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.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
The spectral weak-recovery threshold for linearized AMP in the multi-view spiked Wigner model is SNR(λ,B)=1, where SNR is the largest eigenvalue of Diag(√λ)(B⊙B)Diag(√λ), and this coincides with the information-theoretic threshold for a broad class of spike priors.
Two steps of gradient descent on first-layer weights in linear-width two-layer networks produce a spiked random matrix with floor(alpha2/(1/2-alpha1)) outliers, each a learned direction, and batch reuse allows capturing directions with information exponent exceeding one.
A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
Near-linear time algorithm for robust regression under Gaussian covariates achieves O(sqrt(ε κ)) error with Õ(d/ε⁴) samples when ε κ ≲ 1, plus SQ and low-degree lower bounds.
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.
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.
-
Sharp Spectral Thresholds for Multi-View Spiked Wigner Models
The spectral weak-recovery threshold for linearized AMP in the multi-view spiked Wigner model is SNR(λ,B)=1, where SNR is the largest eigenvalue of Diag(√λ)(B⊙B)Diag(√λ), and this coincides with the information-theoretic threshold for a broad class of spike priors.
-
Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
Two steps of gradient descent on first-layer weights in linear-width two-layer networks produce a spiked random matrix with floor(alpha2/(1/2-alpha1)) outliers, each a learned direction, and batch reuse allows capturing directions with information exponent exceeding one.
-
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
A solvable hierarchical model with power-law feature strengths yields explicit power-law scaling of prediction error through sequential recovery of latent directions by a layer-wise spectral algorithm.
-
On efficient robust regression with subquadratic samples
Near-linear time algorithm for robust regression under Gaussian covariates achieves O(sqrt(ε κ)) error with Õ(d/ε⁴) samples when ε κ ≲ 1, plus SQ and low-degree lower bounds.
-
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.