Zobrazeno 1 - 10
of 973
pro vyhledávání: '"Li, Weijian"'
We develop a first-order accelerated algorithm for a class of constrained bilinear saddle-point problems with applications to network systems. The algorithm is a modified time-varying primal-dual version of an accelerated mirror-descent dynamics. It
Externí odkaz:
http://arxiv.org/abs/2409.18285
Autor:
Li, Weijian, Pavel, Lacra
We consider seeking generalized Nash equilibria (GNE) for noncooperative games with coupled nonlinear constraints over networks. We first revisit a well-known gradientplay dynamics from a passivity-based perspective, and address that the strict monot
Externí odkaz:
http://arxiv.org/abs/2408.12536
Modern deep neural networks often require distributed training with many workers due to their large size. As worker numbers increase, communication overheads become the main bottleneck in data-parallel minibatch stochastic gradient methods with per-i
Externí odkaz:
http://arxiv.org/abs/2406.13936
Incorporating Gradients to Rules: Towards Lightweight, Adaptive Provenance-based Intrusion Detection
As cyber attacks grow increasingly sophisticated and stealthy, it becomes more imperative and challenging to detect intrusion from normal behaviors. Through fine-grained causality analysis, provenance-based intrusion detection systems (PIDS) demonstr
Externí odkaz:
http://arxiv.org/abs/2404.14720
Autor:
Hu, Jerry Yao-Chieh, Chang, Pei-Hsuan, Luo, Robin, Chen, Hong-Yu, Li, Weijian, Wang, Wei-Po, Liu, Han
We introduce an Outlier-Efficient Modern Hopfield Model (termed $\mathrm{OutEffHop}$) and use it to address the outlier inefficiency problem of {training} gigantic transformer-based models. Our main contribution is a novel associative memory model fa
Externí odkaz:
http://arxiv.org/abs/2404.03828
Autor:
Xu, Chenwei, Huang, Yu-Chao, Hu, Jerry Yao-Chieh, Li, Weijian, Gilani, Ammar, Goan, Hsi-Sheng, Liu, Han
We introduce the \textbf{B}i-Directional \textbf{S}parse \textbf{Hop}field Network (\textbf{BiSHop}), a novel end-to-end framework for deep tabular learning. BiSHop handles the two major challenges of deep tabular learning: non-rotationally invariant
Externí odkaz:
http://arxiv.org/abs/2404.03830
We present STanHop-Net (Sparse Tandem Hopfield Network) for multivariate time series prediction with memory-enhanced capabilities. At the heart of our approach is STanHop, a novel Hopfield-based neural network block, which sparsely learns and stores
Externí odkaz:
http://arxiv.org/abs/2312.17346
Autor:
Liao, Haofu, RoyChowdhury, Aruni, Li, Weijian, Bansal, Ankan, Zhang, Yuting, Tu, Zhuowen, Satzoda, Ravi Kumar, Manmatha, R., Mahadevan, Vijay
We present a new formulation for structured information extraction (SIE) from visually rich documents. It aims to address the limitations of existing IOB tagging or graph-based formulations, which are either overly reliant on the correct ordering of
Externí odkaz:
http://arxiv.org/abs/2307.07929
Decoding the linguistic intricacies of the genome is a crucial problem in biology, and pre-trained foundational models such as DNABERT and Nucleotide Transformer have made significant strides in this area. Existing works have largely hinged on k-mer,
Externí odkaz:
http://arxiv.org/abs/2306.15006
We introduce the concept of programmable feature engineering for time series modeling and propose a feature programming framework. This framework generates large amounts of predictive features for noisy multivariate time series while allowing users t
Externí odkaz:
http://arxiv.org/abs/2306.06252