Search Results for author: Wei Deng

Found 16 papers, 8 papers with code

Interacting Contour Stochastic Gradient Langevin Dynamics

1 code implementation ICLR 2022 Wei Deng, Siqi Liang, Botao Hao, Guang Lin, Faming Liang

We propose an interacting contour stochastic gradient Langevin dynamics (ICSGLD) sampler, an embarrassingly parallel multiple-chain contour stochastic gradient Langevin dynamics (CSGLD) sampler with efficient interactions.

Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

1 code implementation23 Dec 2021 Xiang Ling, Lingfei Wu, Jiangyu Zhang, Zhenqing Qu, Wei Deng, Xiang Chen, Chunming Wu, Shouling Ji, Tianyue Luo, Jingzheng Wu, Yanjun Wu

In this paper, we focus on malware with the file format of portable executable (PE) in the family of Windows operating systems, namely Windows PE malware, as a representative case to study the adversarial attack methods in such adversarial settings.

Adversarial Attack Malware Detection +1

On Convergence of Federated Averaging Langevin Dynamics

no code implementations9 Dec 2021 Wei Deng, Yi-An Ma, Zhao Song, Qian Zhang, Guang Lin

Important to our approach is that the communication efficiency does not deteriorate with the injected noise in the Langevin algorithms.

Non-reversible Parallel Tempering for Uncertainty Approximation in Deep Learning

no code implementations29 Sep 2021 Wei Deng, Qian Zhang, Qi Feng, Faming Liang, Guang Lin

Parallel tempering (PT), also known as replica exchange, is the go-to workhorse for simulations of multi-modal distributions.

Information Directed Sampling for Sparse Linear Bandits

no code implementations NeurIPS 2021 Botao Hao, Tor Lattimore, Wei Deng

Stochastic sparse linear bandits offer a practical model for high-dimensional online decision-making problems and have a rich information-regret structure.

Decision Making

A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions

2 code implementations NeurIPS 2020 Wei Deng, Guang Lin, Faming Liang

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics.

An adaptive Hessian approximated stochastic gradient MCMC method

no code implementations3 Oct 2020 Yating Wang, Wei Deng, Guang Lin

The bias introduced by stochastic approximation is controllable and can be analyzed theoretically.

Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction

1 code implementation ICLR 2021 Wei Deng, Qi Feng, Georgios Karagiannis, Guang Lin, Faming Liang

Replica exchange stochastic gradient Langevin dynamics (reSGLD) has shown promise in accelerating the convergence in non-convex learning; however, an excessively large correction for avoiding biases from noisy energy estimators has limited the potential of the acceleration.

Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

2 code implementations ICML 2020 Wei Deng, Qi Feng, Liyao Gao, Faming Liang, Guang Lin

Replica exchange Monte Carlo (reMC), also known as parallel tempering, is an important technique for accelerating the convergence of the conventional Markov Chain Monte Carlo (MCMC) algorithms.

Image Classification

Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications

no code implementations29 Jun 2020 Yating Wang, Wei Deng, Lin Guang

The algorithm utilizes a set of spike-and-slab priors for the parameters in the deep neural network.

Sparse Learning

DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving

2 code implementations17 Feb 2020 Wei Deng, Junwei Pan, Tian Zhou, Deguang Kong, Aaron Flores, Guang Lin

To address the issue of significantly increased serving delay and high memory usage for ad serving in production, this paper presents \emph{DeepLight}: a framework to accelerate the CTR predictions in three aspects: 1) accelerate the model inference via explicitly searching informative feature interactions in the shallow component; 2) prune redundant layers and parameters at intra-layer and inter-layer level in the DNN component; 3) promote the sparsity of the embedding layer to preserve the most discriminant signals.

Click-Through Rate Prediction

An Adaptive Empirical Bayesian Method for Sparse Deep Learning

1 code implementation NeurIPS 2019 Wei Deng, Xiao Zhang, Faming Liang, Guang Lin

We propose a novel adaptive empirical Bayesian method for sparse deep learning, where the sparsity is ensured via a class of self-adaptive spike-and-slab priors.

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