arXiv:2508.18768v2 Announce Type: replace Abstract: We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $widetilde{mathcal{O}}(sqrt{T})$ regret in the adversarial regime and $widetilde{mathcal{O}}(ln T)$ regret in the corrupted stochastic regime. Our approach builds on the Follow-the-Regularized-Leader (FTRL) framework equipped with a Shannon entropy regularizer, yielding a flexible method that admits efficient implementations. Beyond regret bounds, we tackle the practical bottleneck in FTRL (or, equivalently, Online Stochastic Mirror Descent) arising from the high-dimensional projection step encountered […]

Ver mais

• Not all hard problems need ML—validate that adaptive learning actually solves your business problem before building. • Start with simple models (logistic regression, XGBoost) over cutting-edge architectures; prove concept viability first. • Data infrastructure matters as much as the model; invest in sourcing, labeling, and validation before training. • Build feedback loops and track real-world metrics from day one; plan for retraining and model iteration. • Calculate unit economics upfront—inference, training, and infrastructure costs must align with […]

Ver mais

In 2025, the pressure on business leaders to adopt AI and demonstrate immediate financial returns has reached unprecedented levels. With technology budgets steadily climbing to a projected 14% of total revenue a significant increase from previous years the C-suite has definitively shifted from speculative experimentation to demanding a rigorous quantification of AI’s financial impact. But the true path to generating sustainable value from AI is filled with counter-intuitive realities and hidden complexities that extend far beyond the mainstream […]

Ver mais

arXiv:2601.22211v1 Announce Type: new Abstract: Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility by design. Our method, […]

Ver mais

arXiv:2602.11406v1 Announce Type: new Abstract: We consider an online learning problem in environments with multiple change points. In contrast to the single change point problem that is widely studied using classical “high confidence” detection schemes, the multiple change point environment presents new learning-theoretic and algorithmic challenges. Specifically, we show that classical methods may exhibit catastrophic failure (high regret) due to a phenomenon we refer to as endogenous confounding. To overcome this, we propose a new class of learning […]

Ver mais

I recently talked with a contact who repeated what he’d heard regarding agentic AI systems—namely, that they can greatly increase productivity in professional financial management tasks. However, I pointed out that though this is true, these tools do not guarantee correctness, so one has to be very careful letting them manage critical assets such as financial data. It is widely recognized that AI models, even reasoning models and agentic systems, can make mistakes. One example is a case […]

Ver mais

arXiv:2601.15347v1 Announce Type: new Abstract: The rash development of knowledge graph research has brought big driving force to its application in many areas, including the medicine and healthcare domain. However, we have found that the application of some major information processing techniques on knowledge graph still lags behind. This defect includes the failure to make sufficient use of advanced logic reasoning, advanced artificial intelligence techniques, special-purpose programming languages, modern probabilistic and statistic theories et al. on knowledge graphs […]

Ver mais

arXiv:2601.05304v1 Announce Type: cross Abstract: Neuro-symbolic reasoning systems face fundamental challenges in maintaining semantic coherence while satisfying physical and logical constraints. Building upon our previous work on Ontology Neural Networks, we present an enhanced framework that integrates topological conditioning with gradient stabilization mechanisms. The approach employs Forman-Ricci curvature to capture graph topology, Deep Delta Learning for stable rank-one perturbations during constraint projection, and Covariance Matrix Adaptation Evolution Strategy for parameter optimization. Experimental evaluation across multiple problem sizes demonstrates […]

Ver mais