Poster Presentations

Time: Wednesday (12/16/2020) 19:00-22:00 (EST)

We will first have an introduction session in the conference zoom room (that will be available to all registered participants) for about twenty minutes. Each speaker is invited to give a one-minute presentation about the outline of his/her poster. Then, feel free to join the zoom room of each speaker (posted below).

For registered participants, the zoom room is available in your email. You can find the email sent to you with the title "PSU Machine Learning Workshop Information".


  1. Approximation of Functions with Tensor Networks
  2. Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems
  3. Training Sparse Neural Networks using Compressed Sensing
    1. Jianhong Chen
    2. Penn State University, USA
    3. Zoom like: https://psu.zoom.us/j/9431692739

  4. pSVGD: Projected Stein Variational Gradient Descent
  5. Deep Learning of Parameterized Equations with Applications to Uncertainty Quantification
  6. Sparse Harmonic Transforms: Best s-Term Approximation Guarantees for Bounded Orthonormal Product Bases in Sublinear-Time
  7. Quantifying Ancient Landscape Modifications using Machine Learning and Evolutionary Theory: A Case Study from Madagascar
  8. Reduced Training Data for Dynamical Systems
  9. Data-driven learning of nonlocal models: from high-fidelity simulations to constitutive laws
  10. Fast Prediction of Riverine Flow Velocity Using Deep Learning
  11. Nonlinear Reduced Order Modelling of Parametrized PDEs using Deep Neural Networks
  12. Deep Learning-based Reduced Order Models for Real-time Approximation of Nonlinear Time-dependent Parametrized PDEs
  13. Convergence Analysis of the Discovery of Dynamics via Deep Learning
  14. Robust Data-driven Evolutionary PDE Identification from Single Noisy Trajectory
  15. Expedient Hypersonic Aerothermal Prediction for Aerothermoelastic Analysis Via Field Inversion and Machine Learning
  16. Learning Thermodynamically Stable and Galilean Invariant PDEs for Non-equilibrium Flows
  17. New Potential-Based Bounds for Prediction with Expert Advice
  18. Parareal Neural Networks Emulating a Parallel-in-time Algorithm
  19. DeepXDE: A Deep Learning Library for Solving Differential Equations
  20. Deep Bayesian Inference of Nearshore Bathymetry
  21. Robust Learning with Implicit Residual Networks
  22. Consensus-based Optimization on Hypersurfaces
  23. Data Driven Models for Solving Partial Differential Equations
  24. Neural Network Representation of the Probability Density Function of Diffusion Processes
  25. Identifying Eigenfunctions of a Markov Process Using Trajectory Data
  26. Kernel Methods for Bayesian Elliptic Inverse Problems on Manifolds
  27. Learning Diagonal Gaussian Mixture Models and Incomplete Tensor Decompositions
  28. DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
  29. Polynomial Based RKHS - With Applications to Data-Driven Modeling
  30. Solving a Free Boundary System by Using Neural Networks