Learn the Universe -- an ML X Cosmology Workshop

Aug 24, 2021, 8:00 AM → Aug 27, 2021, 5:35 PM America/New_York

2nd Floor, IDA (Flatiron Institute)

Learn the Universe -- an ML X Cosmology Workshop

Tuesday, August 24 - Thursday, August 26

Interactive Day on Friday, August 27

10:00 am - Workshop Day Open

5:00 pm - Workshop Day Close

 

Slack - https://join.slack.com/t/learntheuniverse/shared_invite/zt-ui30qzx3-8dcvUXXGi4PvY2q3MpBGpwhttps://join.slack.com/t/learntheuniverse/shared_invite/zt-ui30qzx3-8dcvUXXGi4PvY2q3MpBGpw

Tuesday, August 24

9:30 AM Breakfast

1 Introduction- Welcome & Outline of the workshop

Structured Section: Simulations Based Inference

Chair: Francisco Villaescusa-Navarro

2 Roger de Belsunce: Unbiased inference from large-scale CMB data using likelihood-approximation schemes

REMOTE

3 ChangHoon Hahn: Higher-Order LSS with SBI

4 Ben Horowitz: hyphy - Conditional Posterior Surrogate Modeling of Hydrodynamical Physics

REMOTE

5 Boryana Hadzhiyska: TBD

6 Digvijay Wadekar : Symbolic regression for cluster mass estimation

11:45 AM AM Break

7 Unstructured Section: Problems we can't solve with current tools that we may have a shot with ML

Chair: Simone Ferraro & Colin Hill

1:00 PM Lunch

Structured Section: Extracting non-Gaussian information

Chair: Andrina Nicola

8 Sihao Cheng: The scattering transform in cosmology, or, a CNN without Training

9 Kate Storey-Fisher: Emulation of Summary Statistics for Cosmology from Galaxy Surveys

10 Agnès Ferté: Categorizing cosmological models with unsupervised learning

11 Colin Hill: Non-Gaussian Information in CMB Secondary Anisotropies

12 Luisa Lucie-Smith: Deep learning insights into dark matter halo formation

REMOTE

3:45 PM PM Break

13 Unstructured Section: Have non-Gaussian statistics been made redundant?

Chair: Zoltan Haiman

5:00 PM Workshop Social

Wednesday, August 25

9:30 AM Breakfast

Structured Section: Simulation X ML

Chair: Sultan Hassan

14 Francisco Villaescusa-Navarro: The Cosmology and Astrophysics with Machine Learning Simulations (CAMELS) project

15 Siamak Ravanbakhsh: deep Networks for Spherical Data

16 Neerav Kaushal: Mapping from Fast Simulations to Full N-body Simulations

17 Yin Li: Cosmological Forward Modeling with Adjoint Method

18 Leander Thiele: DeepSets applied to Clusters: Machine learning the Lagrangian way

11:45 AM AM Break

Unstructured Section: Pitch your Astro challenge in 5 mins Or Pitch your method in 5 mins

Chair: ChangHoon Hahn and Miles Cranmer

1:00 PM Lunch

Structured Section: Robust ML for science

Chair: Shirley Ho

19 Biwei Dai: Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis

20 David Yallup : Principled Bayesian Neural Networks

21 Miles Cranmer: Histogram Pooling Operators for Interpretable Deep Learning in Cosmology

22 Anima Anandkumar: AI4 Science A revolution in the making

REMOTE

23 Michael Eickenberg: Wavelet Modulus Integrals for Parameter Estimation

3:45 PM PM Break

Unstructured Section: ML 4 Science - Promises and Problems

Chair: Viviana Acquaviva

5:00 PM Workshop Dinner

Thursday, August 26

9:30 AM Breakfast

Unstructured Section: The State of Affairs in Cosmology Post-Pandemic

Chair: David Spergel

11:00 AM AM Break

Structured Section: Cosmological Applications

Chair: Alice Pisani

24 Andrina Nicola : Forecasting cosmological and astrophysical constraints from electron-matter cross-correlations

25 Christina Kreisch: Precision Cosmology from Voids in the Machine Learning Era

26 Ira Wolfson: The Fault In Our Spectrum: A 'no go' on small field models analytics

27 Adrian Bayer: The Look-Elsewhere Effect

28 Max Lee: Gradient based inference in cosmology using MADLens

29 Alina Sabyr: Cosmological Constraints from Weak Lensing Peaks: Can Halo Models Accurately Predict Peak Counts?

1:00 PM Lunch

Structured Section: Robust ML for science

Chair: Shirley Ho

30 Anima Anandkumar, “ AI4 Science A revolution in the making “

REMOTE

31 Greg Bryan, Introducing the Simons Collaboration “Learning the Universe”

32 Rachel Somerville: New methods to model galaxy formation so that we can Learn the Universe

33 Ana Maria Delgado: Modeling Galaxy-Halo connection with Machine Learning

34 Sultan Hassan: HIFlow: Fast Emulator of HI maps using Normalizing Flow

3:45 PM PM Break

Unstructured Section: What qualifies as interpretability? Do we need it?

Chair: Julia Kempe and Vanessa Bohm

5:00 PM Workshop Reception

Friday, August 27

9:30 AM Breakfast

Hack Day: (Flexible)

11:15 AM AM Break

Hack Day: (Flexible)

1:00 PM Lunch

Hack Day: (Flexible)

3:15 PM PM Break

Hack Day: (Flexible)