Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
Foundations and Trends
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Develops sFLSQR and sFLSMR as randomized sketched flexible variants of LSQR/LSMR that recover short recurrences and applies them to large-scale inverse problems with theoretical analysis and experiments.
RL4RLA is a reinforcement learning framework that discovers interpretable symbolic randomized linear algebra algorithms by combining curriculum learning and graph-based search to overcome sparse rewards and large search spaces.
citing papers explorer
-
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.
-
Randomized Flexible LSQR and LSMR with applications to inverse problems
Develops sFLSQR and sFLSMR as randomized sketched flexible variants of LSQR/LSMR that recover short recurrences and applies them to large-scale inverse problems with theoretical analysis and experiments.
-
RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search
RL4RLA is a reinforcement learning framework that discovers interpretable symbolic randomized linear algebra algorithms by combining curriculum learning and graph-based search to overcome sparse rewards and large search spaces.