3 papers
cs.LG2026
Size Transferability of Graph Transformers with Convolutional Positional Encodings
Javier Porras-Valenzuela, Zhiyang Wang, Xiaotao Shang +3
Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key desi…
cs.LG2026
A Constrained Optimization Perspective of Unrolled Transformers
Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro
We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints…
cs.LG2024
Loss Shaping Constraints for Long-Term Time Series Forecasting
Ignacio Hounie, Javier Porras-Valenzuela, Alejandro Ribeiro
Several applications in time series forecasting require predicting multiple steps ahead. Despite the vast amount of literature in the topic, both classical and recent deep learning…