Mojtaba Sahraee-Ardakan — accepted AI-conference papers

2025

Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration

Yuyang Hu, Kangfu Mei, Mojtaba Sahraee-Ardakan, Ulugbek S. Kamilov, Peyman Milanfar, Mauricio Delbracio

NeurIPS 2025poster

Diffusion models show promise for image restoration, but existing methods often struggle with inconsistent fidelity and undesirable artifacts. To address this, we introduce Kernel Density Steering (KDS), a novel inference-time framework promoting robust, high-fidelity outputs through explicit local…

Cited by 0 Source ↗Scholar ↗

2021

Asymptotics of Ridge Regression in Convolutional Models

Mojtaba Sahraee-Ardakan, Tung Mai, Anup Rao, Ryan A. Rossi, Sundeep Rangan, Alyson K Fletcher

ICML 2021spotlight

Understanding generalization and estimation error of estimators for simple models such as linear and generalized linear models has attracted a lot of attention recently. This is in part due to an interesting observation made in machine learning community that highly over-parameterized neural network…

Cited by 5 Source ↗PDF ↗Scholar ↗

2021

Implicit Bias of Linear RNNs

Melikasadat Emami, Mojtaba Sahraee-Ardakan, Parthe Pandit, Sundeep Rangan, Alyson K Fletcher

ICML 2021spotlight

Contemporary wisdom based on empirical studies suggests that standard recurrent neural networks (RNNs) do not perform well on tasks requiring long-term memory. However, RNNs’ poor ability to capture long-term dependencies has not been fully understood. This paper provides a rigorous explanation of t…

Cited by 13 Source ↗PDF ↗Scholar ↗

2020

Generalization Error of Generalized Linear Models in High Dimensions

Melikasadat Emami, Mojtaba Sahraee-Ardakan, Parthe Pandit, Sundeep Rangan, Alyson Fletcher

ICML 2020poster

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our understanding of their generalization capabilities is incomplete and…

Cited by 64 Source ↗PDF ↗Scholar ↗

2019

Sparse Multivariate Bernoulli Processes in High Dimensions

Parthe Pandit, Mojtaba Sahraee-Ardakan, Arash Amini, Sundeep Rangan, Alyson K. Fletcher

AISTATS 2019poster

We consider the problem of estimating the parameters of a multivariate Bernoulli process with auto-regressive feedback in the high-dimensional setting where the number of samples available is much less than the number of parameters. This problem arises in learning interconnections of networks of dyn…

Cited by 6 Source ↗PDF ↗Scholar ↗

2017

Estimation and learning of Dynamic Nonlinear Networks (DyNNets)

Mojtaba Sahraee-Ardakan, Alyson K. Fletcher

ICASSP 2017accepted

Learning high-dimensional systems from data is often computationally challenging in the presence of nonlinearities and dynamics. This paper proposes a novel approach for identification of high-dimensional systems based on decomposing systems into networks of low-dimensional linear dynamical subsyste…

Cited by 0 Source ↗Scholar ↗

2017

Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems

Alyson K. Fletcher, Mojtaba Sahraee-Ardakan, Sundeep Rangan, Philip Schniter

NeurIPS 2017poster

The problem of estimating a random vector x from noisy linear measurements y=Ax+w with unknown parameters on the distributions of x and w, which must also be learned, arises in a wide range of statistical learning and linear inverse problems. We show that a computationally simple iterative message-…

Cited by 20 Source ↗PDF ↗Scholar ↗