Group Meetings

Biweekly Group Meetings

The group organizes regular weekly meetings that can be found at this indico. Meetings are held on Thursdays at noon Pacific Time. Anyone in the Berkeley community (campus and lab, including affiliates) interested in hearing about or working on developing, adapting, or deploying machine learning in fundamental physics is welcome to participate. The goal of these meetings is to discuss technical and methodological aspects of work in progress and to foster cross-cutting research and collaboration. Please subscribe to hep-ml@lbl.gov to receive reminders and updates about meetings. Meetings are hybrid – see email announcements for the room number.

The code of conduct for our meetings can be found here.

Upcoming meetings:

  • Sign up for future meetings is here.

Past meetings:

  • Dec. 14, 2023. New data representation for detector understanding: a large language model approach (Xiangyang Ju/LBNL).
  • Nov. 30, 2023. Partonic Frontiers: mapping present and future of TMDs and shaping collinear PDF analysis with Neural Networks (Chiara Bissolotti/ANL).
  • Nov. 16, 2023. Toward Realistic Hyperon Reconstruction using Deep Learning in the PANDA Experiment (Adeel Akram/Uppsala).
  • Oct. 12, 2023. Learned optimizers: why they’re the future, why they’re hard, and what they can do now (Jascha Sohl-Dickstein/Google; joint with BIDMaP on campus).
  • Sep. 28, 2023. Re-imagining the search for fundamental interactions with machine learning (Ben Nachman/LBNL; joint with BIDMaP on campus).
  • Sep. 21, 2023. Geometric transformers for reconstruction in the IceCube experiment (Troels Petersen/NBI).
  • Sep. 14, 2023. 1-minute introductions (joint with BIDMaP on campus).
  • Sep. 7, 2023. A shot in the dark: How CMS searches for new particles in the dark sector (Benedikt Maier/KIT).
  • May 11, 2023. Probing Hotspots on the CMB with Neural Networks (Soubhik Kumar/LBNL).
  • May 4, 2023. Multi-GPU Training on Perlmutter (Andrew Naylor/NERSC).
  • April 13, 2023. Incorporating Hard Physics Constraints in Convolutional Neural Networks for Electrodynamics (Alex Scheinker/LANL).
  • April 6, 2023. “Do you need a distance?” Optimal Transport for High Energy Physics (Tianji Cai/UCSB).
  • March 9, 2023. The Noise Injection Phase Diagram, Deep Learning Dynamics & Implicit Regularization (Noam Levi/Tel Aviv U.).
  • March 2, 2023. Interpretable Machine Learning for Neutrinoless Double-Beta Decay Searches in 76Ge (Julieta Gruszko/UNC).
  • Feb. 23, 2023. Manifold Learning via Quantum Dynamics (Mohan Sarovar/Sandia).
  • Feb. 9, 2023. Upsampling Hydrodynamical Simulations for Realistic Mock Gaia Catalogs (Kailash Raman/LBNL).
  • Feb. 2, 2023. System for Optimised Fast Inference code Emit (SOFIE) (Lorenzo Moneta/CERN).
  • Dec. 8, 2022. Building foundations for scientific machine learning at scale (Michael Mahoney/LBNL/UCB).
  • Dec. 1, 2022. Teaching Machine Learning in a 4-Year College: Hands-on and Interdisciplinary (Xiaosheng Huang/USF).
  • Nov. 10, 2022. Generative Modeling of Particle Physics Data (Sascha Diefenbacher/Hamburg).
  • Nov. 3, 2022. Training neural networks using gradient-based and non-gradient-based algorithms (Stephen Whitelam/LBNL).
  • Oct. 27, 2022. From Images to Dark Matter: End-To-End Inference of Substructure From Hundreds of Strong Gravitational Lenses (Sebastian Wagner-Carena/Stanford/SLAC).
  • Oct. 20, 2022. CaloScore: Score-based Generative Models for Calorimeter Shower Simulation (Vinicius Mikuni/NERSC).
  • Oct. 13, 2022. Anomaly Detection with Multiple Reference Datasets (Mayee Chen/Stanford).
  • Oct. 7, 2022. Neural Fields and Differentiable Programming for Quantum Sensing in the MAGIS Experiment (Sean Gasiorowski/SLAC).
  • Sep. 29, 2022. ML in applied nuclear physics (Marco Salthe/LBNL).
  • Sep. 15, 2022. Symmetry Group Equivariant NNs (Mariel Pettee/LBNL).
  • Sep. 9, 2022. The future of ML in HEP (Recap of Snowmass) (Ben Nachman/LBNL).
  • May 19, 2022. Data and Analytics Services (Wahid Bhimji/NERSC).
  • April 21, 2022. CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals (Sam Klein/U. Geneva).
  • April 14, 2022. GIGA-Lens: A Fast Differentiable Lens Modeling Framework (Andi Gu/UCB).
  • April 7, 2022. ML for Planetary Science / Overview of Bayesian Mars (Abby Azari/UCB and SSI).
  • March 31, 2022. Industry Career Panel.
  • March 24, 2022. Non-Parametric Data-Driven Background Modelling using Conditional GANs (Elliot Reynolds/LBNL).
  • March 17, 2022. Using the ONNX open standard for machine learning (Aishik Ghosh/LBNL and UCI).
  • March 10, 2022. Adaptive ML-guided workflows at scale (Vincent Pascuzzi/BNL).
  • March 3, 2022. Hyperparameter Optimization with HYPPO (Juliane Mueller and Vincent Dumont/LBNL).
  • February 24, 2022. Real-time Gravitational Wave Inference with Normalizing Flows (Max Dax/Max Planck Institute for Intelligent Systems).
  • February 17, 2022. Evolutionary RL for self-assembly (Stephen Whitelam/LBNL).
  • February 3, 2022. Bayesian Inference for heavy-ion observables with JETSCAPE (Raymond Ehlers/UCP and LBNL).
  • January 13, 2022. Probabilistic Surrogate Networks for Simulators with Unbounded Randomness (Andreas Munk/UBC).
  • December 16, 2021. Isolated Photon Hadron Correlations in pp and p–Pb Collisions at 5.02 TeV at ALICE (Fernando Torales Acosta/UCB).
  • December 15, 2021. Quantifying the Quark Gluon Plasma (Matthew Heffernan/McGill).
  • December 8, 2021. Real-time dynamics of lattice field theories via machine learning (Yukari Yamauchi/Maryland).
  • December 2, 2021. CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows (Claudius Krause/Rutgers).
  • November 18, 2021. Online-Compatible Unsupervised Anomaly Detection (Vinicius Mikuni).
  • November 11, 2021. The Danger of ML-Decorrelating Uncertainties (Aishik Ghosh).
  • November 4, 2021. The information content of jet quenching and machine learning assisted observable design (James Mulligan).
  • October 28, 2021. Snowmass Discussion.
  • October 18, 2021. Training event: hyper parameter optimization (Daniel Murnane, Vanessa Bohem, Jordan Ott).
  • October 14, 2021. A first data result with deep learning-based unfolding (Ben Nachman).
  • October 7, 2021. Normalizing Flow Monte Carlo (Uros Seljak).
  • September 30, 2021. GPU Neutrino Detector Simulation (Stefano Roberto Soleti).
  • September 16, 2021. Welcome and White House RFI for AI/ML Task Force.
  • May 27, 2021. Overview of the Berkeley Lab CS Area and ML (Peter Nugent).
  • May 20, 2021. Enhancing Astronomical Transient Classification via Deep Learning and Multi-messenger data (Antonino Cucchiara).
  • May 13, 2021. Inference of neutrino flavor evolution through data assimilation and neural differential equations (Ermal Rrapaj).
  • May 6, 2021. Deep Learning Surrogates for Hydrodynamics in Cosmological Simulations (Peter Harrington and Ben Horowitz).
  • April 29, 2021. Switching ML Frameworks (Shuo Han, Xiangyang Ju, Scott Kravitz, Daniel Murnane).
  • April 22, 2021. Symmetry Discovery (Krish Desai).
  • April 15, 2021. Efficient Edge AI for Real-Time Detector Readout (Nhan Tran/FNAL).
  • April 8, 2021. Funding Discussion.
  • April 1, 2021. FPGA-accelerated Deep Learning Controller for Ultrafast Lasers and Accelerators (Qiang Du).
  • March 25, 2021. Human-understandable GAN to elucidate parton showers (Yu Shi Lai).
  • March 18, 2021. ML for Pulsar Timing Arrays (Marat Freytsis).
  • March 11, 2021. Uncertainty-aware neural networks (Aishik Ghosh).
  • March 4, 2021. Anomaly Detection for Stellar Streams (David Shih).
  • February 25, 2021. The LHC Olympics Anomaly Detection Challenge (Ben Nachman).
  • February 18, 2021. Graph Neural Networks for top quark physics (Ryan Roberts).
  • February 11, 2021. Graph Neural Network (Xiangyang Ju).
  • February 4, 2021. Particle Tracking (Daniel Murname).
  • January 28, 2021. MADLens – Fast, accurate and differentiable simulations of weak cosmic lensing (Vanessa Bohm).
  • January 21, 2021. ML Reconstruction for Neutrino Detectors (Jack Newsom and Ethan Lu).
  • January 14, 2021. Self-Supervised Representation Learning for Astronomical Images (George Stein).
  • December 10, 2020. Parameter Estimation using Neural Networks in the Presence of Detector Effects (Adi Suresh).
  • December 3, 2020. Generative Models for the CMB (Giuseppe Puglisi).
  • November 19, 2020. ML at LZ and Anomaly Detection for DESI (Scott Kravitz, Alex Kim, Vanessa Bohem).
  • November 5, 2020. Welcome and Expectations, Roundtable Introductions, Plans and Goals of the Group.