Intelligence & Research

AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory

by Yuanhe Zhang, Jason D. Lee, Fanghui Liu on 12.06.2026 at 04:00

arXiv:2602.02285v2 Announce Type: replace Abstract: We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-end formal infrastructure implement the missing contents in latest Lean library, including a complete development of Gaussian Lipschitz concentration, Dudley’s entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to the human-verified Lean 4 toolbox for SLT. Beyond implementation, the formalization process exposes and resolves implicit assumptions and missing details in standard SLT textbooks, enforcing a granular, line-by-line understanding of the theory. This work establishes a reusable formal foundation and opens the door for future developments in machine learning theory. The code is provided in https://github.com/YuanheZ/lean-stat-learning-theory.

Calibrating Decision Robustness via Inverse Conformal Risk Control

by Wenbin Zhou, Shixiang Zhu on 12.06.2026 at 04:00

arXiv:2510.07750v3 Announce Type: replace-cross Abstract: Robust optimization safeguards decisions against uncertainty by optimizing against worst-case scenarios, yet their effectiveness hinges on a prespecified robustness level that is often chosen ad hoc, leading to either insufficient protection or overly conservative and costly solutions. Recent approaches using conformal prediction construct data-driven uncertainty sets with finite-sample coverage guarantees, but they still fix coverage targets a priori and offer little guidance for selecting robustness levels. We propose a new framework that provides distribution-free, finite-sample guarantees on both miscoverage and regret for any family of robust predict-then-optimize policies. Our method constructs valid estimators that trace out the miscoverage–regret Pareto frontier, enabling decision-makers to reliably evaluate and calibrate robustness levels according to their cost–risk preferences. The framework is simple to implement, broadly applicable across classical optimization formulations, and achieves sharper finite-sample performance. This paper offers a principled data-driven methodology for guiding robustness selection and empowers practitioners to balance robustness and conservativeness in high-stakes decision-making.

An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect

by Dihia Lanasri, Fatima Benbarek on 12.06.2026 at 04:00

arXiv:2606.13411v1 Announce Type: new Abstract: The rapid growth of social media has intensified the spread of rumours. This issue is more challenging in the Algerian context due to the informal and code-switched nature of dialectal content, the scarcity of annotated resources, and the limited effectiveness of standard Arabic NLP tools on dialect text. This paper presents an end-to-end rumour detection hybrid framework for Algerian dialect social media content. We build a domain-specific annotated dataset by combining real social media posts, synthetic data, and the FASSILA corpus, with automatic labeling based on a similarity-based annotation process. A transliteration pipeline is also introduced to generate parallel datasets in Arabic script and Arabizi. We evaluate multiple approaches, including classical machine learning, deep learning, transformers, and hybrid models. Experimental results show that a hybrid approach combining transformer embeddings with a classical classifier achieves the best performance, reaching an F1-score of 0.84. We also find that domain-specific pre-training is more important than model size, with social media-trained models outperforming larger models trained on formal Arabic corpora. These results demonstrate the feasibility of rumour detection in low-resource Algerian dialect settings.

What Uncertainties Do We Need for Dynamical Systems?

by Yusuf Sale, Christopher B\"ulte, Felix Czaja, Joshua Stiller, Eyke H\"ullermeier on 12.06.2026 at 04:00

arXiv:2606.11988v1 Announce Type: new Abstract: The distinction between aleatoric and epistemic uncertainty has received considerable attention in machine learning research, mainly in the context of supervised learning but also in other settings such as generative modeling. In this paper, we offer a machine learning perspective on uncertainty modeling for dynamical systems, which has been studied much less so far. In particular, we ask: what uncertainties do we need for dynamical systems? We discuss sources of uncertainty, clarify their nature (aleatoric or epistemic), and consider how the objectives of representing and quantifying uncertainty vary across different tasks.

Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation

by Jarek Duda on 12.06.2026 at 04:00

arXiv:2601.03326v2 Announce Type: replace-cross Abstract: PCA can be used for rotation invariant features, describing a shape with its $p_{ab}=E[(x_i-E[x_a])(x_b-E[x_b])]$ covariance matrix approximating shape by ellipsoid, allowing for rotation invariants like its traces of powers. However, real shapes are usually much more complicated, hence there is proposed its extension to e.g. $p_{abc}=E[(x_a-E[x_a])(x_b-E[x_b])(x_c-E[x_c])]$ order-3 or higher tensors describing central moments, or polynomial times Gaussian allowing decodable shape descriptors of arbitrarily high accuracy, and their analogous rotation invariants. Its practical applications could be rotation-invariant features to include shape modulo rotation e.g. for molecular shape descriptors, or for up to rotation object recognition in 2D images/3D scans maybe also for 3D scene understanding, or shape similarity metric allowing inexpensive comparison of objects modulo rotation avoiding costly optimization over rotations.

NIST Mathematical Proof Supports Transition to a Continuous-Monitor-and-Update Security Model for AI Systems

by Sarah Henderson on 09.06.2026 at 12:00

The proof extends to AI the logic used by famed mathematician Kurt Gödel, whose incompleteness theorems have had a profound effect on math for nearly a century.

NIST Expands Its Library of ‘Chemical Fingerprints’ to Identify Unknown Substances

by Sarah Henderson on 09.06.2026 at 12:00

Researchers and manufacturers rely on the library to identify unknown compounds in food, drugs, cosmetics, the environment, body fluids, forensic evidence and even space rocks.

NIST Researchers Discover a New Way to Whisk Alloys Together With Lasers

by Sarah Henderson on 04.06.2026 at 12:00

NIST also improved how X-rays are used to study the atomic structure of metals in real time during 3D printing, allowing researchers to observe how materials change under extreme conditions.

New AI Model Shows How to Evacuate for Fires One Safe Step at a Time

by Sarah Henderson on 04.06.2026 at 12:00

A NIST-led team has created a new AI model that can identify safe evacuation routes in a single-story floor plan during a fire, with a multilevel version in the works.

NIST Expands AI Consortium’s Scope, Calls for New Members

by Sarah Henderson on 29.05.2026 at 12:00

The consortium will focus on AI innovation and adoption, with six task groups concentrating on different aspects of AI measurement science and evaluation.