collaborators

21 papers

cs.LG2026

Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation

Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim +2

Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is incomplete: it primarily capture…

cs.AI2026

Soro: A Lightweight Foundation Model and Chatbot for Tajik

Stanislav Liashkov, Haitz Sáez de Ocáriz Borde, Azizjon Azimi +3

We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Ta…

stat.ML2026

Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples

Yicen Li, Ruiyang Hong, Anastasis Kratsios +2

Classical clustering methods usually return either a finite partition of the observed data or a finite dendrogram over it. This finite-sample view is inadequate when the hierarchy…

stat.ML2026

Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity

Anastasis Kratsios, Gregory Cousins, Haitz Sáez de Ocáriz Borde +2

We show that, in a precise sense, a broad class of feedforward neural networks learn (have finite sample complexity) in the PAC model: every fixed finite feedforward architecture w…

cs.LG2026

k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS

Jonas De Schouwer, Haitz Sáez de Ocáriz Borde, Xiaowen Dong

Graph transformers have shown promise in overcoming limitations of traditional graph neural networks, such as oversquashing and difficulties in modeling long-range dependencies. Ho…

cs.LG2026

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

Huidong Liang, Haitz Sáez de Ocáriz Borde, Baskaran Sripathmanathan +2

Long-range dependencies are critical for effective graph representation learning, yet most existing datasets focus on small graphs tailored to inductive tasks, offering limited ins…