Imagen de Portada

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Block, Jacob L., Mohri, Mehryar, Mokhtari, Aryan, Shakkottai, Sanjay
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

Machine Unlearning under Overparameterization
por: Block, Jacob L., et al.
Publicado: (2025)

Provable Meta-Learning with Low-Rank Adaptations
por: Block, Jacob L., et al.
Publicado: (2024)

Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization
por: Jiang, Ruichen, et al.
Publicado: (2026)

Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
por: Mohri, Mehryar, et al.
Publicado: (2026)

Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
por: Mao, Anqi, et al.
Publicado: (2025)

Rational Transductors
por: Mohri, Mehryar
Publicado: (2026)

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
por: Collins, Liam, et al.
Publicado: (2023)

Principled Approaches for Learning to Defer with Multiple Experts
por: Mao, Anqi, et al.
Publicado: (2023)

Beyond Tsybakov: Model Margin Noise and $\mathcal{H}$-Consistency Bounds
por: Mohri, Mehryar, et al.
Publicado: (2025)

In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
por: Collins, Liam, et al.
Publicado: (2024)

A Theoretical Framework for Modular Learning of Robust Generative Models
por: Cortes, Corinna, et al.
Publicado: (2026)

Mind the Gap: Structure-Aware Consistency in Preference Learning
por: Mohri, Mehryar, et al.
Publicado: (2026)

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
por: Mohri, Mehryar, et al.
Publicado: (2026)

Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning
por: Mohri, Mehryar, et al.
Publicado: (2026)

Budgeted Multiple-Expert Deferral
por: DeSalvo, Giulia, et al.
Publicado: (2025)

Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment
por: Wang, Ye, et al.
Publicado: (2026)

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
por: Dann, Christoph, et al.
Publicado: (2026)

Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
por: Mao, Anqi, et al.
Publicado: (2024)

Regression with Multi-Expert Deferral
por: Mao, Anqi, et al.
Publicado: (2024)

$H$-Consistency Guarantees for Regression
por: Mao, Anqi, et al.
Publicado: (2024)

A Universal Growth Rate for Learning with Smooth Surrogate Losses
por: Mao, Anqi, et al.
Publicado: (2024)

Top-$k$ Classification and Cardinality-Aware Prediction
por: Mao, Anqi, et al.
Publicado: (2024)

Coherence Mechanisms for Provable Self-Improvement
por: Mohri, Mehryar, et al.
Publicado: (2025)

Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
por: Mao, Anqi, et al.
Publicado: (2025)

Improved Balanced Classification with Theoretically Grounded Loss Functions
por: Cortes, Corinna, et al.
Publicado: (2025)

Enhanced $H$-Consistency Bounds
por: Mao, Anqi, et al.
Publicado: (2024)

Multi-Label Learning with Stronger Consistency Guarantees
por: Mao, Anqi, et al.
Publicado: (2024)

Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
por: Mao, Anqi, et al.
Publicado: (2023)

Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms
por: Mao, Anqi, et al.
Publicado: (2023)

Tempered Guided Diffusion
por: Makris, Andreas, et al.
Publicado: (2026)

Cardinality-Aware Set Prediction and Top-$k$ Classification
por: Cortes, Corinna, et al.
Publicado: (2024)

Algorithms for Learning Kernels Based on Centered Alignment
por: Cortes, Corinna, et al.
Publicado: (2012)

Progressive Tempering Sampler with Diffusion
por: Rissanen, Severi, et al.
Publicado: (2025)

Distributional Alignment Games for Answer-Level Fine-Tuning
por: Mohri, Mehryar, et al.
Publicado: (2026)

Continuously Tempered Diffusion Samplers
por: Erives, Ezra, et al.
Publicado: (2025)

Entropy Aware Reward Guidance for Diffusion Language Model Alignment
por: Tejaswi, Atula, et al.
Publicado: (2026)

Optimized Deferral for Imbalanced Settings
por: Cortes, Corinna, et al.
Publicado: (2026)

Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data
por: Cortes, Corinna, et al.
Publicado: (2025)

Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles
por: Millard, Andrew, et al.
Publicado: (2025)

Parallelly Tempered Generative Adversarial Nets: Toward Stabilized Gradients
por: Sohn, Jinwon, et al.
Publicado: (2024)