158 citations · 259 across the 10 of their papers we have counts for
10 papers
Improving the Gilbert-Varshamov Bound by Graph Spectral Method
Zicheng Ye, Huazi Zhang, Rong Li +3
We improve Gilbert-Varshamov bound by graph spectral method. Gilbert graph is a graph with all vectors in as vertices where two vertices are adjacent i…
The Complete Affine Automorphism Group of Polar Codes
Yuan Li, Huazi Zhang, Rong Li +4
Recently, a permutation-based successive cancellation (PSC) decoding framework for polar codes attaches much attention. It decodes several permuted codewords with independent succe…
On the Weight Spectrum of Pre-Transformed Polar Codes
Yuan Li, Huazi Zhang, Rong Li +3
Polar codes are the first class of channel codes achieving the symmetric capacity of the binary-input discrete memoryless channels with efficient encoding and decoding algorithms.…
Robust Reinforcement Learning with Wasserstein Constraint
Linfang Hou, Liang Pang, Xin Hong +3
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness t…
Target Transfer Q-Learning and Its Convergence Analysis
Yue Wang, Qi Meng, Wei Cheng +3
Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve…
Differential Equations for Modeling Asynchronous Algorithms
Li He, Qi Meng, Wei Chen +2
Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove u…
A Communication-Efficient Parallel Algorithm for Decision Tree
Qi Meng, Guolin Ke, Taifeng Wang +4
Decision tree (and its extensions such as Gradient Boosting Decision Trees and Random Forest) is a widely used machine learning algorithm, due to its practical effectiveness and mo…
Asynchronous Stochastic Proximal Optimization Algorithms with Variance Reduction
Qi Meng, Wei Chen, Jingcheng Yu +3
Regularized empirical risk minimization (R-ERM) is an important branch of machine learning, since it constrains the capacity of the hypothesis space and guarantees the generalizati…
Generalization Error Bounds for Optimization Algorithms via Stability
Qi Meng, Yue Wang, Wei Chen +3
Many machine learning tasks can be formulated as Regularized Empirical Risk Minimization (R-ERM), and solved by optimization algorithms such as gradient descent (GD), stochastic gr…
Asynchronous Stochastic Gradient Descent with Delay Compensation
Shuxin Zheng, Qi Meng, Taifeng Wang +4
With the fast development of deep learning, it has become common to learn big neural networks using massive training data. Asynchronous Stochastic Gradient Descent (ASGD) is widely…