Image de couverture de livre

eGAD! double descent is explained by Generalized Aliasing Decomposition

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Transtrum, Mark K., Hart, Gus L. W., Jarvis, Tyler J., Whitehead, Jared P.
Format:	Preprint
Publié:	2024
Sujets:	Statistics Theory Machine Learning Mathematical Physics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Scorio.jl: A Julia package for ranking stochastic responses
par: Hariri, Mohsen, et autres
Publié: (2026)

Learning general conditional independence structures via the neighbourhood lattice
par: Amini, Arash A., et autres
Publié: (2022)

Gradient descent for deep equilibrium single-index models
par: Dandapanthula, Sanjit, et autres
Publié: (2025)

Spike-timing-dependent Hebbian learning as noisy gradient descent
par: Dexheimer, Niklas, et autres
Publié: (2025)

Information-Geometric Decomposition of Generalization Error in Unsupervised Learning
par: Kim, Gilhan
Publié: (2026)

On the rate of convergence of an over-parametrized Transformer classifier learned by gradient descent
par: Kohler, Michael, et autres
Publié: (2023)

One-step corrected projected stochastic gradient descent for statistical estimation
par: Brouste, Alexandre, et autres
Publié: (2023)

Learning single index model with gradient descent: spectral initialization and precise asymptotics
par: Chen, Yuchen, et autres
Publié: (2025)

Universality of high-dimensional scaling limits of stochastic gradient descent
par: Gheissari, Reza, et autres
Publié: (2025)

Sparse Tucker Decomposition and Graph Regularization for High-Dimensional Time Series Forecasting
par: Xia, Sijia, et autres
Publié: (2026)

When are dynamical systems learned from time series data statistically accurate?
par: Park, Jeongjin, et autres
Publié: (2024)

Analysis of Corrected Graph Convolutions
par: Wang, Robert, et autres
Publié: (2024)

Long-time dynamics and universality of nonconvex gradient descent
par: Han, Qiyang
Publié: (2025)

Entropy Equivalence Testing
par: Canonne, Clément L., et autres
Publié: (2026)

Gradient descent inference in empirical risk minimization
par: Han, Qiyang, et autres
Publié: (2024)

Nonparametric MLE for Gaussian Location Mixtures: Certified Computation and Generic Behavior
par: Polyanskiy, Yury, et autres
Publié: (2025)

Invariant Subspace Decomposition
par: Lazzaretto, Margherita, et autres
Publié: (2024)

Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
par: Cheng, Xiuyuan, et autres
Publié: (2023)

Zero-Truncated Poisson Regression for Sparse Multiway Count Data Corrupted by False Zeros
par: López, Oscar, et autres
Publié: (2022)

Rigorous dynamical mean field theory for stochastic gradient descent methods
par: Gerbelot, Cedric, et autres
Publié: (2022)

Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
par: Dette, Holger, et autres
Publié: (2024)

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
par: Farghly, Tyler, et autres
Publié: (2025)

The Loss Surfaces of Neural Networks with General Activation Functions
par: Baskerville, Nicholas P., et autres
Publié: (2020)

A Complete Decomposition of Stochastic Differential Equations
par: Duffield, Samuel
Publié: (2026)

Rescuing double robustness: safe estimation under complete misspecification
par: Testa, Lorenzo, et autres
Publié: (2025)

Causal Models for Growing Networks
par: Bravo-Hermsdorff, Gecia, et autres
Publié: (2025)

Semiparametric inference for impulse response functions using double/debiased machine learning
par: Ballinari, Daniele, et autres
Publié: (2024)

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
par: Camilli, Francesco, et autres
Publié: (2025)

Diffusion Factor Models: Generating High-Dimensional Returns with Factor Structure
par: Chen, Minshuo, et autres
Publié: (2025)

Optimal Sparse Singular Value Decomposition for High-dimensional High-order Data
par: Zhang, Anru, et autres
Publié: (2018)

Convergence Bounds for Sequential Monte Carlo on Multimodal Distributions using Soft Decomposition
par: Lee, Holden, et autres
Publié: (2024)

On Learning-Curve Monotonicity for Maximum Likelihood Estimators
par: Sellke, Mark, et autres
Publié: (2025)

Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS
par: Bloch, Daniel
Publié: (2026)

Decomposition of Spillover Effects Under Misspecification: Pseudo-true Estimands and a Local-Global Extension
par: Park, Yechan, et autres
Publié: (2026)

Precise gradient descent training dynamics for finite-width multi-layer neural networks
par: Han, Qiyang, et autres
Publié: (2025)

Consistent support recovery for high-dimensional diffusions
par: Marushkevych, Dmytro, et autres
Publié: (2025)

Fast Spawn\&Prune (FS\&P): Global convergence of stochastic conic particle gradient descent via birth/death process
par: De Castro, Yohann, et autres
Publié: (2026)

Low-rank matrix completion and denoising under Poisson noise
par: McRae, Andrew D., et autres
Publié: (2019)

Monotonicity Testing of High-Dimensional Distributions with Subcube Conditioning
par: Chakrabarty, Deeparnab, et autres
Publié: (2025)

An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models
par: Mao, Jialin, et autres
Publié: (2025)