Probably actually reading/writing
March 5, 2020 — October 11, 2023
Stuff that I am currently actively reading or otherwise working upon. If you are looking at this, and you aren’t me, you may need to consider reevaluating your hobbies.
1 Triage
2 Notes
I need to reclassify the bio computing links; that section has become confusing and there are too many nice ideas there not clearly distinguished.
3 Currently writing
Not all published yet, expect broken links.
Singularity lite, the orderly retreat from relevance
Is residual prediction different to adversarial prediction?

 Movement design
 Returns on hierarchy
 Effective collectivism
 Alignment
 Emancipating my tribe, the cruelty of collectivism (and why I love it anyway)
 Institutions for angels
 Institutional allignment
 Beliefs and rituals of tribes
 Where to deploy taboo
 The Great Society will never feel great, merely be better than the alternatives
 Egregores etc
 Player versus game
Something about the fungibility of hipness and cash
What even are GFlownets?
What is an energy based model?? tl;dr branding for models that handle likelihoods though a potential function which is not normalised to be a density. I do not think there is anything new there per se
Funnyshape learning
 Causal attention
 graphical ML
 gradient message passing
 All inference is already variational inference
Human learner series
 Our moral wetware
 Something about universal grammar and its learnable local approximations, versus universal ethics and its learnable local approximations. Morality by template, computational difficulty of moral identification. Leading by example of necessity.
 Burkean conservatism is about unpacking when moral training data is Outofdistribution
 Morality under uncertainty and computational constraint
 Superstimuli
 Clickbait bandits
 correlation construction
 Moral explainability
 Akrasia in stochastic processes: What timeintegrated happiness should we optimise?
 ~~Comfort traps ~~ ✅ Good enough for now
Myths✅ a few notes is enough
Classification and society series
Shouting at each other on the internet series (Teleological liberalism)
 The Activist and decoupling games, and gamechanging.
 lived evidence deductions and/or ad hominem for discussing genetic arguments.
 diffusion of responsibility — is this distinct from messenger shooting?
 Iterative game theory of communication styles
 Invasive arguments
 Coalition games
 All We Need Is Hate
 Speech standards
 Player versus game
 Startup justice warriors/move fast and cancel things
Pluralism✅
Learning in context
Epistemic community design
 Scientific community
 Messenger shooting
 Experimental ethics and surveillance
 Steps to an ecology of mind
 Epistemic bottlenecks is probably in this series too.
 Ensemble strategies at the population level. I don’t need to guess right, we need a society in which people in aggregate guess in a calibrated way.
Epistemic bottlenecks and bandwidth problems
 Information versus learning as a fundamental question of ML. When do we store exemplars on disk? When do we gradient updates? How much compute to spend on compressing?
 What is special about science? One thing is transmissibility. Can chatGPT do transmission? Or is it 100% tacit? How does explainability relate to transmissibility?
Tail risks and epistemic uncertainty
Enclosing the intellectual commons as economic dematerialisation
Academic publications as Veblen goods
Haunting and exchangeability. Connection to interpolation, and individuation, and to legibility, and nonparametrics.
Something about the limits of legible fairness versus metis in common property regimes
anthropic principles✅ Good enoughYou can’t talk about us without us❌ what did I even mean? something about mottes and baileys?subculture dynamics✅ Good enoughOpinion dynamics (memetics for beginners)✅ Good enoughIterative game theory under bounded rationality❌ too generalMemetics❌ (too big, will never finish)Cradlesnatch calculator✅ Good enough
4 music stuff
5 Misc
 Transforming Probability Spaces
 Does not CGD find a pursuit basis?
6 Workflow optimisation
 Shell Integration  Documentation  iTerm2  macOS Terminal Replacement
 josStorer/chatGPTBox: Integrating ChatGPT into your browser deeply, everything you need is here
 GPT Everywhere: The Ultimate AI Assistant App for Seamless Integration with Your Files, Keyboard Shortcuts, Whisper AI, and Custom LLaMAs
7 graphical models
 versus autodiff: There and Back Again: A Tale of Slopes and Expectations  Mathematics for Machine Learning
 Zhoubin
 Montanari
 Machine Learning — Graphical Model Exact inference (Variable elimination, Belief propagation, Junction tree)  by Jonathan Hui
 scribe_note_lecture13.pdf
 Belief propagation 
 gss2013_11344.pdf
8 “transfer” learning
 Bernhard Schölkopf: From statistical to causal learning
 Bernhard Schölkopf: Learning Causal Mechanisms (ICLR invited talk)
 thuml/TransferLearningLibrary: Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
 Transfer Learning — Transfer Learning Library 0.0.24 documentation
 thuml/ARoadmapforTransferLearning
9 Custom diffusion
 GitHub  PRIVCreation/AwesomeDiffusionPersonalization: A collection of resources on personalization with diffusion models.
 GitHub  PRIVCreation/UniDiffusion: A Diffusion training toolbox based on diffusers and existing SOTA methods, including Dreambooth, Texual Inversion, LoRA, Custom Diffusion, XTI, ….
10 Commoncog
 Start Here: Commoncog’s Best Posts  Commoncog
 The 2022 Commoncog Recap  Commoncog
 Setting the Business Expertise Series Free  Commoncog
 Reading (nonfiction) books for presentself vs futureself  Self Improvement Inputs  The Commonplace Community
 On Moving Fast and How to Move Faster  Self Improvement Inputs  The Commonplace Community
 The Commonplace Community
 Top topics  The Commonplace Community
 Commoncog  Commoncog
11 Music skills
12 Internal
13 ICML 2023 workshop
 Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators  ICML 2023 Workshop, Honolulu, Hawaii — ICML 2023
 Structured Probabilistic Inference & Generative Modeling @ ICML — ICML 2023
 Duality Principles for Modern ML — ICML 2023
 Synergy of Scientific and Machine Learning Modeling — ICML 2023
14 Neurips 2022 followups
 The Symbiosis of Deep Learning and Differential Equations (DLDE)
 NeurIPS 2022 Workshop DLDE  OpenReview
 Arya et al. (2022) — stochastic gradients are more general than deterministic ones because they are defined on discrete vars
 Rudner et al. (2022)
 Phillips et al. (2022) — diffusions in the spectral domain allow us to handle continuous function valued inputs
 Gahungu et al. (2022)
 Wu, Maruyama, and Leskovec (2022) LEPDE is a learnable lowrank approximation method
 Holl, Koltun, and Thuerey (2022) — Physics loss via forward simulations, without the need for sensitivity.
 Neural density estimation
 Metrics for inverse design and inverse inference problems  the former is in fact easier. Or is it? can we simply attain forward prediction loss?
 Noise injection in emulator learning (see refs in Su et al. (2022))
15 Conf, publication venues
16 Neurips 2022
 NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decisionmaking Systems
 SBM @ NeurIPS
 Causal dynamics
 The Symbiosis of Deep Learning and Differential Equations (DLDE)
 Machine Learning and the Physical Sciences, NeurIPS 2022
 AI for Science: Progress and Promises
 Machine Learning Street Talk
17 Neurips 2021
 Storchastic: A Framework for General Stochastic Automatic Differentiation
 Causal Inference & Machine Learning: Why now?
 RealTime Optimization for Fast and Complex Control Systems
 [2104.13478] Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
 Cheng Soon Ong, Marc Peter Deisenroth  There and Back Again: A Tale of Slopes and Expectations (“Lets unify automatic differentiation, integration and mesage passing”
 David Duvenaud, J. Zico Kolter, Matt Johnson  Deep Implicit Layers: Neural ODEs, Equilibrium Models and Beyond
18 Music
Nestup / cutelabnyc/nestedtuplets: Fancy javascript for manipulating nested tuplets.
19 Hot topics
 Beyond Message Passing: a PhysicsInspired Paradigm for Graph Neural Networks
 WeeSun Lee on GNNs
 How GNNs and Symmetries can help to solve PDEs  Max Welling
 Equations of Motion from a Time Series
 Path Integrals and Feynman Diagrams for Classical Stochastic Processes
 Inference for Stochastic Differential Equations
 George Ho, Modern Computational Methods for Bayesian Inference: A Reading List is a good curation of modern Bayes methods posts. The next links come from there
 will wolf on neural methods in SimulationBased Inference
 will wolf, Deriving ExpectationMaximization
 will wolf, Deriving MeanField Variational Bayes
 Reality Is Just a Game Now
 Michael Bronstein, Graph Neural Networks as gradient flows, re: [2206.10991] Graph Neural Networks as Gradient Flows: understanding graph convolutions via energy
 M Bronstein’s ICLR 2021 Keynote, Geometric Deep Learning: The Erlangen Programme of ML
 How to write a great research paper
 The Notion of “Double Descent”
 Jaan on translating between variational terminology in physics and ML
 Sander on waveform audio
 yuge shi’s ELBO gradient post is excellent
 Francis Bach, the many faces of integration by parts.
 Bubeck on hot results in learning theory takes him far from the world of mirror descent, where i first met him. Also lectures well, IMO.
 Causality for Machine Learning
20 Stein stuff
22 GP research
 https://www.patreon.com/posts/newlinearized69325387
 Regressionbased covariance functions for nonstationary spatial modeling
 kalmanjax/sde_gp.py at master · AaltoML/kalmanjax
 AaltoML/kalmanjax: Approximate inference for Markov Gaussian processes using iterated Kalman smoothing, in JAX
22.1 Invenia’s GP expansion ideas
 Gaussian Processes: from one to many outputs
 Implementing a scalable multioutput GP model with exact inference
 Scaling multioutput Gaussian process models with exact inference
 wesselb/stheno: Gaussian process modelling in Python
 Linear Models from a Gaussian Process Point of View with Stheno and JAX
23 SDEs, optimisation and gradient flows
Nguyen and Malinsky (2020)
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.
24 Career tips and metalearning
Making the right moves: A Practical Guide to Scientific Management for Postdocs and New Faculty
There is a Q&A site about this, Academia stackexchange
For early career types, classic blog Thesis Whisperer
Read Academic worklifebalance survey to feel like not bothering with academe.
AI research: the unreasonably narrow path and how not to be miserable
How to Become the Best in the World at Something
This is how skill stacking works. It’s easier and more effective to be in the top 10% in several different skills — your “stack” — than it is to be in the top 1% in any one skill.
25 Ensembles and particle methods
26 Foundations of ML
So much Michael Betancourt.
 Probability Theory (For Scientists and Engineers)
 Course Notes 7: Gaussian Process Engineering  Michael Betancourt on Patreon
 Conditional Probability Theory (For Scientists and Engineers)
 Autodiff for Implicit Functions Paper Live Stream Wed 1/12 at 11 AM EST  Michael Betancourt on Patreon
 New Autodiff Paper  Michael Betancourt on Patreon
 Rumble in the Ensemble
 Scholastic Differential Equations  Michael Betancourt on Patreon
 Identity Crisis
 Invited Talk: Michael Bronstein
 Product Placement
 (Not So) Free Samples
 Updated Geometric Optimization Paper
 We Built Sparse City
 Rumble in the Ensemble