Stuff that I am currently actively reading. If you are looking at this, and you aren’t me, you should really be re-evaluating your hobbies.

See also my more aspirational paper reading list.

- Invited Talk - Michael Bronstein · SlidesLive
- [2104.13478] Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

## Hydrology

## home internet stuff

## Foundations

- Product Placement
- (Not So) Free Samples | Michael Betancourt on Patreon
- Sampling Case Study Live Stream Wed 4/14 at 2 PM EDT | Michael Betancourt on Patreon
- Updated Geometric Optimization Paper | Michael Betancourt on Patreon
- We Built Sparse City | Michael Betancourt on Patreon
- Modeling Sparsity Case Study Live Stream Tue 6/8 at 2 PM EDT | Michael Betancourt on Patreon

## GP research

- Bayesian inference with INLA
- R-INLA Project
- Linear Models from a Gaussian Process Point of View with Stheno and JAX · Invenia Blog
- Regression-based covariance functions for nonstationary spatial modeling
- kalman-jax/sde_gp.py at master · AaltoML/kalman-jax
- Probability Theory (For Scientists and Engineers)
- Scaling multi-output Gaussian process models with exact inference · Invenia Blog
- wesselb/stheno: Gaussian process modelling in Python

## Ai for music fun pack

- neuralfunkv2 - Google Drive
- neuralfunkv2.ipynb - Colaboratory
- GitHub - chrisdonahue/wavegan: WaveGAN: Learn to synthesize raw audio with generative adversarial networks
- AI generates endless break beats (NeuralFunk vol.2) - YouTube

https://djtechtools.com/2020/07/14/best-ai-platforms-to-help-you-make-music/

https://www.patreon.com/loudlystudio

Open AI Jukebox is the latest hot generative music thing that I should be across. I would personally take a rather different approach to them to solve this problem, but they are the current benchmark.

## Misc

Jaan on translating between variational terminology in physics and ML

Francis Bach, the many faces of integration by parts.

Efficiently sampling functions from Gaussian process posteriors

https://jaan.io/what-is-variational-autoencoder-vae-tutorial/

Whittle likelihood

“Sethuraman” rep of Dirichlet proc = stick breaking

Bubeck on hot results in learning theory takes him far from the world of mirror descent. Also lectures well, IMO.

## learning SDEs

- [1912.05509] The Wasserstein-Fourier Distance for Stationary Time Series
- [2001.04385] Universal Differential Equations for Scientific Machine Learning
- 18.337J/6.338J: Parallel Computing and Scientific Machine Learning
- 2007.09660.pdf
- 2010.00746.pdf
- 978-0-387-21540-2_8.pdf
- AaltoML/SDE: Example codes for the book Applied Stochastic Differential Equations
- An Implicit/Explicit CUDA-Accelerated Solver for the 2D Beeler-Reuter Model
- DiffEqFlux.jl – A Julia Library for Neural Differential Equations
- DiffEqFlux.jl: Generalized Physics-Informed and Scientific Machine Learning (SciML) · DiffEqFlux.jl
- DifferentialEquations.jl: Scientific Machine Learning (SciML) Enabled Simulation and Estimation · DifferentialEquations.jl
- dnncode/Spatio-Temporal-Model-for-SPDE: Statistical Modeling for Spatio-Temporal Data from Physical Convection-Diffusion Processes
- Empirical Arithmetic Averaging Over the Compact Stiefel Manifold - IEEE Journals & Magazine
- Generalizing Automatic Differentiation to Automatic Sparsity, Uncertainty, Stability, and Parallelism - Stochastic Lifestyle
- GitHub - mitmath/18303 at spring19
- Global Sensitivity Analysis · DifferentialEquations.jl
- Hilbert space methods for reduced-rank Gaussian process regression
- How can the general Green’s function of a linear homogeneous differential equation be derived? - Mathematics Stack Exchange
- ICERM SciML conf
- Introduction to Scientific Machine Learning 2: Physics-Informed Neural Networks - YouTube
- Introduction to Scientific Machine Learning through Physics-Informed Neural Networks
- JB_grothendieck_proof.pdf
- JuliaSim - Julia Computing
- kar12Supple.pdf
- Kolmogorov Backward Equations
- mitmath/18303: 18.303 - Linear PDEs course
- ModelingToolkit, Modelica, and Modia: The Composable Modeling Future in Julia - Stochastic Lifestyle
- Neural SDEs: Deep Generative Models in the Diffusion Limit - Maxim Raginsky - YouTube
- NeuralNetDiffEq.jl: A Neural Network solver for ODEs
- Noise Processes · DifferentialEquations.jl
- Parameter Estimation and Bayesian Analysis · DifferentialEquations.jl
- Physics-Informed Neural Networks solver · NeuralPDE.jl
- SciML: Open Source Software for Scientific Machine Learning* random_fields.pdf
- SciML/DiffEqFlux.jl: Universal neural differential equations with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
- SciML/NeuralPDE.jl: Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
- SciML/SciMLTutorials.jl: Tutorials for doing scientific machine learning (SciML) and high-performance differential equation solving with open source software.
- Score-Based Generative Modeling through Stochastic Differential Equations
- Seminars & Workshops | DATA DRIVEN SCIENCE & ENGINEERING
- Solving Systems of Stochastic PDEs and using GPUs in Julia - Stochastic Lifestyle
- Structured Random Matrices
- Verdinelli , Wasserman : Hybrid Wasserstein distance and fast distribution clustering
- willtebbutt/TemporalGPs.jl: Fast inference for Gaussian processes in problems involving time

## General emulation

## Spectral bizness

- QuantEcon/lecture-source-jl: Source files for “Lectures in Quantitative Economics” -- Julia version
- mschauer/Kalman.jl: Flexible filtering and smoothing in Julia
- QuantEcon.jl/kalman.jl at master · QuantEcon/QuantEcon.jl
- Whittle.pdf
- time_series - spectral_estimation.pdf
- mschauer/Kalman.jl: Flexible filtering and smoothing in Julia
- A First Look at the Kalman Filter – Quantitative Economics with Julia
- How a Kalman filter works, in pictures | Bzarg

## SDEs in optimisation

To explore: Gradient flows gradient flow.

Statistical Inference via Convex Optimization.

Conjugate functions illustrated.

Francis Bach on the use of geometric sums and a different take by Julyan Arbel.

Tutorial to approximating differentiable control problems. An extension of this is universal differential equations.

## No comments yet. Why not leave one?