data science

RLTLDR: Self-improvement by Internalizing Self-generated Feedback

RLTL;DR is introduced, a promising compacted training paradigm of the form"on this sort of task, keep this sort of thing in mind", which it is hoped will inspire future research on.

A Sharp Transition in Data Reconstruction under Differential Privacy

This work studies informed attackers who aim to reconstruct a single $d$-dimensional training sample from a $\rho$-zero-concentrated DP model, knowing all other training data, and derives entropy-based lower bounds for any private mechanism and any attack, demonstrating that the privacy budget guaranteeing adequate pro...

Identifying ODEs from Unstructured Data with Causal Representation Learning

We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typically assume direct measurements of the variables, or do not provide theoretical guarantees on the learned variables and equations. While Cau...

Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models

RCA-DCM improves top-1 accuracy over the strongest baseline on both Sock Shop and Online Boutique, and when the true root cause in the causal chamber is unobserved and acts as a latent confounder, it recovers the exact root-cause set more often than any competing method.

Second-Moment Stochastic Approximation Methods

This work derives second-moment stochastic approximation methods through the lens of optimal preconditioning for solving matrix equations, and develops a two-stage framework for their convergence analysis.

MoRE: Scaling mixture of experts with hardware-aware low-rank routing

This work proves that rank logarithmic in $M$ suffices for routing expressivity when the number of active experts is fixed, and is necessary up to precision factors, and introduces MoRE (Mixture of Rank-reduced-routed Experts), which factorizes the router weight matrix at rank r and reduces the routing cost to $O((h +...

Intrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes

Geometry does more than constrain an associative memory: curvature determines what it remembers and which states it creates. We develop intrinsic dense associative memories on Riemannian manifolds by casting memory as Epanechnikov kernel-density mode seeking. We compare geodesic and volume-corrected energies and show t...

XU-RS: Explaining Credal Width in Random-Set Language Models

Uncertainty estimates tell us how unsure a model is, but not why. Without knowing which parts of an input influences a model's uncertainty, we cannot tell whether that uncertainty score depends on input features that are relevant for the task. We study this problem in randomset classifiers built using pretrained langua...

OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models

The Optimal Transport-based Robust Off-Policy Evaluation (OTROPE) is proposed, a likelihood-free evaluation that performs distributional correction in a semantic space via optimal transport to align labeled behavior-policy samples with unlabeled target-policy samples, yielding a doubly robust-style evaluation.

Examining Issues in Translating Qualitative Data in Cross-Cultural Health Science Research Conducted in Malaysia: A Systematic Review

Pengembangan Media Monopoli untuk Meningkatkan Motivasi Belajar Siswa IPAS Kelas V Sekolah Dasar

This study aims to determine the difference in students’ concept understanding improvement between learning using the Discovery Learning model assisted by digital picture storybooks and conventional learning, as well as to determine the effect of the model on students’ concept understanding in Natural and Social Scienc...

Derived data and code for mapping pediatric sepsis host-response and biomarker research

Permission-compatible aggregate and derived outputs plus author-created code accompany the literature-level analysis of 278 author-confirmed working-Include Web of Science publication records, with a 106-record direct-sepsis sensitivity set. A separate PubMed branch provides period-stratified, bounded cross-database co...