activity
20212023
most citedRobust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

eess.SY2024

Probabilistic Reachability Analysis of Stochastic Control Systems

Saber Jafarpour, Zishun Liu, Yongxin Chen

We address the reachability problem for continuous-time stochastic dynamic systems. Our objective is to present a unified framework that characterizes the reachable set of a dynami…

eess.SY2024

: A Parallelizable and Differentiable Toolbox for Interval Analysis and Mixed Monotone Reachability in JAX

Akash Harapanahalli, Saber Jafarpour, Samuel Coogan

We present an implementation of interval analysis and mixed monotone interval reachability analysis as function transforms in Python, fully composable with the computational framew…

eess.SY2023

A Contracting Dynamical System Perspective toward Interval Markov Decision Processes

Saber Jafarpour, Samuel Coogan

Interval Markov decision processes are a class of Markov models where the transition probabilities between the states belong to intervals. In this paper, we study the problem of ef…

cs.LG20221 cited

Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach

Saber Jafarpour, Alexander Davydov, Matthew Abate +2

This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks based upon non-Euclidean contraction theory. The…

math.OC2022

Network Critical Slowing Down: Data-Driven Detection of Critical Transitions in Nonlinear Networks

Mohammad Pirani, Saber Jafarpour

In a Nature article, Scheffer et al. presented a novel data-driven framework to predict critical transitions in complex systems. These transitions, which may stem from failures, de…

cs.LG2021

Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach

Saber Jafarpour, Matthew Abate, Alexander Davydov +2

Implicit neural networks are a general class of learning models that replace the layers in traditional feedforward models with implicit algebraic equations. Compared to traditional…