6 papers
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…
Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces
Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer
Machine learning models with inputs in a Euclidean space , when implemented on digital computers, generalize, and their generalization gap converges to at a rate…
Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning
Anastasis Kratsios, A. Martina Neuman, Philipp Petersen
We compare in-context learning with fixed queries and agentic learning with adaptive queries for uniform approximation of task families. We consider two settings: an unrestricted r…
Reconstruction of frequency-localized functions from pointwise samples via least squares and deep learning
A. Martina Neuman, Andres Felipe Lerma Pineda, Jason J. Bramburger +1
Recovering frequency-localized functions from pointwise data is a fundamental task in signal processing. We examine this problem from an approximation-theoretic perspective, focusi…
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…
Consistency of augmentation graph and network approximability in contrastive learning
Chenghui Li, A. Martina Neuman
Contrastive learning leverages data augmentation to develop feature representation without relying on large labeled datasets. However, despite its empirical success, the theoretica…