025)

CiTrus: Squeezing Extra Performance out of Low-data Bio-signal Transfer Learning
por: Geenjaar, Eloy, et al.
Publicado: (2024)