On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “hypergraphons”

Nonparametric Modeling of Higher-Order Interactions via Hypergraphonsstat.ML

Estimates hypergraphons for modeling complex interactions efficiently.

problem Modeling higher-order interactions using hypergraphons.

method Restricted class of Simple Lipschitz Hypergraphons (SLH) for efficient estimation.

result Optimal rates of convergence for SLH estimator.

hypergraphons higher-order interactions Lipschitz functions statistical estimation

2021-05-18abs ↗pdf ↗

Statistical and Computational Efficiency for Smooth Tensor Estimation with Unknown Permutationsmath.ST

We tackle tensor denoising with unknown permutations, achieving optimal recovery with polynomial estimators.

problem Structured tensor denoising with unknown permutations in recommendation systems, neuroimaging, etc.

method Developed a constrained least-squares estimator in a block-wise polynomial family.

result Achieved the minimax error bound with polynomial estimators of degree up to

(m-2)(m+1)/2

Tensor Denoising Unknown Permutations Minimax Error Bound Polynomial Estimators Phase Transition

2021-11-08abs ↗pdf ↗

Beyond the Signs: Nonparametric Tensor Completion via Sign Seriesstat.ML

New method estimates tensors from noisy data with missing entries.

problem Tensor estimation from noisy observations with missing entries.

method Sign series representation for tensor completion, addressing low- and high-rank signals.

result Excess risk bounds, estimation error rates, and sample complexities established.

tensor completion sign series classification tasks excess risk bounds estimation error rates

2021-01-31abs ↗pdf ↗

Statistical and computational rates in high rank tensor estimationstat.ME

Develops methods to estimate high rank tensors from noisy data.

problem Estimating high rank tensors from noisy observations.

method Generative latent variable tensor model, polynomial-time spectral algorithm.

result Achieves computationally optimal rate for signal tensor estimation.

tensor estimation high rank latent variable spectral algorithm statistical-computational gap

2023-04-08abs ↗pdf ↗