Image de couverture de livre

When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Obuchi, Tomoyuki, Tanaka, Toshiyuki
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Disordered Systems and Neural Networks Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
par: Cavaliere, Angelo Giorgio, et autres
Publié: (2025)

Perfect reconstruction of sparse signals using nonconvexity control and one-step RSB message passing
par: Gu, Xiaosi, et autres
Publié: (2025)

Transfer Learning in $\ell_1$ Regularized Regression: Hyperparameter Selection Strategy based on Sharp Asymptotic Analysis
par: Okajima, Koki, et autres
Publié: (2024)

Bayes optimal learning of attention-indexed models
par: Boncoraglio, Fabrizio, et autres
Publié: (2025)

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
par: Nguyen, Minh-Toan, et autres
Publié: (2026)

Bayes-optimal learning of an extensive-width neural network from quadratically many samples
par: Maillard, Antoine, et autres
Publié: (2024)

A universal compression theory for lottery ticket hypothesis and neural scaling laws
par: Wang, Hong-Yi, et autres
Publié: (2025)

Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
par: Boncoraglio, Fabrizio, et autres
Publié: (2025)

Deep ReLU networks -- injectivity capacity upper bounds
par: Stojnic, Mihailo
Publié: (2024)

Injectivity capacity of ReLU gates
par: Stojnic, Mihailo
Publié: (2024)

On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance
par: Barbier, Jean, et autres
Publié: (2024)

Rare dense solutions clusters in asymmetric binary perceptrons -- local entropy via fully lifted RDT
par: Stojnic, Mihailo
Publié: (2025)

Storage capacity of perceptron with variable selection
par: Xu, Yingying, et autres
Publié: (2025)

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
par: Erba, Vittorio, et autres
Publié: (2025)

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
par: Barbier, Jean, et autres
Publié: (2025)

A unified theory of feature learning in RNNs and DNNs
par: Bauer, Jan P., et autres
Publié: (2026)

Training neural networks with structured noise improves classification and generalization
par: Benedetti, Marco, et autres
Publié: (2023)

Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation
par: Barbier, Jean, et autres
Publié: (2025)

A CLuP algorithm to practically achieve $\sim 0.76$ SK--model ground state free energy
par: Stojnic, Mihailo
Publié: (2025)

Exact capacity of the \emph{wide} hidden layer treelike neural networks with generic activations
par: Stojnic, Mihailo
Publié: (2024)

Fixed width treelike neural networks capacity analysis -- generic activations
par: Stojnic, Mihailo
Publié: (2024)

Capacity of the Hebbian-Hopfield network associative memory
par: Stojnic, Mihailo
Publié: (2024)

Binary perceptron computational gap -- a parametric fl RDT view
par: Stojnic, Mihailo
Publié: (2025)

Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection
par: Stojnic, Mihailo
Publié: (2026)

Parametric RDT approach to computational gap of symmetric binary perceptron
par: Stojnic, Mihailo
Publié: (2026)

Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications
par: Xu, Yizhou, et autres
Publié: (2025)

The Persian Rug: solving toy models of superposition using large-scale symmetries
par: Cowsik, Aditya, et autres
Publié: (2024)

Precise asymptotic analysis of Sobolev training for random feature models
par: Fisher, Katharine E, et autres
Publié: (2025)

CLuP practically achieves $\sim 1.77$ positive and $\sim 0.33$ negative Hopfield model ground state free energy
par: Stojnic, Mihailo
Publié: (2025)

Asymptotics of feature learning in two-layer networks after one gradient-step
par: Cui, Hugo, et autres
Publié: (2024)

Adaptive kernel predictors from feature-learning infinite limits of neural networks
par: Lauditi, Clarissa, et autres
Publié: (2025)

Ratio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback--Leibler Divergence Learning
par: Ishida, Yuichi, et autres
Publié: (2024)

Statistical mechanics of extensive-width Bayesian neural networks near interpolation
par: Barbier, Jean, et autres
Publié: (2025)

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

Analysis of Diffusion Models for Manifold Data
par: George, Anand Jerry, et autres
Publié: (2025)

Random features and polynomial rules
par: Aguirre-López, Fabián, et autres
Publié: (2024)

A solvable model of learning generative diffusion: theory and insights
par: Cui, Hugo, et autres
Publié: (2025)

Quantum circuit complexity and unsupervised machine learning of topological order
par: Che, Yanming, et autres
Publié: (2025)

Restoring balance: principled under/oversampling of data for optimal classification
par: Loffredo, Emanuele, et autres
Publié: (2024)

Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions
par: Keup, Christian, et autres
Publié: (2024)