An efficient black-box reduction from PQ to TDS learning for any Boolean concept class in the distribution-free setting implies hardness for TDS learning of halfspaces, while membership queries enable efficient PQ learning of halfspaces via iterative Forster transforms.
Journal of Machine Learning Research , volume=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Multi-head attention is an ensemble of Nadaraya-Watson estimators whose MSE decreases monotonically with a new spectral Head Diversity Index measuring subspace decorrelation, yielding optimal head count and dimension scaling laws under fixed total dimension.
The sharp MSE bound for the ℓ1-minimum-norm interpolator under isotropic Gaussian covariates is recovered via the geometry of symmetric Gaussian polytopes, without the convex Gaussian min-max theorem.
Clients encode private images through a frozen public autoencoder, compute additive class-conditional latent statistics protected by differential privacy, and the server decodes a synthetic dataset that trains competitive global models in one communication round.
Pre-training provides a geometric warm start in a single-index model that enables weak-to-strong generalization up to a supervisor-limited bound, with empirical phase-transition evidence in LLMs.
Derives novel generalization error bounds for multimodal pairwise metric learning showing that fine-grained modality features reduce hypothesis space complexity via enhanced complementarity.
citing papers explorer
-
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
An efficient black-box reduction from PQ to TDS learning for any Boolean concept class in the distribution-free setting implies hardness for TDS learning of halfspaces, while membership queries enable efficient PQ learning of halfspaces via iterative Forster transforms.
-
Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity
Multi-head attention is an ensemble of Nadaraya-Watson estimators whose MSE decreases monotonically with a new spectral Head Diversity Index measuring subspace decorrelation, yielding optimal head count and dimension scaling laws under fixed total dimension.
-
Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of Gaussianity
The sharp MSE bound for the ℓ1-minimum-norm interpolator under isotropic Gaussian covariates is recovered via the geometry of symmetric Gaussian polytopes, without the convex Gaussian min-max theorem.
-
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
Clients encode private images through a frozen public autoencoder, compute additive class-conditional latent statistics protected by differential privacy, and the server decodes a synthetic dataset that trains competitive global models in one communication round.
-
On the Blessing of Pre-training in Weak-to-Strong Generalization
Pre-training provides a geometric warm start in a single-index model that enables weak-to-strong generalization up to a supervisor-limited bound, with empirical phase-transition evidence in LLMs.
-
Quantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning
Derives novel generalization error bounds for multimodal pairwise metric learning showing that fine-grained modality features reduce hypothesis space complexity via enhanced complementarity.