Search Results - "Pedarsani, Ramtin"
-
1
Coded Computation Over Heterogeneous Clusters
Published in IEEE transactions on information theory (01-07-2019)“…In large-scale distributed computing clusters, such as Amazon EC2, there are several types of "system noise" that can result in major degradation of…”
Get full text
Journal Article -
2
An Exact Quantized Decentralized Gradient Descent Algorithm
Published in IEEE transactions on signal processing (01-10-2019)“…We consider the problem of decentralized consensus optimization, where the sum of <inline-formula><tex-math notation="LaTeX">n</tex-math></inline-formula>…”
Get full text
Journal Article -
3
Platoons of connected vehicles can double throughput in urban roads
Published in Transportation research. Part C, Emerging technologies (01-04-2017)“…If vehicles cross intersections in platoons, the saturation flow rates can be increased by a factor as large as two or three. Such a platoon organization…”
Get full text
Journal Article -
4
Communication-Aware Scheduling of Serial Tasks for Dispersed Computing
Published in IEEE/ACM transactions on networking (01-08-2019)“…There is a growing interest in the development of in-network dispersed computing paradigms that leverage the computing capabilities of heterogeneous resources…”
Get full text
Journal Article -
5
Robustness and Adaptability of Reinforcement Learning-Based Cooperative Autonomous Driving in Mixed-Autonomy Traffic
Published in IEEE open journal of intelligent transportation systems (2022)“…Building autonomous vehicles (AVs) is a complex problem, but enabling them to operate in the real world where they will be surrounded by human-driven vehicles…”
Get full text
Journal Article -
6
Sharp Guarantees and Optimal Performance for Inference in Binary and Gaussian-Mixture Models
Published in Entropy (Basel, Switzerland) (30-01-2021)“…We study convex empirical risk minimization for high-dimensional inference in binary linear classification under both discriminative binary linear models, as…”
Get full text
Journal Article -
7
Congestion-Aware Bi-Modal Delivery Systems Utilizing Drones
Published in Future transportation (01-03-2023)“…With e-commerce demand rising, logistic operators are investing in alternative delivery methods such as drones. Because of their aerial reach, drones can…”
Get full text
Journal Article -
8
Speeding Up Distributed Machine Learning Using Codes
Published in IEEE transactions on information theory (01-03-2018)“…Codes are widely used in many engineering applications to offer robustness against noise . In large-scale systems, there are several types of noise that can…”
Get full text
Journal Article -
9
Binary Classification Under ℓ0 Attacks for General Noise Distribution
Published in IEEE transactions on information theory (01-02-2024)“…Adversarial examples have recently drawn considerable attention in the field of machine learning due to the fact that small perturbations in the data can…”
Get full text
Journal Article -
10
Pricing for multi-modal pickup and delivery problems with heterogeneous users
Published in Transportation research. Part C, Emerging technologies (01-12-2024)“…In this paper, we study the pickup and delivery problem with multiple transportation modalities, and address the challenge of efficiently allocating…”
Get full text
Journal Article -
11
Asymptotic Behavior of Adversarial Training in Binary Linear Classification
Published in IEEE transaction on neural networks and learning systems (18-07-2023)“…Adversarial training using empirical risk minimization (ERM) is the state-of-the-art method for defense against adversarial attacks, that is, against small…”
Get full text
Journal Article -
12
Online Coded Caching
Published in IEEE/ACM transactions on networking (01-04-2016)“…We consider a basic content distribution scenario consisting of a single origin server connected through a shared bottleneck link to a number of users each…”
Get full text
Journal Article -
13
Routing for Traffic Networks With Mixed Autonomy
Published in IEEE transactions on automatic control (01-06-2021)“…In this article, we propose a macroscopic model for studying routing on networks shared between human-driven and autonomous vehicles that captures the effects…”
Get full text
Journal Article -
14
SAFFRON: A fast, efficient, and robust framework for group testing based on sparse-graph codes
Published in 2016 IEEE International Symposium on Information Theory (ISIT) (01-07-2016)“…The group testing problem is to identify a population of K defective items from a set of n items by pooling groups of items. The result of a test for a group…”
Get full text
Conference Proceeding Journal Article -
15
Generalized Likelihood Ratio Test for Adversarially Robust Hypothesis Testing
Published in IEEE transactions on signal processing (2022)“…Machine learning models are known to be susceptible to adversarial attacks, which can cause misclassification by introducing small but well designed…”
Get full text
Journal Article -
16
Learning how to dynamically route autonomous vehicles on shared roads
Published in Transportation research. Part C, Emerging technologies (01-09-2021)“…•Autonomous vehicles increase the road capacities under the CTM model.•Reinforcement learning achieves routing autonomous vehicles to minimize latency.•Optimal…”
Get full text
Journal Article -
17
Learning Mixtures of Sparse Linear Regressions Using Sparse Graph Codes
Published in IEEE transactions on information theory (01-03-2019)“…In this paper, we consider the mixture of sparse linear regressions model. Let <inline-formula> <tex-math notation="LaTeX">\boldsymbol {\beta }^{(1)},\ldots,…”
Get full text
Journal Article -
18
Provably Private Distributed Averaging Consensus: An Information-Theoretic Approach
Published in IEEE transactions on information theory (01-11-2023)“…In this work, we focus on solving a decentralized consensus problem in a private manner. Specifically, we consider a setting in which a group of nodes,…”
Get full text
Journal Article -
19
Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity
Published in IEEE journal on selected areas in information theory (01-06-2022)“…Federated learning is a novel paradigm that involves learning from data samples distributed across a large network of clients while the data remains local. It…”
Get full text
Journal Article -
20
Coded Computing for Distributed Graph Analytics
Published in IEEE transactions on information theory (01-10-2020)“…Many distributed computing systems have been developed recently for implementing graph based algorithms such as PageRank over large-scale graph-structured…”
Get full text
Journal Article