Ji Xu
10 papers · 2016–2022 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze
π§
Keyword Pioneer
β
The Questioner
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory Β· Machine Learning
(9)
Mathematics & Optimization
(5)
Optimization
(5)
Core Methods
(3)
Deep Learning
(2)
Speech & Audio
(2)
Recognition
(2)
Analysis
(1)
Architectures
(1)
Learning Paradigms
(1)
Learning Types
(1)
Mathematics
(1)
Optimization & Theory Β· Deep Learning
(1)
Synthesis
(1)
Keywords
double descent
(2)
phase retrieval
(2)
signal recovery
(2)
non-convex optimization
(2)
automatic speech recognition
(2)
expectation maximization
(2)
ridge regression
(1)
asymptotic analysis
(1)
feature selection
(1)
maximum likelihood
(1)
parameter estimation
(1)
expectation propagation
(1)
approximate message passing
(1)
high-dimensional analysis
(1)
principal component regression
(1)
natural gradient descent
(1)
convergence analysis
(1)
speaker diarization
(1)
statistical modeling
(1)
compressed sensing
(1)
Papers
Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset
Interspeech 2022
Analysis of Sensing Spectral for Signal Recovery under a Generalized Linear Model
NeurIPS 2021
On the proliferation of support vectors in high dimensions
AISTATS 2021
When does preconditioning help or hurt generalization?
ICLR 2021
On the Optimal Weighted β_2 Regularization in Overparameterized Linear Regression
NeurIPS 2020
On the number of variables to use in principal component regression
NeurIPS 2019
Approximate message passing for amplitude based optimization
ICML 2018
Benefits of over-parameterization with EM
NeurIPS 2018
Output-Gate Projected Gated Recurrent Unit for Speech Recognition
Interspeech 2018
Global Analysis of Expectation Maximization for Mixtures of Two Gaussians
NeurIPS 2016