arXiv:2511.07486v1 Announce Type: cross 
Abstract: We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision processes (RCMDPs), where the agent must maximize reward while ensuring cumulative utility exceeds a threshold under the worst-case dynamics within an uncertainty set. While recent works have established finite-time iteration complexity guarantees for RCMDPs using policy optimization, their sample complexity guarantees remain largely unexplored. In this paper, we first show that Markovian policies may fail to be optimal even under rectangular uncertainty sets unlike the {\em unconstrained} robust MDP. To address this, we introduce an augmented state space that incorporates the remaining utility budget into the state representation. Building on this formulation, we propose a novel Robust constrained Value iteration (RCVI) algorithm with a sample complexity of $\mathcal{\tilde{O}}(|S||A|H^5/\epsilon^2)$ achieving at most $\epsilon$ violation using a generative model where $|S|$ and $|A|$ denote the sizes of the state and action spaces, respectively, and $H$ is the episode length. To the best of our knowledge, this is the {\em first sample complexity guarantee} for RCMDP. Empirical results further validate the effectiveness of our approach.

تقدم دراسة جديدة حول عمليات اتخاذ القرار الماركوفي المقيدة القوية (RCMDP) خوارزمية تكرار القيمة المقيدة القوية (RCVI)، التي تعمل على تحسين السياسات لزيادة المكافآت التراكمية مع الالتزام بالقيود الأمنية. هذه الدراسة مهمة لأنها توفر أول ضمانات لتعقيد العينة لـ RCMDP، مما يظهر أن السياسات الماركوفي التقليدية قد لا تكون مثالية في ظروف معينة. تحقق خوارزمية RCVI تعقيد عينة قدره O(|S||A|H^5/ε²)، مما يضمن انتهاكًا أدنى للحدود الأمنية.

Un nuevo estudio sobre procesos de decisión de Markov restringidos robustos (RCMDP) presenta el algoritmo de Iteración de Valor Restringido Robusto (RCVI), que optimiza políticas para maximizar recompensas acumulativas mientras se cumplen las restricciones de seguridad. Esta investigación es significativa ya que proporciona las primeras garantías de complejidad de muestra para RCMDP, demostrando que las políticas markovianas tradicionales pueden no ser óptimas en ciertas condiciones. El algoritmo RCVI logra una complejidad de muestra de O(|S||A|H^5/ε²), asegurando una violación mínima de los umbrales de seguridad.

Une nouvelle étude sur les processus de décision markoviens contraints robustes (RCMDP) présente l'algorithme d'itération de valeur contrainte robuste (RCVI), qui optimise les politiques pour maximiser les récompenses cumulées tout en respectant les contraintes de sécurité. Cette recherche est significative car elle fournit les premières garanties de complexité d'échantillonnage pour les RCMDP, démontrant que les politiques markoviennes traditionnelles peuvent ne pas être optimales dans certaines conditions. L'algorithme RCVI atteint une complexité d'échantillonnage de O(|S||A|H^5/ε²), garantissant une violation minimale des seuils de sécurité.

A new study on robust constrained Markov decision processes (RCMDPs) introduces the Robust Constrained Value Iteration (RCVI) algorithm, which optimizes policies to maximize cumulative rewards while adhering to safety constraints. This research is significant as it provides the first sample complexity guarantees for RCMDPs, demonstrating that traditional Markovian policies may not be optimal under certain conditions. The RCVI algorithm achieves a sample complexity of O(|S||A|H^5/ε²), ensuring minimal violation of safety thresholds.

Provably Efficient Sample Complexity for Robust CMDP

Here's everything you need to know about the latest smart ring by Oura, based on a wearable expert's real-world usage.

Is the $500 Oura Ring 4 Ceramic worth it? I wore one for a month, and here's my advice

Samsung's QN90F QLED delivers great streaming and gaming performance, making it a strong holiday value.

Why I recommend this Samsung QLED TV over pricier OLED models in 2025 - and don't regret it

<h1>
 
 
 AI Amnesia: Erasing Knowledge Without a Trace
</h1>

Imagine your AI model accidentally learned something it shouldn't have – sensitive customer data, for example. Current methods for deleting this information often require retraining the entire model, an expensive and time-consuming process. What if we could surgically remove that knowledge without starting from scratch?

The key lies in a novel approach: creating artificial "forgetting cues." We're teaching the model to unlearn specific data patterns by exposing it to carefully crafted synthetic examples. These examples are designed to strongly contradict the information we want the model to forget, effectively overwriting the problematic associations in its memory. This works even if you don’t have access to the original data you need to erase.

Think of it like this: you're trying to forget a bad song stuck in your head. Instead of trying to actively suppress it (which rarely works), you blast an even more catchy song. The new song overwrites the old one, effectively erasing it from your mental playlist.

Benefits of Selective Forgetting:

<ul>
<li> Enhanced Data Privacy: Remove sensitive data without compromising the overall model's performance.</li>
<li> Reduced Retraining Costs: Avoid full model retraining, saving significant time and resources.</li>
<li> Improved Model Security: Eliminate vulnerabilities introduced by unintentionally learned patterns.</li>
<li> Adaptable Learning: Enables continuous refinement of AI models based on evolving data landscapes.</li>
<li> Compliance Ready: Supports compliance with data privacy regulations like GDPR.</li>
<li> Scalable Solutions: Works efficiently even with limited access to training data.</li>
</ul>

Practical Tip: One challenge is ensuring the synthetic data accurately targets the information you want to remove without negatively impacting the model's ability to generalize. Rigorous testing and validation with holdout datasets are crucial.

The promise of AI that can truly 'forget' opens exciting possibilities for responsible AI development. By enabling precise data deletion, we pave the way for more secure, compliant, and adaptable machine learning systems. Imagine AI models that can adapt to changing ethical guidelines or quickly unlearn incorrect information, all without massive retraining efforts. This is a crucial step towards trustworthy and responsible AI that respects data privacy and aligns with societal values. Future exploration could include extending this to different data modalities and model architectures.

Related Keywords: machine unlearning, data privacy, few-shot learning, zero-shot learning, synthetic data, model editing, catastrophic forgetting, incremental learning, continual learning, deep learning, neural networks, data security, algorithmic fairness, responsible ai, ethical ai, federated unlearning, privacy-preserving ai, model retraining, AI governance, data deletion, GDPR compliance

يتناول المقال نهجًا جديدًا لمعالجة مشكلة نسيان الذكاء الاصطناعي، حيث قد تحتفظ نماذج الذكاء الاصطناعي عن غير قصد بمعلومات حساسة. تتطلب الطرق التقليدية لحذف هذه البيانات غالبًا إعادة تدريب كاملة للنموذج، وهو ما يعد مكلفًا ويستغرق وقتًا. تتضمن التقنية الجديدة إنشاء 'إشارات نسيان' اصطناعية تساعد النموذج على نسيان أنماط بيانات معينة من خلال تعريضه لأمثلة صناعية تتناقض مع المعلومات غير المرغوب فيها، مما يسمح بإزالة المعرفة المستهدفة دون الحاجة للوصول إلى البيانات الأصلية.

El artículo aborda un nuevo enfoque para tratar el problema de la amnesia de la IA, donde los modelos de IA pueden retener inadvertidamente información sensible. Los métodos tradicionales para eliminar estos datos a menudo requieren un reentrenamiento completo del modelo, lo que es costoso y lleva tiempo. La nueva técnica implica crear 'señales de olvido' artificiales que ayudan al modelo a desaprender patrones de datos específicos al exponerlo a ejemplos sintéticos que contradicen la información no deseada, permitiendo así la eliminación selectiva de conocimientos sin necesidad de acceder a l…

L'article traite d'une nouvelle approche pour résoudre le problème de l'amnésie de l'IA, où les modèles d'IA peuvent involontairement conserver des informations sensibles. Les méthodes traditionnelles pour supprimer ces données nécessitent souvent un réentraînement complet du modèle, ce qui est coûteux et long. La nouvelle technique consiste à créer des 'cues d'oubli' artificiels qui aident le modèle à désapprendre des schémas de données spécifiques en lui présentant des exemples synthétiques qui contredisent les informations indésirables, permettant ainsi une suppression ciblée des connaissan…

The article discusses a novel approach to address the issue of AI amnesia, where AI models may inadvertently retain sensitive information. Traditional methods for deleting such data often require complete retraining of the model, which is costly and time-consuming. The new technique involves creating artificial 'forgetting cues' that help the model unlearn specific data patterns by presenting it with synthetic examples that contradict the unwanted information, allowing for targeted knowledge removal without needing access to the original data.

AI Amnesia: Erasing Knowledge Without a Trace

Baseus' Enercore CG11 travel adapter is one of the better designed ones I've tested, although its best feature isn't immediately apparent.

Traveling soon? Why this one charger is the only one you'll ever need to pack

Turning materials like wood chips, crop residues and municipal solid waste into fuels and chemicals is important for our country's energy independence.

طور الباحثون نماذج حاسوبية متقدمة تهدف إلى تحسين التنبؤات لعمليات طحن الكتلة الحيوية. تركز هذه الابتكارات على تحويل مواد مثل رقائق الخشب، بقايا المحاصيل، والنفايات الصلبة البلدية إلى وقود ومواد كيميائية قيمة، وهو أمر مهم لتعزيز استقلالية الطاقة في البلاد. من المتوقع أن تعمل النماذج على تحسين كفاءة معالجة الكتلة الحيوية، مما يساهم في حلول الطاقة المستدامة.

Investigadores han desarrollado modelos informáticos avanzados destinados a mejorar las predicciones para los procesos de molienda de biomasa. Esta innovación se centra en convertir materiales como astillas de madera, residuos de cultivos y residuos sólidos municipales en combustibles y productos químicos valiosos, lo que es crucial para mejorar la independencia energética del país. Se espera que los modelos optimicen la eficiencia del procesamiento de biomasa, contribuyendo así a soluciones energéticas sostenibles.

Des chercheurs ont développé des modèles informatiques avancés visant à améliorer les prévisions pour les processus de broyage de la biomasse. Cette innovation se concentre sur la conversion de matériaux tels que les copeaux de bois, les résidus de culture et les déchets solides municipaux en combustibles et produits chimiques précieux, ce qui est crucial pour renforcer l'indépendance énergétique du pays. Les modèles devraient optimiser l'efficacité du traitement de la biomasse, contribuant ainsi à des solutions énergétiques durables.

Researchers have developed advanced computer models aimed at improving predictions for biomass milling processes. This innovation focuses on converting materials such as wood chips, crop residues, and municipal solid waste into valuable fuels and chemicals, which is crucial for enhancing energy independence in the country. The models are expected to optimize the efficiency of biomass processing, thereby contributing to sustainable energy solutions.

Researchers develop computer models for better biomass milling predictions

The most interesting aspect of the latest Even Realities glasses may be their limitations.

I've tried several AI smart glasses (including Meta Ray-Bans) in 2025 - these are the most comfortable

arXiv:2511.06854v2 Announce Type: replace-cross 
Abstract: Irregularly sampled time series (ISTS), characterized by non-uniform time intervals with natural missingness, are prevalent in real-world applications. Existing approaches for ISTS modeling primarily rely on observed values to impute unobserved ones or infer latent dynamics. However, these methods overlook a critical source of learning signal: the reconstruction error inherently produced during model training. Such error implicitly reflects how well a model captures the underlying data structure and can serve as an informative proxy for unobserved values. To exploit this insight, we propose iTimER, a simple yet effective self-supervised pre-training framework for ISTS representation learning. iTimER models the distribution of reconstruction errors over observed values and generates pseudo-observations for unobserved timestamps through a mixup strategy between sampled errors and the last available observations. This transforms unobserved timestamps into noise-aware training targets, enabling meaningful reconstruction signals. A Wasserstein metric aligns reconstruction error distributions between observed and pseudo-observed regions, while a contrastive learning objective enhances the discriminability of learned representations. Extensive experiments on classification, interpolation, and forecasting tasks demonstrate that iTimER consistently outperforms state-of-the-art methods under the ISTS setting.

يقدم المقال iTimER، وهو إطار عمل للتدريب الذاتي الموجه مصمم لتعلم تمثيلات السلاسل الزمنية المأخوذة بشكل غير منتظم (ISTS). تتميز ISTS بفترات زمنية غير متساوية وغياب طبيعي، مما يشكل تحديات أمام أساليب النمذجة التقليدية. يستفيد iTimER من خطأ إعادة البناء الناتج أثناء تدريب النموذج لإنشاء ملاحظات زائفة للعلامات الزمنية غير الملاحظة، مما يعزز قدرة النموذج على التقاط الهياكل الأساسية للبيانات وتحسين دقة التنبؤات.

El artículo presenta iTimER, un marco de preentrenamiento auto-supervisado diseñado para aprender representaciones de series temporales muestreadas de manera irregular (ISTS). Las ISTS se caracterizan por intervalos de tiempo no uniformes y faltantes naturales, lo que plantea desafíos para los enfoques de modelado tradicionales. iTimER aprovecha el error de reconstrucción generado durante el entrenamiento del modelo para crear pseudo-observaciones para marcas de tiempo no observadas, mejorando la capacidad del modelo para capturar las estructuras subyacentes de los datos y mejorar la precisión…

L'article présente iTimER, un cadre de pré-entraînement auto-supervisé conçu pour apprendre des représentations de séries temporelles échantillonnées de manière irrégulière (ISTS). Les ISTS se caractérisent par des intervalles de temps non uniformes et des manques naturels, ce qui pose des défis pour les approches de modélisation traditionnelles. iTimER exploite l'erreur de reconstruction générée pendant l'entraînement du modèle pour créer des pseudo-observations pour les horodatages non observés, améliorant ainsi la capacité du modèle à capturer les structures sous-jacentes des données et à a…

The article presents iTimER, a self-supervised pre-training framework designed for learning representations of irregularly sampled time series (ISTS). ISTS are characterized by non-uniform time intervals and natural missingness, which pose challenges for traditional modeling approaches. iTimER leverages the reconstruction error generated during model training to create pseudo-observations for unobserved timestamps, enhancing the model's ability to capture underlying data structures and improve forecasting accuracy.

Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning

arXiv:2503.09887v2 Announce Type: replace-cross 
Abstract: We develop a novel semigroup stability analysis based on Lyapunov techniques and contraction coefficients to prove exponential convergence of Sinkhorn equations on weighted Banach spaces. This operator-theoretic framework yields exponential decays of Sinkhorn iterates towards Schr\"odinger bridges with respect to general classes of $\phi$-divergences and Kantorovich-type criteria, including the relative entropy, squared Hellinger integrals, $\alpha$-divergences as well as weighted total variation norms and Wasserstein distances. To the best of our knowledge, these contraction inequalities are the first results of this type in the literature on entropic transport and the Sinkhorn algorithm.
  We also provide Lyapunov contractions principles under minimal regularity conditions that allow to provide quantitative exponential stability estimates for a large class of Sinkhorn semigroups. We apply this novel framework in a variety of situations, ranging from polynomial growth potentials and heavy tailed marginals on general normed spaces to more sophisticated boundary state space models, including semi-circle transitions, Beta, Weibull, exponential marginals as well as semi-compact models. Last but not least, our approach also allows to consider statistical finite mixture of the above models, including kernel-type density estimators of complex data distributions arising in generative modeling.

On the contraction properties of Sinkhorn semigroups

arXiv:2511.13049v1 Announce Type: cross 
Abstract: We study a matrix completion problem where both the ground truth $R$ matrix and the unknown sampling distribution $P$ over observed entries are low-rank matrices, and \textit{share a common subspace}. We assume that a large amount $M$ of \textit{unlabeled} data drawn from the sampling distribution $P$ is available, together with a small amount $N$ of labeled data drawn from the same distribution and noisy estimates of the corresponding ground truth entries. This setting is inspired by recommender systems scenarios where the unlabeled data corresponds to `implicit feedback' (consisting in interactions such as purchase, click, etc. ) and the labeled data corresponds to the `explicit feedback', consisting of interactions where the user has given an explicit rating to the item. Leveraging powerful results from the theory of low-rank subspace recovery, together with classic generalization bounds for matrix completion models, we show error bounds consisting of a sum of two error terms scaling as $\widetilde{O}\left(\sqrt{\frac{nd}{M}}\right)$ and $\widetilde{O}\left(\sqrt{\frac{dr}{N}}\right)$ respectively, where $d$ is the rank of $P$ and $r$ is the rank of $M$. In synthetic experiments, we confirm that the true generalization error naturally splits into independent error terms corresponding to the estimations of $P$ and and the ground truth matrix $\ground$ respectively. In real-life experiments on Douban and MovieLens with most explicit ratings removed, we demonstrate that the method can outperform baselines relying only on the explicit ratings, demonstrating that our assumptions provide a valid toy theoretical setting to study the interaction between explicit and implicit feedbacks in recommender systems.

يتناول المقال مشكلة إكمال المصفوفات حيث تكون كل من المصفوفة الحقيقية وتوزيع العينة غير المعروف مصفوفات منخفضة الرتبة تشترك في فضاء فرعي مشترك. يبرز توافر كمية كبيرة من البيانات غير المعلّمة المستمدة من توزيع العينة، إلى جانب مجموعة أصغر من البيانات المعلّمة مع تقديرات مشوشة. هذا السيناريو ذو صلة خاصة في أنظمة التوصية، حيث تمثل البيانات غير المعلّمة تعليقات ضمنية وتمثل البيانات المعلّمة تعليقات صريحة. تستفيد الدراسة من نتائج قوية من نظرية استرداد الفضاءات الفرعية المنخفضة الرتبة، إلى جانب حدود التعميم الكلاسيكية لنماذج إكمال المصفوفات، لتظهر حدود الخطأ.

El artículo aborda un problema de completado de matrices donde tanto la matriz verdadera como la distribución de muestreo desconocida son matrices de bajo rango que comparten un subespacio común. Se destaca la disponibilidad de una gran cantidad de datos no etiquetados de la distribución de muestreo, junto con un conjunto más pequeño de datos etiquetados con estimaciones ruidosas. Este escenario es particularmente relevante en sistemas de recomendación, donde los datos no etiquetados representan retroalimentación implícita y los datos etiquetados representan retroalimentación explícita. El est…

L'article traite d'un problème de complétion de matrice où la matrice réelle et la distribution d'échantillonnage inconnue sont des matrices de faible rang partageant un sous-espace commun. Il souligne la disponibilité d'une grande quantité de données non étiquetées provenant de la distribution d'échantillonnage, ainsi qu'un ensemble plus petit de données étiquetées avec des estimations bruitées. Ce scénario est particulièrement pertinent dans les systèmes de recommandation, où les données non étiquetées représentent un retour implicite et les données étiquetées un retour explicite. L'étude s'…

The article discusses a matrix completion problem where both the true matrix and the unknown sampling distribution are low-rank matrices sharing a common subspace. It highlights the availability of a large amount of unlabeled data from the sampling distribution, alongside a smaller set of labeled data with noisy estimates. This scenario is particularly relevant in recommender systems, where unlabeled data represents implicit feedback and labeled data represents explicit feedback. The study leverages low-rank subspace recovery theory and generalization bounds for matrix completion models to dem…

Provably Efficient Sample Complexity for Robust CMDP

Was this article worth reading? Share it