Imagen de Portada

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Javanmard, Adel, Das, Rudrajit, Epasto, Alessandro, Mirrokni, Vahab
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Statistics Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Retraining with Predicted Hard Labels Provably Increases Model Accuracy
por: Das, Rudrajit, et al.
Publicado: (2024)

Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
por: Javanmard, Adel, et al.
Publicado: (2024)

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
por: Tao, Yuxuan, et al.
Publicado: (2025)

Mixed Regression via Approximate Message Passing
por: Tan, Nelvin, et al.
Publicado: (2023)

PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
por: Javanmard, Adel, et al.
Publicado: (2024)

Optimal Approximation -- Smoothness Tradeoffs for Soft-Max Functions
por: Epasto, Alessandro, et al.
Publicado: (2020)

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
por: Hassani, Hamed, et al.
Publicado: (2022)

Inferring Change Points in High-Dimensional Regression via Approximate Message Passing
por: Arpino, Gabriel, et al.
Publicado: (2024)

Orthogonal Approximate Message Passing with Optimal Spectral Initializations for Rectangular Spiked Matrix Models
por: Chen, Haohua, et al.
Publicado: (2025)

Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing
por: Zhang, Yihan, et al.
Publicado: (2023)

Understanding the Role of Training Data in Test-Time Scaling
por: Javanmard, Adel, et al.
Publicado: (2025)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
por: Javanmard, Adel, et al.
Publicado: (2026)

Optimality of Approximate Message Passing Algorithms for Spiked Matrix Models with Rotationally Invariant Noise
por: Dudeja, Rishabh, et al.
Publicado: (2024)

On Universality of Non-Separable Approximate Message Passing Algorithms
por: Lovig, Max, et al.
Publicado: (2025)

Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
por: Zhang, Yihan, et al.
Publicado: (2026)

Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
por: Lovig, Max
Publicado: (2026)

Improving the Variance of Differentially Private Randomized Experiments through Clustering
por: Javanmard, Adel, et al.
Publicado: (2023)

Multi-Environment GLAMP: Approximate Message Passing for Transfer Learning with Applications to Lasso-based Estimators
por: Wang, Longlin, et al.
Publicado: (2025)

Orthogonal Approximate Message Passing Algorithms for Rectangular Spiked Matrix Models with Rotationally Invariant Noise
por: Chen, Haohua, et al.
Publicado: (2026)

Learning Rate Schedules in the Presence of Distribution Shift
por: Fahrbach, Matthew, et al.
Publicado: (2023)

Optimistic Rates for Learning from Label Proportions
por: Li, Gene, et al.
Publicado: (2024)

Less is More: Convergence Benefits of Fewer Data Weight Updates over Longer Horizon
por: Das, Rudrajit, et al.
Publicado: (2026)

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
por: Epasto, Alessandro, et al.
Publicado: (2022)

Differentially Private Synthetic Data Release for Topics API Outputs
por: Dick, Travis, et al.
Publicado: (2025)

P-Tensors: a General Formalism for Constructing Higher Order Message Passing Networks
por: Hands, Andrew, et al.
Publicado: (2023)

Procurement Auctions via Approximately Optimal Submodular Optimization
por: Deng, Yuan, et al.
Publicado: (2024)

Smooth Anonymity for Sparse Graphs
por: Epasto, Alessandro, et al.
Publicado: (2022)

Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning
por: Dang, Hien, et al.
Publicado: (2026)

Online Detection of Changes in Moment-Based Projections: When to Retrain Deep Learners or Update Portfolios?
por: Steland, Ansgar
Publicado: (2023)

Private Training & Data Generation by Clustering Embeddings
por: Zhou, Felix, et al.
Publicado: (2025)

Pearson Chi-squared Conditional Randomization Test
por: Javanmard, Adel, et al.
Publicado: (2021)

DeepCrossAttention: Supercharging Transformer Residual Connections
por: Heddes, Mike, et al.
Publicado: (2025)

A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
por: Lin, Licong, et al.
Publicado: (2025)

Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors
por: Khribch, EL Mahdi, et al.
Publicado: (2026)

Optimal score estimation via empirical Bayes smoothing
por: Wibisono, Andre, et al.
Publicado: (2024)

Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
por: Rioux, Gabriel, et al.
Publicado: (2024)

Multivariate Gaussian Approximation for Random Forest via Region-based Stabilization
por: Shi, Zhaoyang, et al.
Publicado: (2024)

Estimating the Number of Components in Finite Mixture Models via Variational Approximation
por: Wang, Chenyang, et al.
Publicado: (2024)

Universality of Approximate Message Passing algorithms and tensor networks
por: Wang, Tianhao, et al.
Publicado: (2022)

Linear Operator Approximate Message Passing (OpAMP)
por: Rossetti, Riccardo, et al.
Publicado: (2024)