Qi Meng

发表

Optimization of ReLU Neural Networks using Quotient Stochastic Gradient Descent

Qi Meng, Wei Chen, Qiwei Ye, 2018 .

A Highly Efficient Gradient Boosting Decision Tree

Tie-Yan Liu, Wei Chen, Guolin Ke, 2017, NIPS 2017.

Dynamic of Stochastic Gradient Descent with State-Dependent Noise

Zhi-Ming Ma, Tie-Yan Liu, Wei Chen, 2020, ArXiv.

Light Gradient Boosting Machine [R package lightgbm version 3.1.1]

Tie-Yan Liu, Qiwei Ye, Wei Chen, 2020 .

A Convergent Variant of the Boltzmann Softmax Operator in Reinforcement Learning

Tie-Yan Liu, Qi Meng, Wei Chen, 2018 .

Path Space for Recurrent Neural Networks with ReLU Activations

Tie-Yan Liu, Yue Wang, Wei Chen, 2019 .

Expressiveness in Deep Reinforcement Learning

Di He, Tie-Yan Liu, Yunhong Wang, 2018 .

N EURAL O PERATOR WITH R EGULARITY S TRUCTURE FOR M ODELING D YNAMICS D RIVEN BY SPDE S

Yue Wang, Wei Chen, Qi Meng, 2022 .

Does Momentum Change the Implicit Regularization on Separable Data?

Huishuai Zhang, Wei Chen, Qi Meng, 2021, NeurIPS.

Towards Accelerating Training of Batch Normalization: A Manifold Perspective

Zhi-Ming Ma, Mingyang Yi, Wei Chen, 2021, ArXiv.

An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging

Zhi-Ming Ma, H. Qu, Qi Meng, 2022, 2201.08187.

Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations

Yue Wang, Zhi-Ming Ma, Qi Meng, 2022, ArXiv.

DRVN (Deep Random Vortex Network): A new physics-informed machine learning method for simulating and inferring incompressible fluid flows

Yue Wang, Zhi-Ming Ma, Qi Meng, 2022, Physics of Fluids.

Provable Adaptivity in Adam

Huishuai Zhang, Wei Chen, Qi Meng, 2022, ArXiv.

SE(3) Equivariant Graph Neural Networks with Complete Local Frames

Wei Chen, Qi Meng, Yuanqi Du, 2021, ICML.

An efficient Lorentz equivariant graph neural network for jet tagging

Zhi-Ming Ma, H. Qu, Qi Meng, 2022, Journal of High Energy Physics.

Stochastic Lag Time Parameterization for Markov State Models of Protein Dynamics.

Zhiming Ma, Qi Meng, Shiqi Gong, 2022, The journal of physical chemistry. B.

Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs

Yue Wang, Wei Chen, Qi Meng, 2022, ArXiv.

LightGBM: A Highly Efficient Gradient Boosting Decision Tree

Tie-Yan Liu, Qi Meng, Wei Chen, 2017, NIPS.

Momentum Doesn't Change the Implicit Bias pdf

Qi Meng, Ruoyu Sun, Huishuai Zhang, 2021, ArXiv.

Asynchronous Stochastic Gradient Descent with Delay Compensation

Nenghai Yu, Tie-Yan Liu, Qi Meng, 2016, ICML.

A Communication-Efficient Parallel Algorithm for Decision Tree

Tie-Yan Liu, Qi Meng, Wei Chen, 2016, NIPS.

NeuralStagger: accelerating physics-constrained neural PDE solver with spatial-temporal decomposition

Yue Wang, Qi Meng, Wenlei Shi, 2023, ICML.

Monte Carlo Neural Operator for Learning PDEs via Probabilistic Representation

Yue Wang, Zhi-Ming Ma, Qi Meng, 2023, ArXiv.

SE(3) Equivariant Graph Neural Networks with Complete Local Frames

Wei Chen, Qi Meng, Yuanqi Du, 2021, ICML.

G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space

Nenghai Yu, Tie-Yan Liu, Qi Meng, 2018, ICLR.

Reinforcement Learning with Dynamic Boltzmann Softmax Updates pdf

Tie-Yan Liu, Qi Meng, Wei Chen, 2019, IJCAI.

Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling

Tie-Yan Liu, Qi Meng, Wei Chen, 2017, Neurocomputing.

Capacity Control of ReLU Neural Networks by Basis-path Norm pdf

Nenghai Yu, Tie-Yan Liu, Qi Meng, 2018, AAAI.

R-Drop: Regularized Dropout for Neural Networks pdf

Tao Qin, Qi Meng, Lijun Wu, 2021, NeurIPS.

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior

Tie-Yan Liu, Tao Qin, Xu Tan, 2021, ICLR.

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior pdf

Tao Qin, Qi Meng, Sungroh Yoon, 2021, ArXiv.

Equivariant vector field network for many-body system modeling pdf

Qi Meng, Wei Chen, Tie-Yan Liu, 2021, ArXiv.

Positively Scale-Invariant Flatness of ReLU Neural Networks pdf

Tie-Yan Liu, Qi Meng, Wei Chen, 2019, ArXiv.

Differential Equations for Modeling Asynchronous Algorithms pdf

Tie-Yan Liu, Qi Meng, Wei Chen, 2018, IJCAI.

Complex-valued neural-operator-assisted soliton identification.

Qi Meng, Yue Wang, Deng Zhang, 2023, Physical review. E.

Machine-Learning Non-Conservative Dynamics for New-Physics Detection pdf

Qi Meng, Max Tegmark, Wei Chen, 2021, Physical review. E.

Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics pdf

Lijun Wu, Qi Meng, Zhi-Ming Ma, 2021, Neurocomputing.

Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD pdf

Qi Meng, Huishuai Zhang, Wei Chen, 2021, ArXiv.

Interpreting the Basis Path Set in Neural Networks

Wei Chen, Qi Meng, Zhiming Ma, 2021, Journal of Systems Science and Complexity.

Constructing the Basis Path Set by Eliminating the Path Dependency pdf

Yue Wang, Wei Chen, Qi Meng, 2020, Journal of Systems Science and Complexity.

Interpreting the Basis Path Set in Neural Networks

Wei Chen, Qi Meng, Juanping Zhu, 2019, J. Syst. Sci. Complex..

UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost

Tie-Yan Liu, Tao Qin, Lijun Wu, 2021, NAACL.

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks

Wei Chen, Qi Meng, Bohan Wang, 2020, ICML.

Target Transfer Q-Learning and Its Convergence Analysis

Tie-Yan Liu, Qi Meng, Wei Chen, 2018, Neurocomputing.

The Implicit Regularization for Adaptive Optimization Algorithms on Homogeneous Neural Networks

Tie-Yan Liu, Wei Chen, Qi Meng, 2022 .

Asynchronous Stochastic Gradient Descent with Delay Compensation pdf

Nenghai Yu, Tie-Yan Liu, Qi Meng, 2016, ICML.

Asynchronous Stochastic Proximal Optimization Algorithms with Variance Reduction

Tie-Yan Liu, Qi Meng, Wei Chen, 2016, AAAI.

Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation

Yue Wang, Zhi-Ming Ma, Qi Meng, 2023, 2302.05104.

𝒪-GNN: incorporating ring priors into molecular modeling

Tie-Yan Liu, Tao Qin, Lijun Wu, 2023, ICLR.

Power-law Dynamic arising from machine learning

Zhi-Ming Ma, Wei Chen, Qi Meng, 2023, arXiv.org.

IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL

Tie-Yan Liu, Wei Chen, Qingpeng Cai, 2019, IJCAI.

Deep Latent Regularity Network for Modeling Stochastic Partial Differential Equations

Yue Wang, Qi Meng, Rongchan Zhu, 2023, AAAI.