Annotated guide to Beyond the Observable

IAIFI Fellow, MIT

Carolina Cuesta-Lazaro

Art: "Drawing Hands" by M.C. Escher

A Machine Learning perspective on modern Cosmology

Start with the crime scene!

Think about other people in the field working on similar things.

 

How is your voice different?

Does your talk reflect this in every part, even introduction?

1-Dimensional

Machine Learning

Secondary anisotropies

Galaxy formation

Intrinsic alignments

DESI / SphereX / Hetdex

Euclid / LSST

SO / CMB-S4

Ligo / Einstein

The era of Big Data Cosmology

xAstrophysics

HERA / CHIME

SAGA / MANGA

Galaxy formation

Emitters Census

Reionization

Cosmic Microwave Background

Galaxies / Dwarfs

21 cm

Galaxy Surveys

Gravitational Lensing

Gravitational Waves

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

AGN Feedback/Supernovae

It's not a review talk, bring it back to who you are

How is your voice different?

Does your talk reflect this in every part, even introduction?

The talk should be focused topically, but you can find a sneaky way to let them know that you have broad interests without actually going into them

Why Now?

Beyond tools 

Optimisation

Neural representations

Baryonification

Inflation

Symmetry-preserving ML

Early Universe - JWST

Simulation Based Inference

Epidemiological simulations

Medical Imaging

Natural Language Processing

Exoplanets

Compute

Simulations

Data

ML

Statistics

Physics

What is dark matter made of?

What is driving the accelerated expansion?

How did the Universe begin?

A new way of thinking

 about

physical systems

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

Good Visualizations of Why Now help

GANS

Deep Belief Networks

2006

VAEs

Normalising Flows

BigGAN

Diffusion Models

2014

2017

2019

2022

A folk music band of anthropomorphic autumn leaves playing bluegrass instruments

Contrastive Learning

2023

Meanwhile, on Earth...

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

p(\mathrm{World}|\mathrm{Prompt})
["Genie 2: A large-scale foundation model" Parker-Holder et al (2024)]
p(\mathrm{Drug}|\mathrm{Properties})
["Generative AI for designing and validating easily synthesizable and structurally novel antibiotics" Swanson et al]

Probabilistic ML has made high dimensional inference tractable

1024x1024xTime

["Genie 3: A new frontier for world models" Parker-Holder et al (2025)]

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

smsharma/awesome-neural-sbi

Astrophysics proliferates Simulation-based Inference

on Simulations

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

You'll have to be a bring cringe...

["A point cloud approach to generative modeling for galaxy surveys at the field level"

Cuesta-Lazaro and Mishra-Sharma
International Conference on Machine Learning ICML AI4Astro 2023, Spotlight talk, arXiv:2311.17141]

Base Distribution

Target Distribution

Simulated Galaxy 3d Map

Prompt:

\Omega_m, \sigma_8

Prompt: A person half Yoda half Gandalf

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

Make sure people learn something interesting today, they're looking for signals of whether you will be a good teacher

Some people say you have to say something that sounds overly complicated and technical so that you know you are smart. That sounds very silly to me. It's more impressive if you can take something complicated and make it seem easy. That's the kind of person I want to work with!

Generative Models 101

Maximize the likelihood of the training samples

\hat \phi = \argmax \left[ \log p_\phi (x_\mathrm{train}) \right]
x_1
x_2

Parametric Model

p_\phi(x)

Training Samples

x_\mathrm{train}

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

x_1
x_2

Trained Model

p_\phi(x)

Evaluate probabilities

Low Probability

High Probability

Generate Novel Samples

Simulator

Generative Model

Fast emulators

Testing Theories

Generative Model

Simulator

Generative Models: Simulate and Analyze

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

p(z_0)
p(z_T)
p(z_2)
p(z_1)

Reverse diffusion: Denoise previous step

Forward diffusion: Add Gaussian noise (fixed)

Prompt: A person half Yoda half Gandalf

Diffusion model

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

Summarize the context of why you think what you've done is cool. It might not be obvious for people outside of your subfield

6 seconds / sim  vs 40 million CPU hours

Fast Emulation:

Parameter constraints:

Generative Models: Simulate and Analyze

Diffusion

Pair Counting

Carol's optimistic forecast

\mathcal{O}(10^{4-7})
\mathcal{O}(10)

High dimensional inference

Alternative Clustering Methods

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

Sampling over                                             jointly with theory parameters

+

Constrained Simulations for Galaxy Surveys

100M dimensions

Reconstructing ALL latent variables:

Dark Matter distribution

Entire formation history

Peculiar velocities

Interpretability:

Cross-Correlation with other probes

[Image Credit: Yuuki Omori]

 

Constraining Inflation:

Inferring primordial non-gaussianity

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

Make sure you leave space for all the cool stuff you want to do in the future, and that the connection to who you are and what you've done in the past is obvious

Simulations

Observations

Guided by observational constraints

Robust Inference

Generative Models:

Beyond Simulation Emulation

Part 1

What is driving the accelerated expansion?

Reconstructing latent features:

Dark matter, ICs...

Part 2

How did the Universe begin?

What is dark matter made of?

Anomaly Detection for new physics searches

Baryonic feedback

Hybrid simulators

Part 3

Future Directions

Breaking LCDM

Predictive hydro sims

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

If it makes sense, tell them why you think you'll love it there

Beyond tools 

Compute

Simulations

Data

ML

Statistics

Physics

Use-inspired AI developments

The future of Astrophysics

A new way of thinking

 about

physical systems

Carolina Cuesta-Lazaro IAIFI/MIT @ NYU 2025

Eric Vanden-Eijnden

Kyunghyun Cho

Mehryar Mohri

Yann Lecun

Rob Fergus

CCPP

Denis Zorin

Roman Scoccimarro

Jeremy Tinker

Mike O'Neil

Anthony Pullen

Leslie Greengard

David W. Hogg

Georg Stadler

 

Ken Van Tilburg

Neal Weiner

Olivier Pauluis

Glennys R. Farrar

Edwin P. Berger

Yacine Ali-Haïmoud

Practice with people that have a critical mindset but that you trust, ideally also with people that are not super familiar with your research / field