This workshop focused on substantive connections between machine learning (including but not limited to deep learning) and physics (including astrophysics). Namely, we are interested in topics like imbuing physical laws into training (e.g., physics regularization of layers), learning new physical phenomena from learned models, physics-constrained reinforcement learning, prediction outside training parameters, causal inference, and the (physical) interpretability of models. Registration has closed for this event.
VIDEO PLAYLIST
Links to individual talks/abstracts are also included in the agenda below.
8:15-8:30 Arrival and Registration
8:35-8:40 Logistics & Introduction -- Josh Bloom, UC Berkeley Astronomy
8:40-8:50 Welcome and Introductory Remarks -- UC Berkeley Provost Paul Alivisatos, Chemistry
Producing & Discovering Dynamical Models -- Moderator, Laura Waller
- 8:50-9:06 Data-driven methods for the discovery of governing equations -- J. Nathan Kutz, UW
- 9:06-9:22 AI Feynman: a Physics-Inspired Method for Symbolic Regression -- Silviu-Marian Udrescu, MIT
- 9:22-9:38 Learning physical interaction in many ways -- Jiajun Wu, MIT
- 9:38-9:54 Data Driven Discretization for Partial Differential Equations -- Stephan Hoyer, Google Research
- 9:54-10:10 Solving Astrophysical PDEs with Deep Neural Networks and TensorFlow -- Milos Milosavljevic, The University of Texas at Austin
- 10:10 - 10:25 Session Panel: Producing & Discovering Dynamical Models
- 10:25 - 10:35 Break
Incorporating Physics directly into the Models -- Moderator, Fernando Pérez
- 10:35-10:51 Machine learning for lattice gauge theory -- Phiala Shanahan, MIT
- 10:51-11:07 Physics informed Machine Learning -- Guofei Pang, Brown
- 11:07-11:23 Machine learning in high-energy particle physics experiments, from simulation, through reconstruction to physics analysis -- Heather Gray, UC Berkeley/LBNL
- 11:23-11:39 FPGA-accelerated machine learning inference as a service for particle physics computing -- Miaoyuan Liu, Fermilab
- 11:39-11:55 Physics Constrained Fluid Flow Prediction using Lyapunov's Method -- Ben Erichson, UC Berkeley
- 11:55-12:11 Cosmology for Machine Learning -- Uros Seljak, UC Berkeley/LBNL
- 12:11-12:25 Session Panel: Incorporating Physics directly into the Models
- 12:25-1:00 Lunch
Generative Models -- Moderator, Eric Jonas
- 1:00-1:16 Generative models as priors for signal denoising -- Soledad Villar, NYU
- 1:16-1:32 Flow-based generative models for lattice field theory -- Tej Kanwar, MIT
- 1:32-1:48 Putting Non-Euclidean Geometry to Work in ML: Hyperbolic and Product Manifold Embeddings -- Frederic Sala, Stanford
- 1:48-2:04 Deducing Inference from Hyperspectral Imaging of Materials Using Deep Recurrent Neural Networks -- Joshua Agar, Lehigh University
- 2:04-2:20 Improved learning for materials and chemical structures through symmetry, hierarchy and similarity -- Bert de Jong, LBNL
- 2:20-2:36 Towards a cosmology emulator using Generative Adversarial Networks -- Wahid Bhimji, NERSC/LBNL
- 2:36-2:52 Hybrid Physical - Deep Learning Models for Astronomical Inverse Problems -- François Lanusse, UC Berkeley
- 2:52-3:07 Session Panel: Generative Models
- 3:07-3:15 Break
Learning with Physical Systems -- Moderator, Federica Bianco
- 3:15-3:31 Physics-constrained Computational Imaging -- Laura Waller, UC Berkeley
- 3:31-3:47 Spectral Inference Networks: Unifying Deep and Spectral Learning -- David Pfau, DeepMind
- 3:47-4:03 Noise2Self: Blind Denoising by Self-Supervision -- Joshua Batson, CZ Biohub
- 4:03-4:19 Reinforcement Learning for Materials Synthesis -- Rama Vasudevan, Oak Ridge National Laboratory
- 4:19-4:35 Reinforcement Learning, Control, and Inference -- Sergey Levine, UC Berkeley
- 4:35-4:51 Reducing simulation dependence with deep learning -- Benjamin Nachman, LBNL
- 4:51-5:10 Session Panel: Learning with Physical Systems & Wrap-up
- 5:10-5:30 Group Walk to the Reception - Gather Restaurant (Downtown Berkeley)
- 5:30-7:30 Joint Day 1/Day 2 Reception
Scientific Organizing Committee
Joshua Bloom (UC Berkeley)
Laura Waller (UC Berkeley)
Fernando Perez (UC Berkeley)
David Hogg (NYU)
Kyle Cramner (NYU)
Benjamin Nachman (LBNL)
Local Organizing Committee
Stacey Dorton
Stefan van der Walt
Francois Lanusse
Peter Nugent
If you have any questions, please contact workshop@ml4science.org or Josh Bloom.
Speaker(s)
Joshua Bloom
Josh Bloom an astronomy professor at the University of California, Berkeley, where he teaches high-energy astrophysics, Python bootcamps, and a graduate-level class on Python for data-driven science. He has published more than 250 refereed articles, largely on time-domain transients events and telescope/insight automation. Expressed in his research is output of a collaborative effort between talented astronomers, statisticians, and computer scientists (ranging from students to peers) at the nexus of physics, scalable computation, and machine learning. His book on gamma-ray bursts was published in 2011, as part of the "Frontiers in Physics" series by Princeton University Press. He has been awarded the Pierce Prize from the American Astronomical Society, and he is a former Sloan Fellow, Junior Fellow at the Harvard Society, and Hertz Foundation Fellow. He holds a PhD from Caltech and degrees from Harvard and Cambridge University. Recently, he has working as co-PI of the Moore-Sloan Data Science Initiative at UC Berkeley and an elected member of the management oversight body of the Large Synoptic Survey Telescope (LSST).