Geometric ergodicity of SGLD via reflection coupling

no code implementations • 17 Jan 2023 • Lei LI, Jian-Guo Liu, Yuliang Wang

We consider the geometric ergodicity of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm under nonconvexity settings.

A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics

no code implementations • 19 Jul 2022 • Lei LI, Yuliang Wang

We establish a sharp uniform-in-time error estimate for the Stochastic Gradient Langevin Dynamics (SGLD), which is a popular sampling algorithm.

valid

On uniform-in-time diffusion approximation for stochastic gradient descent

no code implementations • 11 Jul 2022 • Lei LI, Yuliang Wang

The main technique is to establish the exponential decay rates of the derivatives of the solution to the backward Kolmogorov equation.

valid

Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization

2 code implementations • 1 Dec 2019 • Yuchen Guo, Nicholas Hanoian, Zhexiao Lin, Nicholas Liskij, Hanbaek Lyu, Deanna Needell, Jiahao Qu, Henry Sojico, Yuliang Wang, Zhe Xiong, Zhenhong Zou

We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF).

Chatbot