Skip to content

Author

Ahmad Mousavi

American University

We have 4 of 18 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM Unlearning

Existing LLM unlearning methods struggle with robustness: unbounded forget losses degrade model coherence, fixed-weight balancing cannot adapt as retain difficulty shifts mid-training, and methods that work on one benchmark falter under scaling or repeated application. We propose BLADE, a constrained bilevel framework...

Md Toufikuzzaman, Ahmad Mousavi, Dongwon Lee · 0 citations
#machine learning Preprint Sep 2026

A family of spectral conjugate gradient algorithms derived by least-squares approximations based on a modified quasi--Newton update with application to a revised robust binary classification model

We develop a spectral three-term modification of the classic Hestenes--Stiefel conjugate gradient algorithm, preserving its anti-jamming characteristic and, simultaneously, taking care of the sufficient descent property. We discuss how a modified secant equation can be extracted from our modification scheme, yielding a...

Saman Babaie-Kafaki, Maryam Khoshsimaye-Bargard, Ahmad Mousavi · 0 citations
Preprint Aug 2026

The Rank-Collapse Principle for Quadratic Optimization

A unified, careful framework and a set of quantitative consequences for fixed-rank tractability results are claimed, rather than a claim to originate the known fixed-rank tractability results that motivate it.

M. Soltanalian, Ahmad Mousavi · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.