SPSC recovers drifting low-rank subspaces from scalar rewards under known noise variance, bounded coupling, and full probe support, then achieves dynamic regret scaling as r sqrt(T) plus lower-order terms instead of d sqrt(T).
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Riemannian networks are introduced for the full-rank correlation matrix manifold by extending MLR, FC, and convolutional layers to five geometries with backpropagation methods for two, showing effectiveness over SPD and Grassmannian baselines.
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
Muon succeeds by guaranteeing local step-size optimality rather than by tracking any ideal global geometry, as random-spectrum and quasi-norm variants match its performance on language models.
A single-network fixed-point formulation for neural optimal transport eliminates adversarial min-max optimization and implicit differentiation while enforcing dual feasibility exactly.
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
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
-
Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
SPSC recovers drifting low-rank subspaces from scalar rewards under known noise variance, bounded coupling, and full probe support, then achieves dynamic regret scaling as r sqrt(T) plus lower-order terms instead of d sqrt(T).
-
Riemannian Networks over Full-Rank Correlation Matrices
Riemannian networks are introduced for the full-rank correlation matrix manifold by extending MLR, FC, and convolutional layers to five geometries with backpropagation methods for two, showing effectiveness over SPD and Grassmannian baselines.
-
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.
-
Muon is Not That Special: Random or Inverted Spectra Work Just as Well
Muon succeeds by guaranteeing local step-size optimality rather than by tracking any ideal global geometry, as random-spectrum and quasi-norm variants match its performance on language models.
-
Fixed-Point Neural Optimal Transport without Implicit Differentiation
A single-network fixed-point formulation for neural optimal transport eliminates adversarial min-max optimization and implicit differentiation while enforcing dual feasibility exactly.
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
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.