Inspired by recent advances in large language models, foundation models have been developed for zero-shot time series forecasting, enabling prediction on datasets unseen during pretraining. These large-scale models, trained on vast collections of time series, learn generalizable representations for both point and probabilistic forecasting, reducing the need for task-specific architectures and manual tuning. In this work, we review the main architectures, pretraining strategies, and optimization methods used in such models, and study the effect of fine-tuning after pretraining to enhance their performance on specific datasets. Our empirical results show that fine-tuning generally improves zero-shot forecasting capabilities, especially for long-term horizons.

Real-time monitoring of the state of health (SoH) of batteries remains a major challenge, particularly in microgrids where operational constraints limit the use of traditional methods. As part of the 4BLife project, we propose an innovative method based on the analysis of a discharge pulse at the end of the charge phase. The parameters of the equivalent electrical model describing the voltage evolution across the battery terminals during this current pulse are then used to estimate the SoH. Based on the experimental data acquired so far, the initial results demonstrate the relevance of the proposed approach. After training using the parameters of two batteries with a capacity degradation of around 85%, we successfully predicted the degradation of two other batteries, cycled down to approximately 90% SoH, with a mean absolute error of around 1% in the worst case, and an explainability score of the estimator close to 0.9. If these performances are confirmed, this method can be easily integrated into battery management systems (BMS) and paves the way for optimized battery management under continuous operation.

A focused crawler aims at discovering as many web pages and web sites relevant to a target topic as possible, while avoiding irrelevant ones. Reinforcement Learning (RL) has been a promising direction for optimizing focused crawling, because RL can naturally optimize the long-term profit of discovering relevant web locations within the context of a reward. In this paper, we propose TRES, a novel RL-empowered framework for focused crawling that aims at maximizing both the number of relevant web pages (aka \textit{harvest rate}) and the number of relevant web sites (\textit{domains}). We model the focused crawling problem as a novel Markov Decision Process (MDP), which the RL agent aims to solve by determining an optimal crawling strategy. To overcome the computational infeasibility of exhaustively searching for the best action at each time step, we propose Tree-Frontier, a provably efficient tree-based sampling algorithm that adaptively discretizes the large state and action spaces and evaluates only a few representative actions. Experimentally, utilizing online real-world data, we show that TRES significantly outperforms and Pareto-dominates state-of-the-art methods in terms of harvest rate and the number of retrieved relevant domains, while it provably reduces by orders of magnitude the number of URLs needed to be evaluated at each crawling step.

Evolution Strategy (ES) is a powerful black-box optimization technique based on the idea of natural evolution. In each of its iterations, a key step entails ranking candidate solutions based on some fitness score. For an ES method in Reinforcement Learning (RL), this ranking step requires evaluating multiple policies. This is presently done via on-policy approaches: each policy's score is estimated by interacting several times with the environment using that policy. This leads to a lot of wasteful interactions since, once the ranking is done, only the data associated with the top-ranked policies is used for subsequent learning. To improve sample efficiency, we propose a novel off-policy alternative for ranking, based on a local approximation for the fitness function. We demonstrate our idea in the context of a state-of-the-art ES method called the Augmented Random Search (ARS). Simulations in MuJoCo tasks show that, compared to the original ARS, our off-policy variant has similar running times for reaching reward thresholds but needs only around 70% as much data. It also outperforms the recent Trust Region ES. We believe our ideas should be extendable to other ES methods as well.

We present AI-SDC, an integrated suite of open source Python tools to facilitate Statistical Disclosure Control (SDC) of Machine Learning (ML) models trained on confidential data prior to public release. AI-SDC combines (i) a SafeModel package that extends commonly used ML models to provide ante-hoc SDC by assessing the vulnerability of disclosure posed by the training regime; and (ii) an Attacks package that provides post-hoc SDC by rigorously assessing the empirical disclosure risk of a model through a variety of simulated attacks after training. The AI-SDC code and documentation are available under an MIT license at https://github.com/AI-SDC/AI-SDC.

Trusted Research environments (TRE)s are safe and secure environments in which researchers can access sensitive data. With the growth and diversity of medical data such as Electronic Health Records (EHR), Medical Imaging and Genomic data, there is an increase in the use of Artificial Intelligence (AI) in general and the subfield of Machine Learning (ML) in particular in the healthcare domain. This generates the desire to disclose new types of outputs from TREs, such as trained machine learning models. Although specific guidelines and policies exists for statistical disclosure controls in TREs, they do not satisfactorily cover these new types of output request. In this paper, we define some of the challenges around the application and disclosure of machine learning for healthcare within TREs. We describe various vulnerabilities the introduction of AI brings to TREs. We also provide an introduction to the different types and levels of risks associated with the disclosure of trained ML models. We finally describe the new research opportunities in developing and adapting policies and tools for safely disclosing machine learning outputs from TREs.

But here are the three articles that caught my eye today. There's no email newsletter on Friday (have an amazing Passover, Good Friday and Easter Sunday). Here's an idea for all the sports teams: since your fans can't attend your sporting event in person due to the pandemic, maybe you can have them rent a robot mannequin as their substitute? During this pandemic, lots of heroes are working: grocery and warehouse people to the truckers delivering your food and others (the medical staff at your local hospital and many others who are keeping you safe and sound). The broadcast engineer at your favorite cable and TV network who's makes sure you can continue to watch your favorite show: I don't have to explain the headline: "What are good journeys to put people on?"

The task can be modeled as building a graph for a given text, whose nodes represent events and edges are labeled with temporal relations correspondingly. Figure 1a illustrates such a graph for the text shown therein. The nodes assassination, slaughtered, rampage, war, and Hutu are the candidate events, and different types of edges specify different temporal relations between them: assassination is BEFORE rampage, rampage INCLUDES slaughtered, and the relation between slaughtered and war is VAGUE. Since "Hutu" is actually not an event, a system is expected to annotate the relations between "Hutu" and all other nodes in the graph as NONE (i.e., no relation). As far as we know, all existing systems treat this task as a pipeline of two separate subtasks, (a) Temporal Relation Graph (b) Pipeline Model (c) Structured Joint Model Figure 1: An illustration of event and relation models in our proposed joint framework.

A non linear regression approach which consists of a specific regression model incorporating a latent process, allowing various polynomial regression models to be activated preferentially and smoothly, is introduced in this paper. The model parameters are estimated by maximum likelihood performed via a dedicated expecation-maximization (EM) algorithm. An experimental study using simulated and real data sets reveals good performances of the proposed approach.