Picture for Xiaohan Wei

Xiaohan Wei

Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems

Add code
Jan 09, 2024
Figure 1 for Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
Figure 2 for Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
Figure 3 for Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
Figure 4 for Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
Viaarxiv icon

Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning

May 31, 2023
Viaarxiv icon

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions

Jul 25, 2022
Figure 1 for Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Figure 2 for Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Viaarxiv icon

DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction

Mar 11, 2022
Figure 1 for DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
Figure 2 for DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
Figure 3 for DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
Figure 4 for DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
Viaarxiv icon

Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits

Add code
Oct 24, 2021
Figure 1 for Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
Figure 2 for Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
Figure 3 for Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
Figure 4 for Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
Viaarxiv icon

Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale

May 26, 2021
Figure 1 for Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
Figure 2 for Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
Figure 3 for Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
Figure 4 for Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
Viaarxiv icon

Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism

Add code
Oct 18, 2020
Figure 1 for Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism
Figure 2 for Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism
Figure 3 for Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism
Figure 4 for Fast Distributed Training of Deep Neural Networks: Dynamic Communication Thresholding for Model and Data Parallelism
Viaarxiv icon

Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning

Aug 23, 2020
Figure 1 for Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning
Viaarxiv icon

Beyond $\mathcal{O}(\sqrt{T})$ Regret for Constrained Online Optimization: Gradual Variations and Mirror Prox

Jun 22, 2020
Figure 1 for Beyond $\mathcal{O}(\sqrt{T})$ Regret for Constrained Online Optimization: Gradual Variations and Mirror Prox
Viaarxiv icon

Upper Confidence Primal-Dual Optimization: Stochastically Constrained Markov Decision Processes with Adversarial Losses and Unknown Transitions

Mar 02, 2020
Viaarxiv icon