Publications

• Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes [paper]

B. Tran, B. Shahbaba, S. Mandt, M. Filippone

International Conference on Machine Learning (ICML 2023)

• Deep Anomaly Detection under Labeling Budget Constraints [paper]

A. Li, C. Qiu, P. Smyth, M. Kloft, S. Mandt, M. Rudolph

International Conference on Machine Learning (ICML 2023)

• An Introduction to Neural Data Compression [paper]

Y. Yang, S. Mandt, and L. Theis

Foundations and Trends in Computer Graphics and Vision (2023)

• Insights from Generative Modeling for Neural Video Compression [paper]

R. Yang, Y. Yang, J. Marino, and S. Mandt

Transactions on Pattern Analysis and Machine Intelligence (2023)

• Probabilistic Querying of Continuous-Time Event Sequences [paper]

A. Boyd, Y. Chang, S. Mandt, and P. Smyth

Artificial Intelligence and Statistics (AISTATS 2023)

• Learning to Simulate High Energy Particle Collisions from Unlabeled Data [paper]

J. Howard, S. Mandt, D. Whiteson, and Y. Yang

Scientific Reports 12.1 (2022): 7567

• Predictive Querying for Autoregressive Neural Sequence Models [paper]

A. Boyd, S. Showalter, S. Mandt, and P. Smyth

Neural Information Processing Systems (Oral) (NeurIPS 2022)

• Latent Outlier Exposure for Anomaly Detection with Contaminated Data [paper]

C. Qiu, A. Li, M. Kloft, M. Rudolph, and S. Mandt

International Conference on Machine Learning (ICML 2022)

• Structured Stochastic Gradient MCMC [paper]

A. Alexos, A. Boyd, and S. Mandt

International Conference on Machine Learning (ICML 2022) 

• Raising the Bar in Graph-level Anomaly Detection

C. Qiu, M. Kloft , S. Mandt, and M. Rudolph

International Joint Conference on Artificial Intelligence (IJCAI 2022).

• Making Thermodynamic Models of Mixtures Predictive by Machine Learning: Matrix Completion of Pair Interactions [paper]

F. Jirasek, R. Bamler, S. Fellenz, M. Bortz, M. Kloft, S. Mandt, and H. Hasse

Chemical Science (2022)

• History Marginalization Improves Forecasting in Variational Recurrent Neural Networks [paper]

C. Qiu, S. Mandt, and M. Rudolph

Entropy 23, 1563 (2021) 

• Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning [paper]

A. Li, A. Boyd, P. Smyth, S. Mandt

Neural Information Processing Systems (NeurIPS 2021).

• Neural Transformation Learning for Deep Anomaly Detection Beyond Images [paper]
  C. Qiu, T. Pfrommer, M. Kloft, S. Mandt, and M. Rudolph

International Conference on Machine Learning (ICML 2021).

• Approximately Equivariant Networks for Imperfectly Symmetric Dynamics [paper]
  Rui Wang, Robin Walters, Rose Yu

International Conference on Machine Learning (ICML 2022).

• Multi-Fidelity Hierarchical Neural Process [paper]
  Dongxia Wu, Matteo Chinazzi, Yi-An Ma, Rose Yu
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
  
  

• Neural Point Process for Learning Spatiotemporal Event Dynamics [paper]
  Zihao Zhou, Xingyi Yang, Ryan Rossi, Handong Zhao, Rose Yu
  Annual Conference  on Learning for Dynamics and Control (L4DC), 2022
  
  

• On Optimal Early Stopping: Over-informative versus Under-informative Parametrization  [paper]
  Ruoqi Shen, Liyao Gao, Yian Ma
  
  

• The Adaptive Spectral Koopman Method for Dynamical Systems [paper]
  Bian Li, Yi-An Ma, J Nathan Kutz, Xiu Yang
  
  

• When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint [paper]
  Y Freund, YA Ma, T Zhang
  Journal of Machine Learning Research (JMLR) 2022
  
  

• Automatic Symmetry Discovery with Lie Algebra Convolutional Network [paper]
  Nima Dehmammy, Robin Walter, Yanchen Liu, Dashun Wang, Rose Yu
  Neural Information Processing Systems (NeurIPS 2021).
  
  

• Incorporating Symmetry into Deep Dynamics Models for Improved Generalization [paper]
  Rui Wang, Robin Walters, Rose Yu

International Conference on Learning  Representations (ICLR 2021).

• Quantifying Uncertainty in Deep Spatiotemporal Forecasting [paper][code]
  Dongxia Wu, Liyao Gao, Xinyue Xiong, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2021
  
  

• Accelerating Stochastic Simulation with Spatiotemporal Neural Processes [paper]
  Dongxia Wu, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu
  
  

• Meta-Learning Dynamics Forecasting Using Task Inference [paper]
  Rui Wang, Robin Walters, Rose Yu
  
  

• Physics-Guided Deep Learning for Dynamical Systems: A Survey [paper]
  Rui Wang, Rose Yu
  
  

• Towards Physics-informed Deep Learning for Turbulent Flow Prediction [paper]
  Rui Wang, Karthik Kashinath, Mustafa Mustafa, Adrian Albert, Rose Yu
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020