Arash Behboodi I am machine learning research scientist and Director of Engineering at Qualcomm AI Research. My research interests are at the intersection of machine learning, mathematical signal processing and information theory and include in particular learning theory, machine learning for inverse problems, compressed sensing, geometric deep learning and differentiable simulation. I am working as well on machine learning design for wireless communication systems.

News and Highlights

• Accepted paper at NeurIPs 2023: Pruning vs Quantization: Which is Better?, and a few more workshop papers.

• Accepted paper at Globecom 2023: Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Maps

• Accepted paper at ICML 2023 - Topology, Algebra, and Geometry in ML: Equivariant Self-supervised Deep Pose Estimation for Cryo EM

• The paper Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks got published at Information and Inference: a Journal of the IMA.

Selected recent papers

• Gabriele Cesa, Arash Behboodi, Algebraic Topological Networks via the Persistent Local Homology Sheaf , Symmetry and Geometry in Neural Representations - NeurReps Workshop, NeurIPS 2023

• Giovanni Luca Marchetti, Gabriele Cesa, Kumar Pratik, Arash Behboodi, Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach , Symmetry and Geometry in Neural Representations - NeurReps Workshop, NeurIPS 2023

• Tim Bakker, Fabio Valerio Massoli, Thomas Hehn, Tribhuvanesh Orekondy, Arash Behboodi, Switching policies for solving inverse problems , NeurIPS 2023 Workshop on Deep Learning and Inverse Problems, NeurIPS 2023

• Thomas M. Hehn, Tribhuvanesh Orekondy, Ori Shental, Arash Behboodi, Juan Bucheli, Akash Doshi, June Namgoong, Taesang Yoo, Ashwin Sampath, Joseph B. Soriaga, Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Maps, Globecom 2023, Arxiv, Dec. 2023

• Andrey Kuzmin, Markus Nagel, Mart van Baalen, Arash Behboodi, Tijmen Blankevoort, Pruning vs Quantization: Which is Better?, NeurIPS 2023, Arxiv, July 2023

• Ekkehard Schnoor, Arash Behboodi, Holger Rauhut, Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks, Information and Inference: A Journal of the IMA, Volume 12, Issue 3, September 2023, (Arxiv)

• Gabriele Cesa, Kumar Pratik, Arash Behboodi, Equivariant Self-supervised Deep Pose Estimation for Cryo EM, ICML 2023 - Topology, Algebra, and Geometry in ML