33 citations · 37 across the 9 of their papers we have counts for
8 papers · 1 filter
An Active-Bottleneck Mechanism for Weak-to-Strong Generalization
Mohammad Zeinalpour, Amir Najafi
Weak-to-strong generalization (W2SG) occurs when a student trained on a teacher's predictions outperforms that teacher. We study when this happens under fully converged, ridgeless…
Fundamental Limits of Learning High-dimensional Simplices in Noisy Regimes
Seyed Amir Hossein Saberi, Amir Najafi, Abolfazl Motahari +1
In this paper, we establish sample complexity bounds for learning high-dimensional simplices in from noisy data. Specifically, we consider i.i.d. samples uniform…
Robust Learnability of Sample-Compressible Distributions under Noisy or Adversarial Perturbations
Arefe Boushehrian, Amir Najafi
Learning distribution families over is a fundamental problem in unsupervised learning and statistics. A central question in this setting is whether a given family of…
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
Amir Hossein Saberi, Amir Najafi, Ala Emrani +5
The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions. In particular, we consider a sequence of $…
Out-Of-Domain Unlabeled Data Improves Generalization
Amir Hossein Saberi, Amir Najafi, Alireza Heidari +3
We propose a novel framework for incorporating unlabeled data into semi-supervised classification problems, where scenarios involving the minimization of either i) adversarially ro…
Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes
Amir Hossein Saberi, Amir Najafi, Seyed Abolfazl Motahari +1
In this paper, we find a sample complexity bound for learning a simplex from noisy samples. Assume a dataset of size is given which includes i.i.d. samples drawn from a uniform…
Distributed Sparse Feature Selection in Communication-Restricted Networks
Hanie Barghi, Amir Najafi, Seyed Abolfazl Motahari
This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. The primary goal is to learn the few causal featur…
Robustness to Adversarial Perturbations in Learning from Incomplete Data
Amir Najafi, Shin-ichi Maeda, Masanori Koyama +1
What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed? To provide a concrete answer to this question, thi…