22 citations · 32 across the 13 of their papers we have counts for
13 papers
Priors learned from legacy reconstructions inherit undetectable overconfidence
Ali Siahkoohi, Sina Alemohammad
Where truths are scarce (e.g., seismic and medical imaging), learned priors in ill-posed inverse problems are trained on archives of legacy reconstructions---i.e., an older method'…
Neon: Negative Extrapolation From Self-Training Improves Image Generation
Sina Alemohammad, Zhangyang Wang, Richard G. Baraniuk
Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic d…
Self-Improving Diffusion Models with Synthetic Data
Sina Alemohammad, Ahmed Imtiaz Humayun, Shruti Agarwal +2
The artificial intelligence (AI) world is running out of real data for training increasingly large generative models, resulting in accelerating pressure to train on synthetic data.…
An Adaptive Tangent Feature Perspective of Neural Networks
Daniel LeJeune, Sina Alemohammad
In order to better understand feature learning in neural networks, we propose a framework for understanding linear models in tangent feature space where the features are allowed to…
Self-Consuming Generative Models Go MAD
Sina Alemohammad, Josue Casco-Rodriguez, Lorenzo Luzi +5
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models. Repeating this…
TITAN: Bringing The Deep Image Prior to Implicit Representations
Lorenzo Luzi, Daniel LeJeune, Ali Siahkoohi +6
We study the interpolation capabilities of implicit neural representations (INRs) of images. In principle, INRs promise a number of advantages, such as continuous derivatives and a…
NeuroView-RNN: It's About Time
CJ Barberan, Sina Alemohammad, Naiming Liu +2
Recurrent Neural Networks (RNNs) are important tools for processing sequential data such as time-series or video. Interpretability is defined as the ability to be understood by a p…
NFT-K: Non-Fungible Tangent Kernels
Sina Alemohammad, Hossein Babaei, CJ Barberan +4
Deep neural networks have become essential for numerous applications due to their strong empirical performance such as vision, RL, and classification. Unfortunately, these networks…
Covariate Balancing Methods for Randomized Controlled Trials Are Not Adversarially Robust
Hossein Babaei, Sina Alemohammad, Richard Baraniuk
The first step towards investigating the effectiveness of a treatment via a randomized trial is to split the population into control and treatment groups then compare the average r…
Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data
Sina Alemohammad, Randall Balestriero, Zichao Wang +1
Kernels derived from deep neural networks (DNNs) in the infinite-width regime provide not only high performance in a range of machine learning tasks but also new theoretical insigh…
Wearing a MASK: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels
Sina Alemohammad, Hossein Babaei, Randall Balestriero +8
High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation. Techniques abound to red…
The Recurrent Neural Tangent Kernel
Sina Alemohammad, Zichao Wang, Randall Balestriero +1
The study of deep neural networks (DNNs) in the infinite-width limit, via the so-called neural tangent kernel (NTK) approach, has provided new insights into the dynamics of learnin…
Recovering Quantized Data with Missing Information Using Bilinear Factorization and Augmented Lagrangian Method
Ashkan Esmaeili, Kayhan Behdin, Sina Al-E-Mohammad +1
In this paper, we propose a novel approach in order to recover a quantized matrix with missing information. We propose a regularized convex cost function composed of a log-likeliho…