6 papers
NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes
Anastasis Kratsios, Giulia Livieri, Philipp Schmocker
We address fundamental challenges in representing and computing -valued predictable square-integrable processes over , collected in the space $\mathcal{H}^2_…
BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning
Shijin Gong, Erhan Xu, Kai Ye +3
Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing algorithms face a tradeoff betw…
READER: Reasoning-Enhanced AI-Generated Text Detection
Pingfan Su, Kai Ye, Shijin Gong +4
Recent advances in large language models (LLMs) have made it increasingly difficult to distinguish human-written text from AI-generated content. Many existing detectors train super…
Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
Anastasis Kratsios, Giulia Livieri, A. Martina Neuman
We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. The underlying computation is given by…
Learning from one graph: transductive learning guarantees via the geometry of small random worlds
Nils Detering, Luca Galimberti, Anastasis Kratsios +2
Since their introduction by Kipf and Welling in , a primary use of graph convolutional networks is transductive node classification, where missing labels are inferred within…
Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach
Reza Arabpour, John Armstrong, Luca Galimberti +2
Predicting the conditional evolution of Volterra processes with stochastic volatility is a crucial challenge in mathematical finance. While deep neural network models offer promise…