( events)   Timezone: »  
Workshop
Mon Dec 13 06:00 AM -- 03:30 PM (PST)
Machine Learning and the Physical Sciences
Anima Anandkumar · Kyle Cranmer · Mr. Prabhat · Lenka Zdeborová · Atilim Gunes Baydin · Juan Carrasquilla · Emine Kucukbenli · Gilles Louppe · Benjamin Nachman · Brian Nord · Savannah Thais





The "Machine Learning and the Physical Sciences" workshop aims to provide a cutting-edge venue for research at the interface of machine learning (ML) and the physical sciences. This interface spans (1) applications of ML in physical sciences (“ML for physics”) and (2) developments in ML motivated by physical insights (“physics for ML”).

ML methods have had great success in learning complex representations of data that enable novel modeling and data processing approaches in many scientific disciplines. Physical sciences span problems and challenges at all scales in the universe: from finding exoplanets in trillions of sky pixels, to finding ML inspired solutions to the quantum many-body problem, to detecting anomalies in event streams from the Large Hadron Collider, to predicting how extreme weather events will vary with climate change. Tackling a number of associated data-intensive tasks including, but not limited to, segmentation, 3D computer vision, sequence modeling, causal reasoning, generative modeling, and efficient probabilistic inference are critical for furthering scientific discovery. In addition to using ML models for scientific discovery, tools and insights from the physical sciences are increasingly brought to the study of ML models.

By bringing together ML researchers and physical scientists who apply and study ML, we expect to strengthen the interdisciplinary dialogue, introduce exciting new open problems to the broader community, and stimulate the production of new approaches to solving challenging open problems in the sciences. Invited talks from leading individuals in both communities will cover the state-of-the-art techniques and set the stage for this workshop, which will also include contributed talks selected from submissions. The workshop will also feature an expert panel discussion on “Physics for ML" and a breakout session dedicated to community building will serve to foster dialogue between physical science and ML research communities.

Session 1 | Opening remarks (Live intro)
Session 1 | Invited talk: Max Welling, "Accelerating simulations of nature, both classical and quantum, with equivariant deep learning" (Invited talk (live))
Session 1 | Invited talk Q&A: Max Welling (Live Q&A)
Session 1 | Invited talk: Bingqing Cheng, "Predicting material properties with the help of machine learning" (Invited talk (live))
Session 1 | Invited talk Q&A: Bingqing Cheng (Live Q&A)
Session 1 | Contributed talk: Tian Xie, "Crystal Diffusion Variational Autoencoder for Periodic Material Generation" (Contributed talk (live))
Session 1 | Poster session (Poster session (Gather.town))
Session 2 | Opening remarks (Live intro)
Session 2 | Panel discussion: Jennifer Chayes, Marylou Gabrié, Michela Paganini, Sara Solla, Moderator: Lenka Zdeborová (Live panel discussion)
Session 2 | Invited talk: Megan Ansdell, "NASA's efforts & opportunities to support ML in the Physical Sciences" (Invited talk (live))
Session 2 | Invited talk Q&A: Megan Ansdell (Live Q&A)
Session 2 | Contributed talk: George Stein, "Self-supervised similarity search for large scientific datasets" (Contributed talk (live))
Session 2 | Poster session (Poster session (Gather.town))
Session 3 | Opening remarks (Live intro)
Session 3 | Invited talk: Surya Ganguli, "From the geometry of high dimensional energy landscapes to optimal annealing in a dissipative many body quantum optimizer" (Invited talk (live))
Session 3 | Invited talk Q&A: Surya Ganguli (Live Q&A)
Session 3 | Invited talk: Laure Zanna, "The future of climate modeling in the age of machine learning" (Invited talk (live))
Session 3 | Invited talk Q&A: Laure Zanna (Live Q&A)
Session 3 | Contributed talk: Maximilian Dax, "Amortized Bayesian inference of gravitational waves with normalizing flows" (Contributed talk (live))
Session 3 | Community development breakouts (Community breakout session (Gather.town))
Session 3 | Feedback from community development breakouts and closing remarks (Live feedback)
Partial-Attribution Instance Segmentation for Astronomical Source Detection and Deblending (Poster)
Equivariant and Modular DeepSets with Applications in Cluster Cosmology (Poster)
Deterministic particle flows for constraining SDEs (Poster)
Crystal Diffusion Variational Autoencoder for Periodic Material Generation (Poster)
Deep-SWIM: A few-shot learning approach to classify Solar WInd Magnetic field structures (Poster)
Deep-DFT: Physics-ML hybrid method to predict DFT energy using Transformer (Poster)
Can semi-supervised learning reduce the amount of manual labelling required for effective radio galaxy morphology classification? (Poster)
Quantum Machine Learning for Radio Astronomy (Poster)
A Convolutional Autoencoder-Based Pipeline For Anomaly Detection And Classification Of Periodic Variables (Poster)
S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Process (Poster)
Rethinking Graph Transformers with Spectral Attention (Poster)
A simple equivariant machine learning method for dynamics based on scalars (Poster)
Multiway Ensemble Kalman Filter (Poster)
Critical parametric quantum sensing with machine learning (Poster)
Discovering PDEs from Multiple Experiments (Poster)
An Imperfect machine to search for New Physics: systematic uncertainties in a machine-learning based signal extraction (Poster)
Physics-enhanced Neural Networks in the Small Data Regime (Poster)
Vision transformers and techniques for improving solar wind speed forecasts using solar EUV images (Poster)
Inferring dark matter substructure with global astrometry beyond the power spectrum (Poster)
Classical variational simulation of the Quantum Approximate Optimization Algorithm (Poster)
Cross-Modal Virtual Sensing for Combustion Instability Monitoring (Poster)
Amortized Variational Inference for Type Ia Supernova Light Curves (Poster)
Uncertainty Aware Learning for High Energy Physics With A Cautionary Tale (Poster)
Weight Pruning and Uncertainty in Radio Galaxy Classification (Poster)
Implicit Quantile Neural Networks for Jet Simulation and Correction (Poster)
Physics-informed neural network for inversely predicting effective electric permittivities of metamaterials (Poster)
Fast synthesis and inversion of spectral lines in stellar chromospheres with graph networks (Poster)
Learning governing equations of interacting particle systems using Gaussian process regression (Poster)
End-To-End Online sPHENIX Trigger Detection Pipeline (Poster)
Normalizing Flows for Random Fields in Cosmology (Poster)
Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows (Poster)
Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector (Poster)
The Quantum Trellis: A classical algorithm for sampling the parton shower with interference effects (Poster)
Automatic differentiation approach for reconstructing spectral functions with neural networks (Poster)
Cooperative multi-agent reinforcement learning outperforms decentralized execution in high-dimensional nonequilibrium control for steady-state design (Poster)
Embedding temporal error propagation on CNN for unsteady flow simulations (Poster)
A Granular Method for Finding Anomalous Light Curves and their Analogs (Poster)
Machine learning accelerated particle-in-cell plasma simulations (Poster)
Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs (Poster)
Modeling Advection on Directed Graphs using Mat\'{e}rn Gaussian Processes for Traffic Flow (Poster)
Neural Symplectic Integrator with Hamiltonian Inductive Bias for the Gravitational N-body Problem (Poster)
PlasmaNet: a framework to study and solve elliptic differential equations using neural networks in plasma fluid simulations (Poster)
An Emulation Framework for Fire Front Spread (Poster)
Generative models for hadron shower simulation (Poster)
Detecting Spatiotemporal Lightning Patterns: An Unsupervised Graph-Based Approach (Poster)
Photometric Redshifts for Cosmology: Improving Accuracy and Uncertainty Estimates Using Bayesian Neural Networks (Poster)
Scalable Bayesian Optimization Accelerates Process Optimization of Penicillin Production (Poster)
Rethinking the modeling of the instrumental response of telescopes with a differentiable optical model (Poster)
Error Analysis of Kilonova Surrogate Models (Poster)
Equivariant Transformers for Neural Network based Molecular Potentials (Poster)
Amortized Bayesian inference of gravitational waves with normalizing flows (Poster)
Efficient kernel methods for model-independent new physics searches (Poster)
DeepBO: Deep Neural-Network Bayesian Optimization of Polaritonic Metasurfaces in Continuous Space (Poster)
Real-time Detection of Anomalies in Multivariate Time Series of Astronomical Data (Poster)
Predicting flux in Discrete Fracture Networks via Graph Informed Neural Networks (Poster)
Score-based Graph Generative Model for Neutrino Events Classification and Reconstruction (Poster)
Simultaneous Multivariate Forecast of Space Weather Indices using Deep Neural Network Ensembles (Poster)
Fast Approximate Model for the 3D Matter Power Spectrum (Poster)
Using physics-informed regularization to improve extrapolation capabilities of neural networks (Poster)
A General Method for Calibrating Stochastic Radio Channel Models with Kernels (Poster)
Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference (Poster)
Missing Data Imputation for Galaxy Redshift Estimation (Poster)
Variational framework for partially-measured physical system control (Poster)
Using Mask R-CNN to detect and mask ghosting and scattered-light artifacts in astronomical images (Poster)
Learning Discrete Neural Reaction Class to Improve Retrosynthesis Prediction (Poster)
Analysis of ODE2VAE with Examples (Poster)
Automatically detecting anomalous exoplanet transits (Poster)
E(2) Equivariant Self-Attention for Radio Astronomy (Poster)
Symmetries and self-supervision in particle physics (Poster)
Probing the Structure of String Theory Vacua with Genetic Algorithms and Reinforcement Learning (Poster)
Probabilistic neural networks for predicting energy dissipation rates in geophysical turbulent flows (Poster)
Marrying the benefits of Automatic and Numerical Differentiation in Physics-Informed Neural Network (Poster)
Robustness of deep learning algorithms in astronomy - galaxy morphology studies (Poster)
Neural quantum states for supersymmetric quantum gauge theories (Poster)
Mixture-of-Experts Ensemble with Hierarchical Deep Metric Learning for Spectroscopic Identification (Poster)
Equivariant graph neural networks as surrogate for computational fluid dynamics in 3D artery models (Poster)
Optimizing High-Dimensional Physics Simulations via Composite Bayesian Optimization (Poster)
Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance (Poster)
Bayesian Stokes inversion with Normalizing flows (Poster)
Fine-tuning Vision Transformers for the Prediction of State Variables in Ising Models (Poster)
Unsupervised Spectral Unmixing for Telluric Correction using a Neural Network Autoencoder (Poster)
Crystal graph convolutional neural networks for per-site property prediction (Poster)
Symmetry Discovery with Deep Learning (Poster)
Accelerator Tuning with Deep Reinforcement Learning (Poster)
Simulation-Based Inference of Strong Gravitational Lensing Parameters (Poster)
Uncertainty quantification for ptychography using normalizing flows (Poster)
Deep Surrogate for Direct Time Fluid Dynamics (Poster)
Towards Improved Global River Discharge Prediction in Ungauged Basins Using Machine Learning and Satellite Observations (Poster)
Learning Size and Shape of Calabi-Yau Spaces (Poster)
Galaxy Morphological Classification with Efficient Vision Transformer (Poster)
Online Bayesian Optimization for Beam Alignment in the SECAR Recoil Mass Separator (Poster)
A New sPHENIX Heavy Quark Trigger Algorithm Based on Graph Neutral Networks (Poster)
Machine Learning and Dynamical Models for Sub-seasonal Climate Forecasting (Poster)
Supplementing Recurrent Neural Network Wave Functions with Symmetry and Annealing to Improve Accuracy (Poster)
Self-supervised similarity search for large scientific datasets (Poster)
A debiasing framework for deep learning applied to the morphological classification of galaxies (Poster)
Sharpness-Aware Minimization for Robust Molecular Dynamics Simulations (Poster)
Turbo-Sim: a generalised generative model with a physical latent space (Poster)
G-SpaNet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention (Poster)
Unbiased Monte Carlo Cluster Updates with Autoregressive Neural Networks (Poster)
Extending turbulence model uncertainty quantification using machine learning (Poster)
Using Deep Learning for estimation of river surface elevation from photogrammetric Digital Surface Models (Poster)
Neural Tensor Contractions and the Expressive Power of Deep Neural Quantum States (Poster)
Neural network is heterogeneous: Phase matters more (Poster)
Robust and Provably Monotonic Networks (Poster)
DeepZipper: A Novel Deep Learning Architecture for Lensed Supernovae Identification (Poster)
Single Image Super-Resolution with Uncertainty Estimation for Lunar Satellite Images (Poster)
Using neural networks to reduce communication in numerical solution of partial differential equations (Poster)
Neural density estimation and uncertainty quantification for laser induced breakdown spectroscopy spectra (Poster)
Explaining machine-learned particle-flow reconstruction (Poster)
Factorized Fourier Neural Operators (Poster)
Detecting Low Surface Brightness Galaxies with Mask R-CNN (Poster)
Deep learning techniques for a real-time neutrino classifier (Poster)
Unsupervised topological learning approach of crystal nucleation in pure Tantalum (Poster)
Stochastic Adversarial Koopman Model for Dynamical Systems (Poster)
An ML Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters (Poster)
A posteriori learning for quasi-geostrophic turbulence parametrization (Poster)
Re-calibrating Photometric Redshift Probability Distributions Using Feature-space Regression (Poster)
RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network (Poster)
Learning the solar latent space: sigma-variational autoencoders for multiple channel solar imaging (Poster)
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion (Poster)
Proximal Biasing for Bayesian Optimization and Characterization of Physical Systems (Poster)
Digital Twin Earth - Coasts: Developing a fast and physics-informed surrogate model for coastal floods via neural operators (Poster)
Stronger symbolic summary statistics for the LHC (Poster)
Calibrating Electrons and Photons in the CMS ECAL using Graph Neural Networks (Poster)
Differentiable Strong Lensing for Complex Lens Modelling (Poster)
Visualization of nonlinear modal structures for three-dimensional unsteady fluid flows with customized decoder design (Poster)
Graph Segmentation in Scientific Datasets (Poster)
Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning (Poster)
Nonlinear pile-up separation with LSTM neural networks for cryogenic particle detectors (Poster)
Classifying Anomalies THrough Outer Density Estimation (CATHODE) (Poster)
Probabilistic segmentation of overlapping galaxies for large cosmological surveys. (Poster)
3D Pre-training improves GNNs for Molecular Property Prediction (Poster)
A data-driven wall model for the prediction of turbulent flow separation over periodic hills (Poster)
Inorganic Synthesis Reaction Condition Prediction with Generative Machine Learning (Poster)
Electromagnetic Counterpart Identification of Gravitational-wave candidates using deep-learning (Poster)
Noether Networks: Meta-Learning Useful Conserved Quantities (Poster)
Approximate Latent Force Model Inference (Poster)
CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation (Poster)
A deep ensemble approach to X-ray polarimetry (Poster)
Out of equilibrium learning dynamics in physical allosteric resistor networks (Poster)
Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations (Poster)
Rethinking Neural Networks with Benford's Law (Poster)
Learning the exchange-correlation functional from nature with differentiable density functional theory (Poster)
Model Inversion for Spatio-temporal Processes using the Fourier Neural Operator (Poster)
Approximate Bayesian Computation for Physical Inverse Modeling (Poster)
A Quasi-Universal Neural Network to Model Structure Formation in the Universe (Poster)
Phenomenological classification of the Zwicky Transient Facility astronomical event alerts (Poster)
Learning Full Configuration Interaction Electron Correlations with Deep Learning (Poster)
A Multi-Survey Dataset and Benchmark for First Break Picking in Hard Rock Seismic Exploration (Poster)
Characterizing γ-ray maps of the Galactic Center with neural density estimation (Poster)