Establishes asymptotic consistency of factor estimates and √T-normality in factor-augmented regressions for fixed R ≥ r using anisotropic local laws from random matrix theory.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
TabKDE generates synthetic tabular data using copula transformations followed by kernel density estimation, matching prior accuracy with negligible training time and reduced storage via coresets.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on benchmarks.
Reusing source latent spaces in diffusion models under distribution shift produces target score error set by principal-angle misalignment and diffusion-time-amplified ambient noise.
The survey unifies extensions of PAC-Bayesian theory to data-dependent sets, geometric and topological complexity measures of optimization trajectories, and stability replacements for information terms into one template inequality with comparative evaluation.
citing papers explorer
-
Fixed-order PCA: Theory for Overestimated Factor Models
Establishes asymptotic consistency of factor estimates and √T-normality in factor-augmented regressions for fixed R ≥ r using anisotropic local laws from random matrix theory.
-
TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates
TabKDE generates synthetic tabular data using copula transformations followed by kernel density estimation, matching prior accuracy with negligible training time and reduced storage via coresets.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
-
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on benchmarks.
-
On the Limits of Latent Reuse in Diffusion Models
Reusing source latent spaces in diffusion models under distribution shift produces target score error set by principal-angle misalignment and diffusion-time-amplified ambient noise.
-
A Survey on Data-Dependent Worst-Case Generalization Bounds
The survey unifies extensions of PAC-Bayesian theory to data-dependent sets, geometric and topological complexity measures of optimization trajectories, and stability replacements for information terms into one template inequality with comparative evaluation.