1

Optimal Eye Surgeon: Finding image priors through sparse generators at initialization
We introduce Optimal Eye Surgeon (OES), a framework for pruning and training deep image generator networks. Typically, untrained deep …
Avrajit Ghosh, Xitong Zhang, Kenneth K Sun, Qing Qu, Saiprasad Ravishankar, Rongrong Wang
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
While task-agnostic debiasing provides notable generalizability and reduced reliance on downstream data, its impact on language …
Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue, Avrajit Ghosh, Bidhan Bashyal, Rongrong Wang, Kristen Johnson
Inferring Metabolic States from Single Cell Transcriptomic Data via Geometric Deep Learning
The ability to measure gene expression at single-cell resolution has elevated our understanding of how biological features emerge from …
Holly R Steach, Siddharth Viswanath, Yixuan He, Xitong Zhang, Natalia Ivanova, Matthew Hirn, Michael Perlmutter, Smita Krishnaswamy
PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent
Fine-tuning pretrained language models (PLMs) for downstream tasks is a large-scale optimization problem, in which the choice of the …
Guangliang Liu, Zhiyu Xue, Xitong Zhang, Kristen Johnson, Rongrong Wang
Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
It is well known that the finite step-size in Gradient Descent (GD) implicitly regularizes solutions to flatter minima. A natural …
Avrajit Ghosh, He Lyu, Xitong Zhang, Rongrong Wang
PDF Cite Slides
Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion
OpenFWI dataset
Chengyuan Deng, Shihang Feng, Hanchen Wang, Xitong Zhang, Peng Jin, Yinan Feng, Qili Zeng, Yinpeng Chen, Youzuo Lin
PDF Cite Project
Unsupervised learning of full-waveform inversion: Connecting CNN and partial differential equation in a loop
This paper investigates unsupervised learning of Full-Waveform Inversion (FWI) by integrating PDE and CNN in a loop.
Peng Jin, Xitong Zhang, Yinpeng Chen, Sharon Xiaolei Huang, Zicheng Liu, Youzuo Lin
PDF Cite
Unsupervised learning of full-waveform inversion: Connecting CNN and partial differential equation in a loop
Magnet: A neural network for directed graphs
We proposed a directed graph neural network based on a complex Hermitian matrix known as the Magnetic Laplacian.
Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, Matthew Hirn
PDF Cite Code
Magnet: A neural network for directed graphs
Shoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms
Trading security threshold estimation by dynamic graph embedding.
Xitong Zhang, He Zhu, Jiayu Zhou
PDF Cite
Shoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms
Boosted trajectory calibration for traffic state estimation
Traffic state estimation is among the most critical issues in intelligent transport systems, and it has been widely explored for years …
Xitong Zhang, Liyang Xie, Zheng Wang, Jiayu Zhou
PDF Cite
Boosted trajectory calibration for traffic state estimation