activity
20242026
collaborators

9 papers

math.OC2026

On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks

Jihun Kim, Yuchen Fang, Javad Lavaei

This paper is concerned with learning the input-output mapping of general nonlinear dynamical systems. While the existing literature focuses on Gaussian inputs and benign disturban…

cs.LG2026

Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks

Ying Chen, Aoxi Li, Jihun Kim +1

The massive computational costs of scaling modern deep learning architectures have driven the widespread use of parameter-efficient low-rank structures, such as LoRA and low-rank f…

math.OC2026

Huber-based Robust System Identification with Near-Optimal Guarantees Across Independent and Adversarial Regimes

Jihun Kim, Javad Lavaei

Dynamical systems can confront one of two extreme types of disturbances: persistent zero-mean independent noise, and sparse nonzero-mean adversarial attacks, depending on the speci…

math.OC2026

System Identification under Noise and Attack Regimes: Agnostic and Composite Robustness

Jihun Kim, Javad Lavaei

Dynamical systems often confront persistent zero-mean independent noise and/or sparse nonzero-mean adversarial attacks. While mean-based estimators like least-squares handle the fo…

math.OC2025

Revisiting the Geometrically Decaying Step Size: Linear Convergence for Smooth or Non-Smooth Functions

Jihun Kim

We revisit the geometrically decaying step size given a positive inverse condition number, under which a locally Lipschitz function shows linear convergence. The positivity does no…

math.OC2025

Bridging Batch and Streaming Estimations to System Identification under Adversarial Attacks

Jihun Kim, Javad Lavaei

System identification in modern engineering systems faces emerging challenges from unanticipated adversarial attacks beyond existing detection mechanisms. In this work, we obtain a…