activity
20042025
most citedStandard deviation of the longest common subsequence

24 citations · 91 across the 27 of their papers we have counts for

collaborators

29 papers

cs.CL2025

Is logical analysis performed by transformers taking place in self-attention or in the fully connected part?

Evgeniy Shin, Heinrich Matzinger

Transformers architecture apply self-attention to tokens represented as vectors, before a fully connected (neuronal network) layer. These two parts can be layered many times. Tradi…

stat.ML2022

Recover the spectrum of covariance matrix: a non-asymptotic iterative method

Juntao Duan, Ionel Popescu, Heinrich Matzinger

It is well known the sample covariance has a consistent bias in the spectrum, for example spectrum of Wishart matrix follows the Marchenko-Pastur law. We in this work introduce an…

math.PR2021

Invariance principle of random projection for the norm

Juntao Duan, Ionel Popescu, Heinrich Matzinger

Johnson-Lindenstrauss guarantees certain topological structure is preserved under random projections when project high dimensional deterministic vectors to low dimensional vectors.…

math.PR2020

An Analytical Formula for Spectrum Reconstruction

Zhibo Dai, Heinrich Matzinger, Ionel Popescu

We study the spectrum reconstruction technique. As is known to all, eigenvalues play an important role in many research fields and are foundation to many practical techniques such…

stat.ML2019

A cost-reducing partial labeling estimator in text classification problem

Jiangning Chen, Zhibo Dai, Juntao Duan +5

We propose a new approach to address the text classification problems when learning with partial labels is beneficial. Instead of offering each training sample a set of candidate l…

cs.IR2019

Naive Bayes with Correlation Factor for Text Classification Problem

Jiangning Chen, Zhibo Dai, Juntao Duan +2

Naive Bayes estimator is widely used in text classification problems. However, it doesn't perform well with small-size training dataset. We propose a new method based on Naive Baye…