activity
20182022
most citedLearning Operators with Coupled Attention

56 citations · 63 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG20226 cited

Random Weight Factorization Improves the Training of Continuous Neural Representations

Sifan Wang, Hanwen Wang, Jacob H. Seidman +1

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to captur…

cs.LG202256 cited

Learning Operators with Coupled Attention

Georgios Kissas, Jacob Seidman, Leonardo Ferreira Guilhoto +3

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general bla…

math.OC20201 cited

Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees

Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado +1

The fragility of deep neural networks to adversarially-chosen inputs has motivated the need to revisit deep learning algorithms. Including adversarial examples during training is a…

math.OC2019

A Control-Theoretic Approach to Analysis and Parameter Selection of Douglas-Rachford Splitting

Jacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado +1

Douglas-Rachford splitting and its equivalent dual formulation ADMM are widely used iterative methods in composite optimization problems arising in control and machine learning app…

math.OC2018

A Chebyshev-Accelerated Primal-Dual Method for Distributed Optimization

Jacob H. Seidman, Mahyar Fazlyab, George J. Pappas +1

We consider a distributed optimization problem over a network of agents aiming to minimize a global objective function that is the sum of local convex and composite cost functions.…