Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from EDBT 2026 / reviewers in the wild / expert

Beichen Xue

dblp:357/4759 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
1since 2021 · last 2023
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Deep learning architectures and training · 70% Learning theory · 30%

Topics — the 4 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Deep learning architectures and training
sequence modeling		 0.712023
State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory · NeurIPS 2023
Machine learning › Deep learning architectures and training
state space model		 0.712023
State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory · NeurIPS 2023
Machine learning › Learning theory › approximation theory › neural network approximation
universal approximation		 0.712023
State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory · NeurIPS 2023
Machine learning › Deep learning architectures and training › sequence modeling
long-range memory		 0.212023
State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory · NeurIPS 2023

Methods — techniques the papers use, named apart from their topics

numerical verification · 0.7layer-wise nonlinear activation · 0.7
YearPublicationVenuePosition
2023 State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory
abstract
State-space models have gained popularity in sequence modelling due to their simple and efficient network structures. However, the absence of nonlinear activation along the temporal direction limits the model's capacity. In this paper, we prove that stacking state-space models with layer-wise nonlinear activation is sufficient to approximate any continuous sequence-to-sequence relationship. Our findings demonstrate that the addition of layer-wise nonlinear activation enhances the model's capacity to learn complex sequence patterns. Meanwhile, it can be seen both theoretically and empirically that the state-space models do not fundamentally resolve the issue of exponential decaying memory. Theoretical results are justified by numerical verifications.
Beichen Xue
 NeurIPS2