Zhouyuan Huo
21 papers · 2017–2024 · 9 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (41) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π¬
Deep Specialist
(11)
π€
Dynamic Duo
(12)
π
Keyword Champion
(2)
π§
Keyword Pioneer
ποΈ
Keyword Collector
(96)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Conference Pioneer
Venues
Top co-authors
Research topics
Machine Learning
(19)
Optimization & Theory Β· Machine Learning
(15)
Deep Learning
(12)
Optimization & Theory Β· Deep Learning
(6)
Mathematics & Optimization
(5)
Speech & Audio
(5)
Application Areas
(5)
Optimization
(5)
Recognition
(5)
Learning Types Β· Machine Learning
(4)
Learning Types Β· Deep Learning
(4)
Techniques
(4)
Artificial Intelligence
(3)
Architectures
(3)
Core Methods
(3)
Keywords
stochastic optimization
(3)
variance reduction
(3)
speech recognition
(3)
convergence guarantee
(3)
parallel training
(3)
automatic speech recognition
(3)
convergence rate
(2)
proximal gradient
(2)
parameter-efficient fine-tuning
(2)
gradient descent
(2)
stochastic gradient descent
(2)
domain adaptation
(2)
unsupervised learning
(2)
model compression
(2)
model parallelism
(2)
distributed learning
(2)
self-supervised learning
(2)
convergence analysis
(2)
neural network optimization
(2)
distributed training
(2)
Papers
AdaRA: Adaptive Rank Allocation of Residual Adapters for Speech Foundation Model
Interspeech 2024
Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism
NeurIPS 2023
Re-investigating the Efficient Transfer Learning of Speech Foundation Model using Feature Fusion Methods
Interspeech 2023
Incremental Layer-Wise Self-Supervised Learning for Efficient Unsupervised Speech Domain Adaptation On Device
Interspeech 2022
Pseudo Label Is Better Than Human Label
Interspeech 2022
A Comparison of Supervised and Unsupervised Pre-Training of End-to-End Models
Interspeech 2021
Large Batch Optimization for Deep Learning Using New Complete Layer-Wise Adaptive Rate Scaling
AAAI 2021
On Large-Cohort Training for Federated Learning
NeurIPS 2021
Step-Ahead Error Feedback for Distributed Training with Compressed Gradient
AAAI 2021
A Unified q-Memorization Framework for Asynchronous Stochastic Optimization
JMLR 2020
On the Acceleration of Deep Learning Model Parallelism With Staleness
CVPR 2020
An End-to-End Generative Architecture for Paraphrase Generation
EMNLP 2019
Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization
AAAI 2019
Ouroboros: On Accelerating Training of Transformer-Based Language Models
NeurIPS 2019
Scalable and Efficient Pairwise Learning to Achieve Statistical Accuracy
AAAI 2019
Asynchronous Doubly Stochastic Group Regularized Learning
AISTATS 2018
Decoupled Parallel Backpropagation with Convergence Guarantee
ICML 2018
Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines
ICML 2018
Training Neural Networks Using Features Replay
NeurIPS 2018
Joint Capped Norms Minimization for Robust Matrix Recovery
IJCAI 2017
Multi-Class Support Vector Machine via Maximizing Multi-Class Margins
IJCAI 2017