deck

Initial Conditions of the Universe

Laws of gravity

3-D distribution of galaxies

Which are the ICs of OUR Universe?

Primordial non-Gaussianity?

Probe Inflation

Galaxy formation

3-D distribution of dark matter

Is GR modified on large scales?

How do galaxies form?

Neutrino mass hierarchy?

Dall-E 3

A 2D animation of a folk music band composed of anthropomorphic autumn leaves, each playing traditional bluegrass instruments, amidst a rustic forest setting dappled with the soft light of a harvest moon

"Sparks of Artificial General Intelligence: Early experiments with GPT-4" Bubeck et al

Produce Javascript code that creates a random graphical image that looks like a painting of Kandinsky

Draw a unicorn in TikZ

ChatGPT

Emulation

x \sim p(x|y)

x \sim p(x|y)

Model uncertainties

Likelihood estimation

p(\theta|x_\mathrm{obs})

p(\theta|x_\mathrm{obs})

Complex priors

lensing

arxiv:2206.14820

p_\phi(x)

p_\phi(x)

Data

A parametric PDF

Maximise the likelihood

(or something similar)

Explicit Density

Implicit Density

Tractable Density

Approximate Density

Normalising flows

Variational Autoencoders

Diffusion models

Generative Adversarial Networks

The zoo of generative models

The backbone of vision generative models

Reverse diffusion: Denoise previous step

Forward diffusion: Add Gaussian noise (fixed)

A person half Yoda half Gandalf

Diffusion Models

z_T

z_T

z_{0}

z_{0}

z_{1}

z_{1}

z_{2}

z_{2}

q_\theta(z_{t-1}|z_t)

q_\theta(z_{t-1}|z_t)

p(z_t|z_{t-1})

p(z_t|z_{t-1})

Reverse diffusion: Denoise previous step

Forward diffusion: Add Gaussian noise (fixed)

Cosmology

Diffusion on point clouds

"Diffusion generative modeling for galaxy surveys: emulating clustering for inference at the field level" Carolina Cuesta-Lazaro, Siddarth Mishra-Sharma

Modelling galaxy surveys

p(x,y,z, v_x, v_y, v_z, M_h|\Omega_m, \sigma_8)

p(x,y,z, v_x, v_y, v_z, M_h|\Omega_m, \sigma_8)

Halo Mass Function

Velocity

PDF

Mean pairwise velocity

h_0

h_0

h_1

h_1

h_5

h_5

h_4

h_4

h_2

h_2

h_3

h_3

h_6

h_6

e_{01}

e_{01}

e_{12}

e_{12}

Node features

Edge features

\mathcal{G} = h^{L}_i, e^{L}_{ij} \rightarrow h^{L+1}_i, e^{L+1}_{ij}

\mathcal{G} = h^{L}_i, e^{L}_{ij} \rightarrow h^{L+1}_i, e^{L+1}_{ij}

e^{L+1}_{ij} = \phi_e(e^L_{ij}, h^L_i, h^L_j)

e^{L+1}_{ij} = \phi_e(e^L_{ij}, h^L_i, h^L_j)

edge embedding

h^{L+1}_{i} = \phi_h( h^L_i, \mathcal{A}_j e^{L+1}_{ij})

h^{L+1}_{i} = \phi_h( h^L_i, \mathcal{A}_j e^{L+1}_{ij})

node embedding

Input

noisy halo properties

Output

noise prediction

Tight constraints with only 5000 positions!

\mathcal{L}_T(x) = \sum_{i=1}^T \mathbb{E}_{q(z_{i}|x)} D_{KL} \left[q(z_{i-1} | z_{i}, x) || p_\theta(z_{i-1} | z_{i}) \right]

\mathcal{L}_T(x) = \sum_{i=1}^T \mathbb{E}_{q(z_{i}|x)} D_{KL} \left[q(z_{i-1} | z_{i}, x) || p_\theta(z_{i-1} | z_{i}) \right]

-\log p(x) \leq -\mathrm{VLB}(x)

-\log p(x) \leq -\mathrm{VLB}(x)

D_{KL}(q(z_T|x) || p(z_T)) + \mathbb{E}_{q(z_0|x)} \left[-\log p(x|z_0) \right] + \mathcal{L}_T(x)

D_{KL}(q(z_T|x) || p(z_T)) + \mathbb{E}_{q(z_0|x)} \left[-\log p(x|z_0) \right] + \mathcal{L}_T(x)

Prior loss

Diffusion loss

Reconstruction loss

Be a true Bayesian: Always maximise the likelihood

arxiv:2107.00630

arxiv:2303.00848

Maximum Likelihood = Denoising

25 \, h^{-1}\mathrm{Mpc}

25 \, h^{-1}\mathrm{Mpc}

(Probabilistic) reconstruction of Dark Matter

"Probabilistic Reconstruction of Dark Matter fields from galaxies using diffusion models"
Victoria Ono, Core Francisco Park,  Nayantara Mudur, Yueying Ni, Carolina Cuesta-Lazaro (in prep)

p_\phi(x_\mathrm{DM}|x_\mathrm{Stars})

p_\phi(x_\mathrm{DM}|x_\mathrm{Stars})

Hybrid hydro simulators?

Hybrid simulators

Nbody

Slow

Non-differentiable

Particle mesh

Accurate

Fast

Differentiable

Missing small scales

Nbodyify

Fast

Differentiable

Accurate

"Nbodyify: adaptive mesh corrections for PM simulations" Carolina Cuesta-Lazaro, Chirag Modi (in prep)

\frac{\mathrm{d} \mathbf{x}}{\mathrm{d} a } = \frac{1}{a^3 E(a)}\mathbf{v}

\frac{\mathrm{d} \mathbf{x}}{\mathrm{d} a } = \frac{1}{a^3 E(a)}\mathbf{v}

\frac{\mathrm{d} \mathbf{v}}{\mathrm{d} a } = \frac{1}{a^2 E(a)}\mathbf{F}(\mathbf{x},a)

\frac{\mathrm{d} \mathbf{v}}{\mathrm{d} a } = \frac{1}{a^2 E(a)}\mathbf{F}(\mathbf{x},a)

\mathbf{F}_\theta(\mathbf{x},a) = \frac{3 \Omega_m}{2} \nabla \left[\phi^\mathrm{PM}(\mathbf{x}) + \phi^\mathrm{corr}_\theta(\mathbf{x}, a, \phi^\mathrm{PM}, \delta^\mathrm{PM}) \right]

\mathbf{F}_\theta(\mathbf{x},a) = \frac{3 \Omega_m}{2} \nabla \left[\phi^\mathrm{PM}(\mathbf{x}) + \phi^\mathrm{corr}_\theta(\mathbf{x}, a, \phi^\mathrm{PM}, \delta^\mathrm{PM}) \right]

\mathbf{F}(\mathbf{x},a) = \frac{3 \Omega_m}{2} \nabla \phi^\mathrm{PM}(\mathbf{x})

\mathbf{F}(\mathbf{x},a) = \frac{3 \Omega_m}{2} \nabla \phi^\mathrm{PM}(\mathbf{x})

Gravitational evolution ODE

Particle-mesh

Hybrid Simulator

Low Resolution

CNN learned features

\phi_\mathrm{corr}(x) = g_\theta \left ( \{ \mathrm{CiC}^{-1}(h_\theta(x)), f_\theta(a) \} \right)

\phi_\mathrm{corr}(x) = g_\theta \left ( \{ \mathrm{CiC}^{-1}(h_\theta(x)), f_\theta(a) \} \right)

h (16D)

h (16D)

\delta_\mathrm{LR}

\delta_\mathrm{LR}

\phi_\mathrm{LR}

\phi_\mathrm{LR}

Emulation

x \sim p(x|y)

x \sim p(x|y)

Likelihood estimation

p(\theta|x_\mathrm{obs})

p(\theta|x_\mathrm{obs})

Model uncertainties

Hybrid simulators?

https://calvinyluo.com/2022/08/26/diffusion-tutorial.html

\log p(\boldsymbol{x}) =

\log p(\boldsymbol{x}) =

\geq \mathbb{E}_{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\left[\log\frac{p(\boldsymbol{x}, \boldsymbol{z})}{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\right]

\geq \mathbb{E}_{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\left[\log\frac{p(\boldsymbol{x}, \boldsymbol{z})}{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\right]

\mathbb{E}_{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\left[\log\frac{p(\boldsymbol{x}, \boldsymbol{z})}{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\right] + \mathcal{D}_{\text{KL}}(q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x}) \mid\mid p(\boldsymbol{z}\mid\boldsymbol{x}))

\mathbb{E}_{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\left[\log\frac{p(\boldsymbol{x}, \boldsymbol{z})}{q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x})}\right] + \mathcal{D}_{\text{KL}}(q_{\boldsymbol{\phi}}(\boldsymbol{z}\mid\boldsymbol{x}) \mid\mid p(\boldsymbol{z}\mid\boldsymbol{x}))

Evidence Lower Bound

Distance to true posterior

q_\theta(z|x) \approx p(z|x)

q_\theta(z|x) \approx p(z|x)

Find

1. ELBO is a lower bound of the evidence

2. Maximising ELBO = Minimising KL

Maximise ELBO to maximise ev/likelihood

Maximise ELBO to approximate true posterior

Generative Models in Astrophysics