Joint KL yields horizon-free approximation but an information-theoretic lower bound of order Omega(H) for estimation error in autoregressive learning, with matching computationally efficient upper bounds.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
A projected gradient descent algorithm for noisy inductive matrix completion achieves linear convergence and stable recovery at sample complexity governed by side-information dimension, extending to inexact side-information with optimal error degradation.
Stationary duality reduces composite cardinality optimization to simple cardinality, yielding dual problems with equivalent local solutions and global solutions under appropriate parameter selection.
citing papers explorer
-
Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds
Joint KL yields horizon-free approximation but an information-theoretic lower bound of order Omega(H) for estimation error in autoregressive learning, with matching computationally efficient upper bounds.
-
Pointwise Generalization in Deep Neural Networks
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
-
Sample-efficient inductive matrix completion with noise and inexact side-information
A projected gradient descent algorithm for noisy inductive matrix completion achieves linear convergence and stable recovery at sample complexity governed by side-information dimension, extending to inexact side-information with optimal error degradation.
-
On the Stationary Duality of Structural Composite Cardinality Optimization
Stationary duality reduces composite cardinality optimization to simple cardinality, yielding dual problems with equivalent local solutions and global solutions under appropriate parameter selection.