BlackHC's Adventures

Sara Hooker’s essay “On the Slow Death of Scaling” (2026) is a thought-provoking piece that deserves a careful read.1 What follows is my interpretation (or perhaps more accurately, a riff) on her arguments, where I’ll both steelman her position and push b…

What is the difference between active learning (and active sampling) and data filtering?

This note explores a seemingly simple yet surprisingly profound example of how rational agents can diverge in their beliefs even when exposed to identical evidence.

Why is the Bayesian model average (BMA) often hailed as the optimal choice for rational actors making predictions under uncertainty?

In the first part of this two-part series on Function-Space Variational Inference (FSVI), we looked at the Data Processing Inequality (DPI).

In information theory, the data processing inequality (DPI) is a powerful concept.

In this blog post, following the previous blog post1 on “Bayesian Appropriation: General Likelihood for Loss Functions”, we will examine and better understand parts of the paper “PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrain…

In this blog post, we explore how some losses could be rewritten as a Bayesian objective using ideas from variational inference—hence, the tongue-in-cheek “Bayesian Appropriation.”

The Rao-Blackwell theorem is a fundamental theorem in statistics that offers a powerful method for improving estimators by conditioning on sufficient statistics.

Software engineering is on the brink of a revolution with the emergence of large language models (LLMs).

While training of deep ensembles or BNNs, we should be able to maximize the BALD score (model disagreement metric) as a regularizer using unlabeled data to improve model diversity and active learning efficiency (or OOD detection) where it matters: for pool

This post introduces a family of much less expensive approximations for BatchBALD that might work well where BatchBALD works.

The paper, accepted as Long Oral at ICML 2022, discusses the (log) marginal likelihood (LML) in detail: its advantages, use-cases, and potential pitfalls, with an extensive review of related work.

The definition of the total variation distance can be confusing (at least to me) as it is formulated as a supremum.

We express common performance metrics, such as recall, precision and so on, for classification tasks using probabilities and examine the F1 score and simplify it to a ratio that is simpler to understand.

This post discusses potential failure cases of outlier exposure—when using “fake” label distributions for outliers—and presents an intellectually pleasing version of outlier exposure in latent space, treating outliers as purely negative samples from a con…

During my day-to-day, I read papers and procrastinate from writing my thesis, so I often come up with high-level questions that I cannot research because I don’t have the experience, time, and computing resources.

This are my notes and observations from reading the Linear Algebra chapter of the Deep Learning book.

I have published a couple of posts on Medium to see how it works: A Dart REPL PoC - Hacking with Dart A well-received post about https://github.com/BlackHC/dart_repl which is a PoC interactive shell for Dart.

Today, I want to release another bit of code from my master’s thesis.