March 2026

The hardest part of using regular expressions is not crafting regular expressions per se. In my opinion, the two hardest parts are minor syntax variations between implementations, and all the environmental stuff outside of regular expressions per se. Embedded regular expression modifiers address one of the environmental complications by putting the modifier in the regular expression itself. For example, if you want to make a grep search case-insensitive, you pass it the -i flag. But if you want to […]

Ver mais

The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizing prediction in representation space rather than reconstruction in observation space. We argue that the resulting separation from probabilistic generative modeling is largely rhetorical rather than structural: the canonical JEPA design, coupled encoders with a context-to-target predictor, mirrors the variational posteriors and learned conditional priors obtained when variational inference is applied to a particular class of coupled latent-variable models, and standard JEPA […]

Ver mais

Key Highlights – Anthropic is not done building out Cowork. Pre-release UI spotted by TestingCatalog shows a project creation flow in development for Claude Cowork on Desktop, one that would turn the tool from a session-based agent into a persistent, organised workspace. The difference might matter more than it sounds. The addition spotted by TestingCatalog shows a project creation flow within Cowork on Desktop. Users would be able to attach an existing local folder or create a new […]

Ver mais

I decided to do multi agent RL for my bachelor thesis and I created a multi agent enviroment in which I want to benchmark multiple algorithms. I’ve been using the SB3 PPO implementation and it works well enough when I only have one agent, but once I have more than one (even just two) the training completely breaks down. The loss jumps all over the place (from 5, to 10, to 300, 2000, …) and I don’t really […]

Ver mais

Machine learning has opened new frontiers in purely data-driven algorithms for data assimilation in, and for forecasting of, dynamical systems; the resulting methods are showing some promise. However, in contrast to model-driven algorithms, analysis of these data-driven methods is poorly developed. In this paper we address this issue, developing a theory to underpin data-driven methods to solve smoothing problems arising in data assimilation and forecasting problems. The theoretical framework relies on two key components: (i) establishing the existence […]

Ver mais

This chapter presents three major reinforcement learning algorithms used for fine-tuning financial forecasters. We propose a clear implementation plan for backpropagating the loss of a reinforcement learning task to a model trained using supervised learning, and compare the performance before and after the fine-tuning. We find an increase in performance after fine-tuning, and transfer learning properties to the models, indicating the benefits of fine-tuning. We also highlight the tuning process and empirical results for future implementation by practitioners.

Ver mais

Continual learning methods usually preserve old behavior by regularizing parameters, matching old outputs, or replaying previous examples. These strategies can reduce forgetting, but they do not directly specify how the latent representation should evolve. We study a narrower geometric alternative for the regime where old and new data should remain on the same latent support: continual learning as continuation of a shared manifold. We instantiate this view within Support-Preserving Manifold Assimilation (SPMA) and evaluate a geometry-preserving variant, SPMA-OG, […]

Ver mais