5.2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- SupélecFR485 papers
- University of Applied Sciences and Arts of Southern SwitzerlandCH485 papers
- New York UniversityUS52 papers
- Google (United States)US16 papers
- Princeton UniversityUS15 papers
- Courant Institute of Mathematical SciencesUS13 papers
- Meta (Israel)IL11 papers
- Massachusetts Institute of TechnologyUS10 papers
- Stanford UniversityUS8 papers
- University of California, BerkeleyUS8 papers
- Cornell UniversityUS7 papers
- Carnegie Mellon UniversityUS6 papers
160 papers · 1 filter
Explainability Matters: Backdoor Attacks on Medical Imaging
Munachiso Nwadike, Takumi Miyawaki, Esha Sarkar +2
Deep neural networks have been shown to be vulnerable to backdoor attacks, which could be easily introduced to the training set prior to model training. Recent work has focused on…
Blackwell Online Learning for Markov Decision Processes
Tao Li, Guanze Peng, Quanyan Zhu
This work provides a novel interpretation of Markov Decision Processes (MDP) from the online optimization viewpoint. In such an online optimization context, the policy of the MDP i…
Power Iteration for Tensor PCA
Jiaoyang Huang, Daniel Z. Huang, Qing Yang +1
In this paper, we study the power iteration algorithm for the spiked tensor model, as introduced in [44]. We give necessary and sufficient conditions for the convergence of the pow…
Comparative Analysis of the Solar Wind: Modeling Charge State Distributions in the Heliosphere
Marcus DuPont, Chengcai Shen, Nicholas A. Murphy
Non-equilibrium ionization (NEI) is a key process often times neglected when modeling astrophysical plasmas with thermodynamical timescales much shorter than the timescales for ion…
Hierarchical clustering in particle physics through reinforcement learning
Johann Brehmer, Sebastian Macaluso, Duccio Pappadopulo +1
Particle physics experiments often require the reconstruction of decay patterns through a hierarchical clustering of the observed final-state particles. We show that this task can…
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
Qiang Zhang, Tete Xiao, Alexei A. Efros +2
At the heart of many robotics problems is the challenge of learning correspondences across domains. For instance, imitation learning requires obtaining correspondence between human…
A splitting method to reduce MCMC variance
Robert J. Webber, David Aristoff, Gideon Simpson
We explore whether splitting and killing methods can improve the accuracy of Markov chain Monte Carlo (MCMC) estimates of rare event probabilities, and we make three contributions.…
NAPA: Neural Art Human Pose Amplifier
Qingfu Wan, Oliver Lu
This is the project report for CSCI-GA.2271-001. We target human pose estimation in artistic images. For this goal, we design an end-to-end system that uses neural style transfer f…
Anomaly Detection in Astronomical Images with Generative Adversarial Networks
Kate Storey-Fisher, Marc Huertas-Company, Nesar Ramachandra +4
We present an anomaly detection method using Wasserstein generative adversarial networks (WGANs) on optical galaxy images from the wide-field survey conducted with the Hyper Suprim…
Learning the Evolution of the Universe in N-body Simulations
Chang Chen, Yin Li, Francisco Villaescusa-Navarro +2
Understanding the physics of large cosmological surveys down to small (nonlinear) scales will significantly improve our knowledge of the Universe. Large N-body simulations have bee…
Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems
Naman Patel, Prashanth Krishnamurthy, Siddharth Garg +1
We show that by controlling parts of a physical environment in which a pre-trained deep neural network (DNN) is being fine-tuned online, an adversary can launch subtle data poisoni…
Average-Case Integrality Gap for Non-Negative Principal Component Analysis
Afonso S. Bandeira, Dmitriy Kunisky, Alexander S. Wein
Montanari and Richard (2015) asked whether a natural semidefinite programming (SDP) relaxation can effectively optimize over $\|\mathbf{x}\…
A Study on the Autoregressive and non-Autoregressive Multi-label Learning
Elham J. Barezi, Iacer Calixto, Kyunghyun Cho +1
Extreme classification tasks are multi-label tasks with an extremely large number of labels (tags). These tasks are hard because the label space is usually (i) very large, e.g. tho…
Independent Gaussian Distributions Minimize the Kullback-Leibler (KL) Divergence from Independent Gaussian Distributions
Song Fang, Quanyan Zhu
This short note is on a property of the Kullback-Leibler (KL) divergence which indicates that independent Gaussian distributions minimize the KL divergence from given independent G…
Reduced Order Models for the Quasi-Geostrophic Equations: A Brief Survey
Changhong Mou, Zhu Wang, David R. Wells +2
Reduced order models (ROMs) are computational models whose dimension is significantly lower than those obtained through classical numerical discretizations (e.g., finite element, f…
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand +6
The early phase of training a deep neural network has a dramatic effect on the local curvature of the loss function. For instance, using a small learning rate does not guarantee st…
Fundamental Limits of Controlled Stochastic Dynamical Systems: An Information-Theoretic Approach
Song Fang, Quanyan Zhu
In this paper, we examine the fundamental performance limitations in the control of stochastic dynamical systems; more specifically, we derive generic bounds that h…
Directional Radio Propagation Path Loss Models for Millimeter-Wave Wireless Networks in the 28-, 60-, and 73-GHz Bands
Ahmed Iyanda Sulyman, Abdulmalik Alwarafy, George R. MacCartney +2
Fifth-generation (5G) cellular systems are likely to operate in the centimeter-wave (3-30 GHz) and millimeter-wave (30-300 GHz) frequency bands, where a vast amount of underutilize…
Modeling Solar Proton Event-induced Martian Surface Radiation Dose
Dimitra Atri, Caitlin MacArthur, Ian Dobbs-Dixon
Solar Proton Events (SPEs) can cause abrupt and significant enhancements to the Martian surface radiation dose. Observations of the impact of SPEs on the Martian surface are availa…
dm2gal: Mapping Dark Matter to Galaxies with Neural Networks
Noah Kasmanoff, Francisco Villaescusa-Navarro, Jeremy Tinker +1
Maps of cosmic structure produced by galaxy surveys are one of the key tools for answering fundamental questions about the Universe. Accurate theoretical predictions for these quan…
Learning Invariances in Neural Networks
Gregory Benton, Marc Finzi, Pavel Izmailov +1
Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present i…
Optimally Supporting IoT with Cell-Free Massive MIMO
Hangsong Yan, Alexei Ashikhmin, Hong Yang
We study internet of things (IoT) systems supported by cell-free (CF) massive MIMO (mMIMO) with optimal linear channel estimation. For the uplink, we consider optimal linear MIMO r…
Clinical prediction system of complications among COVID-19 patients: a development and validation retrospective multicentre study
Ghadeer O. Ghosheh, Bana Alamad, Kai-Wen Yang +10
Existing prognostic tools mainly focus on predicting the risk of mortality among patients with coronavirus disease 2019. However, clinical evidence suggests that COVID-19 can resul…
Learning Principle of Least Action with Reinforcement Learning
Zehao Jin, Joshua Yao-Yu Lin, Siao-Fong Li
Nature provides a way to understand physics with reinforcement learning since nature favors the economical way for an object to propagate. In the case of classical mechanics, natur…