arXiv:2602.12350v1 Announce Type: new Abstract: Many natural optimization problems derived from $sf NP$ admit bilevel and multilevel extensions in which decisions are made sequentially by multiple players with conflicting objectives, as in interdiction, adversarial selection, and adjustable robust optimization. Such problems are naturally modeled by alternating quantifiers and, therefore, lie beyond $sf NP$, typically in the polynomial hierarchy or $sf PSPACE$. Despite extensive study of these problem classes, relatively few natural completeness results are known at these higher […]

Ver mais

arXiv:2506.15492v2 Announce Type: replace-cross Abstract: Some of the simplest, yet most frequently used predictors in statistics and machine learning use weighted linear combinations of features. Such linear predictors can model non-linear relationships between features by adding interaction terms corresponding to the products of all pairs of features. We consider the problem of accurately estimating coefficients for interaction terms in linear predictors. We hypothesize that the coefficients for different interaction terms have an approximate low-dimensional structure and represent each […]

Ver mais

arXiv:2512.21451v2 Announce Type: replace Abstract: Being infinite dimensional, non-parametric information geometry has long faced an “intractability barrier” due to the fact that the Fisher-Rao metric is now a functional incurring difficulties in defining its inverse. This paper introduces a novel framework to resolve the intractability with an Orthogonal Decomposition of the Tangent Space ($T_fM = S oplus S^{perp}$), where $S$ represents an observable covariate subspace. Through the decomposition, we derive the Covariate Fisher Information Matrix (cFIM), denoted as […]

Ver mais

Software development is a very stressful job. There is so much to learn and so little time. Anxiety and fear of missing out make you feel like no matter how hard you work to stay ahead, it will never manage to catch up.  Remote work has transformed the landscape of software development, offering unprecedented flexibility and autonomy. Yet this very freedom can become a double-edged sword, leading to isolation, blurred boundaries, and ultimately, burnout. With statistics showing that up […]

Ver mais

Lately, NeurIPS and ICLR are flooded with these LLM benchmarking papers. All they do is take a problem X and benchmark a bunch of propriety LLMs on this problem. My main question is these proprietary LLMs are updated almost every month. The previous models are deprecated and are sometimes no longer available. By the time these papers are published, the models they benchmark on are already dead. So, what is the point of such papers? Are these big […]

Ver mais

Scaling reinforcement learning to tens of thousands of parallel environments requires overcoming the limited exploration capacity of a single policy. Ensemble-based policy gradient methods, which employ multiple policies to collect diverse samples, have recently been proposed to promote exploration. However, merely broadening the exploration space does not always enhance learning capability, since excessive exploration can reduce exploration quality or compromise training stability. In this work, we theoretically analyze the impact of inter-policy diversity on learning efficiency in policy […]

Ver mais

Agentic Engineering Patterns > I use the term agentic engineering to describe the practice of developing software with the assistance of coding agents. What are coding agents? They’re agents that can both write and execute code. Popular examples include Claude Code, OpenAI Codex, and Gemini CLI. What’s an agent? Clearly defining that term is a challenge that has frustrated AI researchers since at least the 1990s but the definition I’ve come to accept, at least in the field […]

Ver mais

Nica and Sprague [textit{Am. Math. Mon., 2023}] derived a non-Archimedean version of the Gershgorin disk theorem. We derive a non-Archimedean version of the oval (of Cassini) theorem by Brauer [textit{Duke Math. J., 1947}] which generalizes the Nica-Sprague disk theorem. We provide applications for bounding the zeros of polynomials over non-Archimedean fields. We also show that our result is equivalent to the non-Archimedean version of the Ostrowski nonsingularity theorem derived by Li and Li [textit{J. Comput. Appl. Math., 2025}].

Ver mais

Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterophilic hypergraphs, where nodes connected by the same hyperedge tend to have dissimilar semantic representations or belong to different classes. While several HyGNNs, including our prior work BHyGNN, have been proposed to address heterophily, their reliance on labeled data significantly limits their applicability in real-world scenarios where annotations are scarce or costly. To overcome this limitation, we introduce […]

Ver mais