Search Results for author: Xinyan Li

Found 8 papers, 1 papers with code

Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization

no code implementations24 Jul 2019 Xinyan Li, Qilong Gu, Yingxue Zhou, Tiancong Chen, Arindam Banerjee

(2) how can we characterize the stochastic optimization dynamics of SGD with fixed and adaptive step sizes and diagonal pre-conditioning based on the first and second moments of SGs?

Stochastic Optimization

Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances

no code implementations14 Jun 2020 Sijie He, Xinyan Li, Timothy DelSole, Pradeep Ravikumar, Arindam Banerjee

Sub-seasonal climate forecasting (SSF) focuses on predicting key climate variables such as temperature and precipitation in the 2-week to 2-month time scales.

BIG-bench Machine Learning Feature Importance +1

Cloud detection in Landsat-8 imagery in Google Earth Engine based on a deep neural network

no code implementations18 Jun 2020 Zhixiang Yin, Feng Ling, Giles M. Foody, Xinyan Li, Yun Du

This letter proposes a method to directly perform cloud detection in Landsat-8 imagery in GEE based on deep learning (DeepGEE-CD).

Cloud Detection

Experiments with Rich Regime Training for Deep Learning

no code implementations26 Feb 2021 Xinyan Li, Arindam Banerjee

Inspired by this, we investigate probabilistic LWS-SGD, which mostly updates the top layers and occasionally updates the full network.

Inductive Bias

Noisy Truncated SGD: Optimization and Generalization

no code implementations26 Feb 2021 Yingxue Zhou, Xinyan Li, Arindam Banerjee

Our experiments on a variety of benchmark datasets (MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100) with various networks (VGG and ResNet) validate the theoretical properties of NT-SGD, i. e., NT-SGD matches the speed and accuracy of vanilla SGD while effectively working with sparse gradients, and can successfully escape poor local minima.

Learning and Dynamical Models for Sub-seasonal Climate Forecasting: Comparison and Collaboration

1 code implementation29 Sep 2021 Sijie He, Xinyan Li, Laurie Trenary, Benjamin A Cash, Timothy DelSole, Arindam Banerjee

The SSF dataset constructed for the work, dynamical model predictions, and code for the ML models are released along with the paper for the benefit of the broader machine learning community.

Management Weather Forecasting

Stability Based Generalization Bounds for Exponential Family Langevin Dynamics

no code implementations9 Jan 2022 Arindam Banerjee, Tiancong Chen, Xinyan Li, Yingxue Zhou

Recent years have seen advances in generalization bounds for noisy stochastic algorithms, especially stochastic gradient Langevin dynamics (SGLD) based on stability (Mou et al., 2018; Li et al., 2020) and information theoretic approaches (Xu and Raginsky, 2017; Negrea et al., 2019; Steinke and Zakynthinou, 2020).

Generalization Bounds

Cannot find the paper you are looking for? You can Submit a new open access paper.