Variational predictive resampling iteratively imputes data from a variational predictive to produce posterior samples that converge to the exact Bayesian posterior in Gaussian models where mean-field VI retains a gap.
hub
A kernel two-sample test.The journal of machine learning research, 13(1):723–773
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 11representative citing papers
Finite-iteration guarantees are established for asynchronous scalar categorical TD in Cramér geometry and multivariate signed-categorical TD in MMD geometry under i.i.d., Markovian, and episodic sampling.
CNN classifiers work by holographic superposition and destructive interference in pixel space rather than selecting cleaned features, as proven by a new adjoint inversion framework that also yields a covariance-volume channel selection algorithm.
BRICKS creates compositional neural Markov kernels via hybrid transformers and Riemannian Flow Matching on product manifolds to enable zero-shot simulation of radiation-matter interactions across arbitrary material distributions.
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.
DRIO adds worst-case Wasserstein regularization to time series imputation, yielding a tractable adversarial surrogate and alternating algorithm that improves robustness under missingness.
A state distribution view of post-training shows that on-policy supervision from the learner itself can outperform fixed-dataset SFT and preserve retention better than aggressive supervised updates.
SynVA toolkit generates realistic vascular meshes and anatomically plausible aneurysms, releasing 50,000 labeled samples for medical vision tasks.
CAST selects better multimodal coresets by fusing collapse-aware topologies across modalities and matching distributions at multiple scales in the diffusion wavelet domain.
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.
citing papers explorer
-
Variational predictive resampling
Variational predictive resampling iteratively imputes data from a variational predictive to produce posterior samples that converge to the exact Bayesian posterior in Gaussian models where mean-field VI retains a gap.
-
A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning
Finite-iteration guarantees are established for asynchronous scalar categorical TD in Cramér geometry and multivariate signed-categorical TD in MMD geometry under i.i.d., Markovian, and episodic sampling.
-
Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers
CNN classifiers work by holographic superposition and destructive interference in pixel space rather than selecting cleaned features, as proven by a new adjoint inversion framework that also yields a covariance-volume channel selection algorithm.
-
BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation
BRICKS creates compositional neural Markov kernels via hybrid transformers and Riemannian Flow Matching on product manifolds to enable zero-shot simulation of radiation-matter interactions across arbitrary material distributions.
-
Efficient Diffusion Distillation via Embedding Loss
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.
-
Multivariate Time Series Data Imputation via Distributionally Robust Regularization
DRIO adds worst-case Wasserstein regularization to time series imputation, yielding a tractable adversarial surrogate and alternating algorithm that improves robustness under missingness.
-
Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
A state distribution view of post-training shows that on-policy supervision from the learner itself can outperform fixed-dataset SFT and preserve retention better than aggressive supervised updates.
-
SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing
SynVA toolkit generates realistic vascular meshes and anatomically plausible aneurysms, releasing 50,000 labeled samples for medical vision tasks.
-
CAST: Collapse-Aware multi-Scale Topology Fusion for Multimodal Coreset Selection
CAST selects better multimodal coresets by fusing collapse-aware topologies across modalities and matching distributions at multiple scales in the diffusion wavelet domain.
-
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
MDMF detects AI-generated images by learning patch-level forensic signatures and quantifying their distributional discrepancies with MMD, yielding larger separation than global methods when micro-defects are present.
-
A Kernel Nonconformity Score for Multivariate Conformal Prediction
A new kernel nonconformity score for multivariate conformal prediction that adapts to residual geometry, provides finite-sample coverage, and achieves convergence rates based on effective kernel rank rather than ambient dimension.