Image de couverture de livre

The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Majka, Adrien, El-Mhamdi, El-Mahdi
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Statistics Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On Goodhart's law, with an application to value alignment
par: El-Mhamdi, El-Mahdi, et autres
Publié: (2024)

Byzantine Machine Learning: MultiKrum and an optimal notion of robustness
par: Bareilles, Gilles, et autres
Publié: (2026)

On Monotonicity in AI Alignment
par: Bareilles, Gilles, et autres
Publié: (2025)

Convergence of Statistical Estimators via Mutual Information Bounds
par: Khribch, El Mahdi, et autres
Publié: (2024)

Beyond Benign Overfitting in Nadaraya-Watson Interpolators
par: Barzilai, Daniel, et autres
Publié: (2025)

Meta-Learning and representation learner: A short theoretical note
par: Bouchattaoui, Mouad El
Publié: (2024)

Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression
par: Kim, Yeichan, et autres
Publié: (2025)

Learning Curves and Benign Overfitting of Spectral Algorithms in Large Dimensions
par: Lu, Weihao, et autres
Publié: (2026)

Benign Overfitting in Time Series Linear Models with Over-Parameterization
par: Nakakita, Shogo, et autres
Publié: (2022)

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
par: Haas, Moritz, et autres
Publié: (2023)

Dimension-agnostic inference using cross U-statistics
par: Kim, Ilmun, et autres
Publié: (2020)

Benign Overfitting under Learning Rate Conditions for $α$ Sub-exponential Input
par: Okudo, Kota, et autres
Publié: (2024)

A general framework for inference on algorithm-agnostic variable importance
par: Williamson, Brian D., et autres
Publié: (2020)

Model-agnostic information transfer and fusion for classification with label noise
par: Guojun, Zhu, et autres
Publié: (2026)

Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
par: Hanchi, Ayoub El, et autres
Publié: (2023)

Approaching the Harm of Gradient Attacks While Only Flipping Labels
par: El-Kabid, Abdessamad, et autres
Publié: (2025)

A Geometric Analysis of PCA
par: Hanchi, Ayoub El, et autres
Publié: (2025)

The loss landscape of deep linear neural networks: a second-order analysis
par: Achour, El Mehdi, et autres
Publié: (2021)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
par: Frei, Spencer, et autres
Publié: (2022)

It's Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation
par: Jin, Jikai, et autres
Publié: (2025)

General reproducing properties in RKHS with application to derivative and integral operators
par: El-Boukkouri, Fatima-Zahrae, et autres
Publié: (2025)

Optimal structure learning and conditional independence testing
par: Gao, Ming, et autres
Publié: (2025)

Minimax Linear Regression under the Quantile Risk
par: Hanchi, Ayoub El, et autres
Publié: (2024)

On the Efficiency of ERM in Feature Learning
par: Hanchi, Ayoub El, et autres
Publié: (2024)

Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
par: Morisset, Lucas, et autres
Publié: (2026)

Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation
par: Jin, Jikai, et autres
Publié: (2024)

Universality of Benign Overfitting in Binary Linear Classification
par: Hashimoto, Ichiro, et autres
Publié: (2025)

Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning
par: Prevost, Adrien, et autres
Publié: (2025)

Higher-Order Regularization Learning on Hypergraphs
par: Weihs, Adrien, et autres
Publié: (2025)

Analysis of Semi-Supervised Learning on Hypergraphs
par: Weihs, Adrien, et autres
Publié: (2025)

Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors
par: Khribch, EL Mahdi, et autres
Publié: (2026)

Universality laws for Gaussian mixtures in generalized linear models
par: Dandi, Yatin, et autres
Publié: (2023)

High-probability zeroth-order online convex optimisation beyond Euclidean geometry
par: Janz, David, et autres
Publié: (2025)

Strong identifiability and parameter learning in regression with heterogeneous response
par: Do, Dat, et autres
Publié: (2022)

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
par: Firdoussi, Aymane El, et autres
Publié: (2024)

Benign overfitting in Fixed Dimension via Physics-Informed Learning with Smooth Inductive Bias
par: Wong, Honam, et autres
Publié: (2024)

Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
par: Morisset, Lucas, et autres
Publié: (2025)

Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion
par: Vacher, Adrien, et autres
Publié: (2024)

Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay
par: Li, Yicheng, et autres
Publié: (2024)

Inferring the finest pattern of mutual independence from data
par: Marrelec, G., et autres
Publié: (2023)