activity
20202026
most citedOn the ISS Property of the Gradient Flow for Single Hidden-Layer Neural Networks with Linear Activations

2 citations · 5 across the 5 of their papers we have counts for

collaborators

5 papers

cond-mat.mtrl-sci2026★ 1 cited

Electrical and thermal magnetotransport in altermagnetic CrSb

Sajal Naduvile Thadathil, Christoph Müller, Reza Firouzmandi +20

Chromium antimonide has emerged as a key material platform for studying altermagnetism because of its simple binary composition, high Néel temperature, and semimetallic electronic…

cs.LG2025

On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks

Arthur Castello Branco de Oliveira, Dhruv Jatkar, Eduardo Sontag

This paper investigates how the compositional structure of neural networks shapes their optimization landscape and training dynamics. We analyze the gradient flow associated with o…

math.OC2025

Remarks on the Polyak-Lojasiewicz inequality and the convergence of gradient systems

Arthur Castello B. de Oliveira, Leilei Cui, Eduardo D. Sontag

This work explores generalizations of the Polyak-Lojasiewicz inequality (PLI) and their implications for the convergence behavior of gradient flows in optimization problems. Motiva…

cs.LG2023★ 2 cited

On the ISS Property of the Gradient Flow for Single Hidden-Layer Neural Networks with Linear Activations

Arthur Castello B. de Oliveira, Milad Siami, Eduardo D. Sontag

Recent research in neural networks and machine learning suggests that using many more parameters than strictly required by the initial complexity of a regression problem can result…

eess.SY2020★ 2 cited

Edge Selection in Bilinear Dynamical Networks

Arthur Castello B. de Oliveira, Milad Siami, Eduardo D. Sontag

We develop some basic principles for the design and robustness analysis of a continuous-time bilinear dynamical network, where an attacker can manipulate the strength of the interc…