121 citations · 214 across the 22 of their papers we have counts for
23 papers
Power-law Dynamic arising from machine learning
Wei Chen, Weitao Du, Zhi-Ming Ma +1
We study a kind of new SDE that was arisen from the research on optimization in machine learning, we call it power-law dynamic because its stationary distribution cannot have sub-G…
Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
Rui Zhang, Qi Meng, Rongchan Zhu +5
In scenarios with limited available data, training the function-to-function neural PDE solver in an unsupervised manner is essential. However, the efficiency and accuracy of existi…
Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations
Rui Zhang, Peiyan Hu, Qi Meng +5
Navier-Stokes equations are significant partial differential equations that describe the motion of fluids such as liquids and air. Due to the importance of Navier-Stokes equations,…
Breaking Correlation Shift via Conditional Invariant Regularizer
Mingyang Yi, Ruoyu Wang, Jiachen Sun +2
Recently, generalization on out-of-distribution (OOD) data with correlation shift has attracted great attentions. The correlation shift is caused by the spurious attributes that co…
An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
Shiqi Gong, Qi Meng, Jue Zhang +6
Deep learning methods have been increasingly adopted to study jets in particle physics. Since symmetry-preserving behavior has been shown to be an important factor for improving th…
Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics
Shiqi Gong, Qi Meng, Yue Wang +4
Learning dynamics governed by differential equations is crucial for predicting and controlling the systems in science and engineering. Neural Ordinary Differential Equation (NODE),…
Improved OOD Generalization via Adversarial Training and Pre-training
Mingyang Yi, Lu Hou, Jiacheng Sun +4
Recently, learning a model that generalizes well on out-of-distribution (OOD) data has attracted great attention in the machine learning community. In this paper, after defining OO…
Reweighting Augmented Samples by Minimizing the Maximal Expected Loss
Mingyang Yi, Lu Hou, Lifeng Shang +3
Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples e…
BN-invariant sharpness regularizes the training model to better generalization
Mingyang Yi, Huishuai Zhang, Wei Chen +2
It is arguably believed that flatter minima can generalize better. However, it has been pointed out that the usual definitions of sharpness, which consider either the maxima or the…
Characterization of Excess Risk for Locally Strongly Convex Population Risk
Mingyang Yi, Ruoyu Wang, Zhi-Ming Ma
We establish upper bounds for the expected excess risk of models trained by proper iterative algorithms which approximate the local minima. Unlike the results built upon the strong…
Dynamic of Stochastic Gradient Descent with State-Dependent Noise
Qi Meng, Shiqi Gong, Wei Chen +2
Stochastic gradient descent (SGD) and its variants are mainstream methods to train deep neural networks. Since neural networks are non-convex, more and more works study the dynamic…
Interpreting Basis Path Set in Neural Networks
Juanping Zhu, Qi Meng, Wei Chen +1
Based on basis path set, G-SGD algorithm significantly outperforms conventional SGD algorithm in optimizing neural networks. However, how the inner mechanism of basis paths work re…
Off-policy Learning for Multiple Loggers
Li He, Long Xia, Wei Zeng +3
It is well known that the historical logs are used for evaluating and learning policies in interactive systems, e.g. recommendation, search, and online advertising. Since direct on…
Positively Scale-Invariant Flatness of ReLU Neural Networks
Mingyang Yi, Qi Meng, Wei Chen +2
It was empirically confirmed by Keskar et al.\cite{SharpMinima} that flatter minima generalize better. However, for the popular ReLU network, sharp minimum can also generalize well…
Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting
Yue Wang, Wei Chen, Yuting Liu +2
In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy…
-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Qi Meng, Shuxin Zheng, Huishuai Zhang +3
It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient desce…
Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling
Qi Meng, Wei Chen, Yue Wang +2
When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data acro…
Distribution flows associated with positivity preserving coercive forms
Xian Chen, Zhi-Ming Ma, Xue Peng
For a given quasi-regular positivity preserving coercive form, we construct a family of (-finite) distribution flows associated with the semigroup of the form. The canonical cad…
Markov jump processes in modeling coalescent with recombination
Xian Chen, Zhi-Ming Ma, Ying Wang
Genetic recombination is one of the most important mechanisms that can generate and maintain diversity, and recombination information plays an important role in population genetic…
Quasi regular Dirichlet forms and the stochastic quantization problem
Sergio Albeverio, Zhi Ming Ma, Michael Röckner
After recalling basic features of the theory of symmetric quasi regular Dirichlet forms we show how by applying it to the stochastic quantization equation, with Gaussian space-time…
Fukushima type decomposition for semi-Dirichlet forms
Zhi-Ming Ma, Wei Sun, Li-Fei Wang
We present a Fukushima type decomposition in the setting of general quasi-regular semi-Dirichlet forms. The decomposition is then employed to give a transformation formula for mart…
Fukushima's decomposition for diffusions associated with semi-Dirichlet forms
Li Ma, Zhi-Ming Ma, Wei Sun
Diffusion processes associated with semi-Dirichlet forms are studied in the paper. The main results are Fukushima's decomposition for the diffusions and a transformation formula fo…
A general correspondence between Dirichlet forms and right processes
Sergio Albeverio, Zhi-Ming Ma
The theory of Dirichlet forms as originated by Beurling-Deny and developed particularly by Fukushima and Silverstein, is a natural functional analytic extension of classical (and a…