February 2026

Graph data often contain noisy and spurious correlations that mask the true causal relationships, which are essential for enabling graph models to make predictions based on the underlying causal structure of the data. Dependence on spurious connections makes it challenging for traditional Graph Neural Networks (GNNs) to generalize effectively across different graphs. Furthermore, traditional aggregation methods tend to amplify these spurious patterns, limiting model robustness under distribution shifts. To address these issues, we propose Causal Neighbourhood Learning with […]

Ver mais

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for subgoal discovery and trajectory guidance. While LLMs can support exploration, frequent reliance on LLM calls raises concerns about scalability and reliability. We address these challenges by constructing a memory graph that encodes subgoals and trajectories from both LLM guidance and the agent’s […]

Ver mais

Table of Links Abstract and 1. Introduction 2. Financial Market Model and Worst-Case Optimization Problem 3. Solution to the Post-Crash Problem 4. Solution to the Pre-Crash Problem 5. A BSDE Characterization of Indifferences Strategies 6. The Markovian Case 7. Numerical Experiments Acknowledgments and References Appendix A. Proofs from Section 3 Appendix B. Proofs of BASDE Results from Section 5 Appendix C. Proofs of (CIR) Results from Section 6 Abstract. We study and solve the worst-case optimal portfolio problem […]

Ver mais

Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and abstract priors that facilitate early learning. However, heavy reliance on LLM supervision introduces scalability constraints and dependence on potentially unreliable signals. We propose MIRA (Memory-Integrated Reinforcement Learning Agent), which incorporates a structured, evolving memory graph to guide early training. The graph stores decision-relevant information, including trajectory […]

Ver mais

Lately, you can’t open YouTube, read the news, or scroll LinkedIn without getting hit by the same narrative. Every day, another CEO confidently declares that software engineers are obsolete and that anyone can prompt their way to the next billion-dollar app. And to be fair, the AI world has completely tanked the barrier to entry for prototyping. With AI integrated into workflows, a lean team of 10 people can ship faster and better than a firm with 200 […]

Ver mais

Over the last ten years, running has become a huge part of my life. I’m not sure how useful this write-up will be to others, but running preoccupies me enough that I feel the need to document the journey and externalize my thoughts. On 14.02.2026 (Valentine’s day) I ran my longest trail race: Trail du Mont Agel in Monaco. I expected a picturesque and exciting, yet challenging, adventure. I prepared for it by running 20–30 km every week […]

Ver mais

Reached the stage of parallel agent psychosis where I’ve lost a whole feature – I know I had it yesterday, but I can’t seem to find the branch or worktree or cloud instance or checkout with it in. … found it! Turns out I’d been hacking on a random prototype in /tmp and then my computer crashed and rebooted and I lost the code… but it’s all still there in ~/.claude/projects/ session logs and Claude Code can extract […]

Ver mais

Data collection is a critical component of modern statistical and machine learning pipelines, particularly when data must be gathered from multiple heterogeneous sources to study a target population of interest. In many use cases, such as medical studies or political polling, different sources incur different sampling costs. Observations often have associated group identities (for example, health markers, demographics, or political affiliations) and the relative composition of these groups may differ substantially, both among the source populations and between […]

Ver mais

State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs, is a significant challenge because SSMs are sequence models and the shear graph volumes make it very expensive to convert graphs as sequences for effective learning. In this paper, we propose COMBA to tackle large graph learning using state space models, with two […]

Ver mais

Artificial intelligence (AI) has increasingly transformed medical prognostics by enabling rapid and accurate analysis across imaging and pathology. However, the investigation of machine learning predictions applied to prospectively collected, standardized data from observational clinical intervention trials remains underexplored, despite its potential to reduce costs and improve patient outcomes. Chronic rhinosinusitis (CRS), a persistent inflammatory disease of the paranasal sinuses lasting more than three months, imposes a substantial burden on quality of life (QoL) and societal cost. Although many […]

Ver mais