Imagen de Portada

From Recency Bias to Stable Convergence Block Kaczmarz Methods for Online Preference Learning in Matchmaking Applications

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Nguyen, James
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM
por: Nguyen, Son, et al.
Publicado: (2026)

Measuring Recency Bias In Sequential Recommendation Systems
por: Oh, Jeonglyul, et al.
Publicado: (2024)

LayerNorm Induces Recency Bias in Transformer Decoders
por: Kim, Junu, et al.
Publicado: (2025)

Randomized Kaczmarz Methods with Beyond-Krylov Convergence
por: Dereziński, Michał, et al.
Publicado: (2025)

Online Distribution Shift Detection via Recency Prediction
por: Luo, Rachel, et al.
Publicado: (2022)

Demystifying the Recency Heuristic in Temporal-Difference Learning
por: Daley, Brett, et al.
Publicado: (2024)

Linear Discriminant Analysis with the Randomized Kaczmarz Method
por: Chi, Jocelyn T., et al.
Publicado: (2022)

Worth Their Weight: Randomized and Regularized Block Kaczmarz Algorithms without Preprocessing
por: Goldshlager, Gil, et al.
Publicado: (2025)

Matchmaker: Self-Improving Large Language Model Programs for Schema Matching
por: Seedat, Nabeel, et al.
Publicado: (2024)

Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size
por: Dereziński, Michał, et al.
Publicado: (2026)

Re3: Learning to Balance Relevance & Recency for Temporal Information Retrieval
por: Cao, Jiawei, et al.
Publicado: (2025)

Recency-Weighted Temporally-Segmented Ensemble for Time-Series Modeling
por: Johnsen, Pål V., et al.
Publicado: (2024)

Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration
por: Bose, Avinandan, et al.
Publicado: (2024)

Recency Biased Causal Attention for Time-series Forecasting
por: Hegazy, Kareem, et al.
Publicado: (2025)

Kaczmarz Linear Attention
por: Zou, Jiaxuan, et al.
Publicado: (2026)

Active Learning for Fair and Stable Online Allocations
por: Bhattacharya, Riddhiman, et al.
Publicado: (2024)

Coverage Improvement and Fast Convergence of On-policy Preference Learning
por: Kim, Juno, et al.
Publicado: (2026)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
por: Wang, Peihao, et al.
Publicado: (2024)

Last Iterate Convergence of Incremental Methods and Applications in Continual Learning
por: Cai, Xufeng, et al.
Publicado: (2024)

Online Learning Guided Quasi-Newton Methods with Global Non-Asymptotic Convergence
por: Jiang, Ruichen, et al.
Publicado: (2024)

Online Policy Learning from Offline Preferences
por: Zhang, Guoxi, et al.
Publicado: (2024)

Debiasing Online Preference Learning via Preference Feature Preservation
por: Kim, Dongyoung, et al.
Publicado: (2025)

Infinite-Dimensional Operator/Block Kaczmarz Algorithms: Regret Bounds and $λ$-Effectiveness
por: Jeong, Halyun, et al.
Publicado: (2025)

From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
por: Zhu, Mingkang, et al.
Publicado: (2025)

Expert with Clustering: Hierarchical Online Preference Learning Framework
por: Zhou, Tianyue, et al.
Publicado: (2024)

Metric Learning to Accelerate Convergence of Operator Splitting Methods for Differentiable Parametric Programming
por: King, Ethan, et al.
Publicado: (2024)

Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings
por: Badran, Yahya, et al.
Publicado: (2025)

DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback
por: Xiong, Guojun, et al.
Publicado: (2024)

Solving Freshness in RAG: A Simple Recency Prior and the Limits of Heuristic Trend Detection
por: Grofsky, Matthew
Publicado: (2025)

Convergence Guarantees for the DeepWalk Embedding on Block Models
por: Harker, Christopher, et al.
Publicado: (2024)

Online Bandit Learning with Offline Preference Data for Improved RLHF
por: Agnihotri, Akhil, et al.
Publicado: (2024)

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
por: Vyas, Nikhil, et al.
Publicado: (2023)

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
por: Nguyen, Tien-Phat, et al.
Publicado: (2026)

Spectral Souping: A Unified Framework for Online Preference Alignment
por: Chow, Yinlam, et al.
Publicado: (2026)

Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency
por: Deldjoo, Yashar
Publicado: (2024)

Advances in Protein Representation Learning: Methods, Applications, and Future Directions
por: Nguyen, Viet Thanh Duy, et al.
Publicado: (2025)

Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling
por: Cai, Jianfeng, et al.
Publicado: (2025)

Contextual Online Uncertainty-Aware Preference Learning for Human Feedback
por: Lu, Nan, et al.
Publicado: (2025)

Ballistic Convergence in Hit-and-Run Monte Carlo and a Coordinate-free Randomized Kaczmarz Algorithm
por: Bou-Rabee, Nawaf, et al.
Publicado: (2024)

Online Self-Preferring Language Models
por: Zhai, Yuanzhao, et al.
Publicado: (2024)