Seyed Abolfazl Motahari
YOU?
Author Swipe
View article: Fundamental Limits of Learning High-dimensional Simplices in Noisy Regimes
Fundamental Limits of Learning High-dimensional Simplices in Noisy Regimes Open
In this paper, we establish sample complexity bounds for learning high-dimensional simplices in $\mathbb{R}^K$ from noisy data. Specifically, we consider $n$ i.i.d. samples uniformly drawn from an unknown simplex in $\mathbb{R}^K$, each co…
View article: Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization Open
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 $T\ge2$ data distributions $P_1,\ldots,P_T$ undergoing a gra…
View article: Efficient learning of differential network in multi-source non-paranormal graphical models
Efficient learning of differential network in multi-source non-paranormal graphical models Open
This paper addresses learning of sparse structural changes or differential network between two classes of non-paranormal graphical models. We assume a multi-source and heterogeneous dataset is available for each class, where the covariance…
View article: Out-Of-Domain Unlabeled Data Improves Generalization
Out-Of-Domain Unlabeled Data Improves Generalization Open
We propose a novel framework for incorporating unlabeled data into semi-supervised classification problems, where scenarios involving the minimization of either i) adversarially robust or ii) non-robust loss functions have been considered.…
View article: Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes
Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes Open
In this paper, we find a sample complexity bound for learning a simplex from noisy samples. Assume a dataset of size $n$ is given which includes i.i.d. samples drawn from a uniform distribution over an unknown simplex in $\mathbb{R}^K$, wh…
View article: Isoform Function Prediction Using a Deep Neural Network
Isoform Function Prediction Using a Deep Neural Network Open
Isoforms are mRNAs produced from the same gene site in the phenomenon called Alternative Splicing. Studies have shown that more than 95% of human multi-exon genes have undergone alternative splicing. Although there are few changes in mRNA …
View article: Distributed Sparse Feature Selection in Communication-Restricted\n Networks
Distributed Sparse Feature Selection in Communication-Restricted\n Networks Open
This paper aims to propose and theoretically analyze a new distributed scheme\nfor sparse linear regression and feature selection. The primary goal is to\nlearn the few causal features of a high-dimensional dataset based on noisy\nobservat…
View article: Distributed Sparse Feature Selection in Communication-Restricted Networks
Distributed Sparse Feature Selection in Communication-Restricted Networks Open
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 features of a high-dimensional dataset based on noisy observation…
View article: On statistical learning of simplices: Unmixing problem revisited
On statistical learning of simplices: Unmixing problem revisited Open
We study the sample complexity of learning a high-dimensional simplex from a set of points uniformly sampled from its interior. Learning of simplices is a long studied problem in computer science and has applications in computational biolo…
View article: Regularizing Recurrent Neural Networks via Sequence Mixup
Regularizing Recurrent Neural Networks via Sequence Mixup Open
In this paper, we extend a class of celebrated regularization techniques originally proposed for feed-forward neural networks, namely Input Mixup (Zhang et al., 2017) and Manifold Mixup (Verma et al., 2018), to the realm of Recurrent Neura…
View article: The Capacity of Associated Subsequence Retrieval
The Capacity of Associated Subsequence Retrieval Open
The objective of a genome-wide association study (GWAS) is to associate subsequences of individuals' genomes to the observable characteristics called phenotypes (e.g., high blood pressure). Motivated by the GWAS problem, in this paper we i…
View article: De novo RNA sequencing analysis of Aeluropus littoralis halophyte plant under salinity stress
De novo RNA sequencing analysis of Aeluropus littoralis halophyte plant under salinity stress Open
The study of salt tolerance mechanisms in halophyte plants can provide valuable information for crop breeding and plant engineering programs. The aim of the present study was to investigate whole transcriptome analysis of Aeluropus littora…
View article: Reliable clustering of Bernoulli mixture models
Reliable clustering of Bernoulli mixture models Open
A Bernoulli Mixture Model (BMM) is a finite mixture of random binary vectors with independent dimensions. The problem of clustering BMM data arises in a variety of real-world applications, ranging from population genetics to activity analy…
View article: Structure Learning of Sparse GGMs Over Multiple Access Networks
Structure Learning of Sparse GGMs Over Multiple Access Networks Open
A central machine is interested in estimating the underlying structure of a sparse Gaussian Graphical Model (GGM) from datasets distributed across multiple local machines. The local machines can communicate with the central machine through…
View article: Cache-Aided Combination Networks With Interference
Cache-Aided Combination Networks With Interference Open
Centralized coded caching and delivery is studied for a radio access combination network (RACN), whereby a set of H edge nodes (ENs), connected to a cloud server via orthogonal fronthaul links with limited capacity, serve a total of K user…
View article: Private Shotgun DNA Sequencing
Private Shotgun DNA Sequencing Open
Current techniques in sequencing a genome allow a service provider (e.g. a sequencing company) to have full access to the genome information, and thus the privacy of individuals regarding their lifetime secret is violated. In this paper, w…
View article: Private Shotgun DNA Sequencing: A Structured Approach
Private Shotgun DNA Sequencing: A Structured Approach Open
DNA sequencing has faced a huge demand since it was first introduced as a service to the public. This service is often offloaded to the sequencing companies who will have access to full knowledge of individuals' sequences, a major violatio…
View article: Learning of Gaussian Processes in Distributed and Communication Limited Systems
Learning of Gaussian Processes in Distributed and Communication Limited Systems Open
It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. Aiming at characterizing the optimal strategies, we consider learning of …
View article: Cell Identity Codes: Understanding Cell Identity from Gene Expression Profiles using Deep Neural Networks
Cell Identity Codes: Understanding Cell Identity from Gene Expression Profiles using Deep Neural Networks Open
Understanding cell identity is an important task in many biomedical areas. Expression patterns of specific marker genes have been used to characterize some limited cell types, but exclusive markers are not available for many cell types. A …
View article: Cache-Aided Combination Networks with Interference
Cache-Aided Combination Networks with Interference Open
Centralized coded caching and delivery is studied for a radio access combination network (RACN), whereby a set of $H$ edge nodes (ENs), connected to a cloud server via orthogonal fronthaul links with limited capacity, serve a total of $K$ …
View article: Information Theoretic Bounds on Optimal Worst-case Error in Binary Mixture Identification
Information Theoretic Bounds on Optimal Worst-case Error in Binary Mixture Identification Open
Identification of latent binary sequences from a pool of noisy observations has a wide range of applications in both statistical learning and population genetics. Each observed sequence is the result of passing one of the latent mother-seq…
View article: Learning of Tree-Structured Gaussian Graphical Models on Distributed Data Under Communication Constraints
Learning of Tree-Structured Gaussian Graphical Models on Distributed Data Under Communication Constraints Open
In this paper, learning of tree-structured Gaussian graphical models from\ndistributed data is addressed. In our model, samples are stored in a set of\ndistributed machines where each machine has access to only a subset of\nfeatures. A cen…
View article: Genome-Wide Association Studies: Information Theoretic Limits of Reliable Learning
Genome-Wide Association Studies: Information Theoretic Limits of Reliable Learning Open
In the problems of Genome-Wide Association Study (GWAS), the objective is to associate subsequences of individuals' genomes to the observable characteristics called phenotypes. The genome containing the biological information of an individ…
View article: On the Identifiability of Finite Mixtures of Finite Product Measures
On the Identifiability of Finite Mixtures of Finite Product Measures Open
The problem of identifiability of finite mixtures of finite product measures is studied. A mixture model with $K$ mixture components and $L$ observed variables is considered, where each variable takes its value in a finite set with cardina…
View article: Cell Identity Codes: Understanding Cell Identity from Gene Expression\n Profiles using Deep Neural Networks
Cell Identity Codes: Understanding Cell Identity from Gene Expression\n Profiles using Deep Neural Networks Open
Understanding cell identity is an important task in many biomedical areas.\nExpression patterns of specific marker genes have been used to characterize\nsome limited cell types, but exclusive markers are not available for many cell\ntypes.…
View article: Cache-aided fog radio access networks with partial connectivity
Cache-aided fog radio access networks with partial connectivity Open
Centralized coded caching and delivery is studied for a partially-connected fog radio access network (F-RAN), whereby a set of H edge nodes (ENs) (without caches), connected to a cloud server via orthogonal fronthaul links, serve K users o…
View article: Cache-aided fog radio access networks with partial connectivity
Cache-aided fog radio access networks with partial connectivity Open
Centralized coded caching and delivery is studied for a partially-connected fog radio access network (F-RAN), whereby a set of H edge nodes (ENs) (without caches), connected to a cloud server via orthogonal fronthaul links, serve K users o…
View article: Fundamental limits of latency in a cache-aided 4×4 interference channel
Fundamental limits of latency in a cache-aided 4×4 interference channel Open
Fundamental limits of communication is studied in a 4 × 4 interference network, in which the transmitters are equipped with cache memories. Each of the receivers requests one file from a library of N equal-size files. The caches at the tra…
View article: Reliable Learning of Bernoulli Mixture Models
Reliable Learning of Bernoulli Mixture Models Open
In this paper, we have derived a set of sufficient conditions for reliable clustering of data produced by Bernoulli Mixture Models (BMM), when the number of clusters is unknown. A BMM refers to a random binary vector whose components are i…