no code implementations • 7 Jun 2023 • Biwei Dai, Uros Seljak
We propose Multiscale Flow, a generative Normalizing Flow that creates samples and models the field-level likelihood of two-dimensional cosmological data such as weak lensing.
no code implementations • 27 May 2022 • Richard D. P. Grumitt, Biwei Dai, Uros Seljak
We propose a general purpose Bayesian inference algorithm for expensive likelihoods, replacing the stochastic term in the Langevin equation with a deterministic density gradient term.
no code implementations • 10 Feb 2022 • Biwei Dai, Uros Seljak
TRENF is also a generative model of the data, and we show that TRENF samples agree well with the N-body simulations it trained on, and that the inverse mapping of the data agrees well with a Gaussian white noise both visually and on various summary statistics: when this is perfectly achieved the resulting p(x|y) likelihood analysis becomes optimal.
no code implementations • 21 Dec 2020 • George Stein, Uros Seljak, Biwei Dai
Anomaly detection is a key application of machine learning, but is generally focused on the detection of outlying samples in the low probability density regions of data.
no code implementations • 6 Oct 2020 • Biwei Dai, Uros Seljak
In this work we propose Lagrangian Deep Learning (LDL) for this purpose, applying it to learn outputs of cosmological hydrodynamical simulations.
2 code implementations • ICML Workshop INNF 2021 • Biwei Dai, Uros Seljak
We develop an iterative (greedy) deep learning (DL) algorithm which is able to transform an arbitrary probability distribution function (PDF) into the target PDF.
Ranked #2 on Image Generation on Fashion-MNIST