Modern data aggregation often takes the form of a platform collecting da...
It is expected that autonomous vehicles(AVs) and heterogeneous human-dri...
Devising a fair classifier that does not discriminate against different
...
Many existing imitation learning datasets are collected from multiple
de...
Building autonomous vehicles (AVs) is a complex problem, but enabling th...
Machine learning models are known to be susceptible to adversarial attac...
Training intelligent agents that can drive autonomously in various urban...
With the adoption of autonomous vehicles on our roads, we will witness a...
Widespread adoption of autonomous vehicles will not become a reality unt...
Despite the advances in the autonomous driving domain, autonomous vehicl...
Coordination is often critical to forming prosocial behaviors – behavior...
Traffic congestion has large economic and social costs. The introduction...
The COVID-19 pandemic has severely affected many aspects of people's dai...
Machine learning models are vulnerable to adversarial attacks that can o...
It is widely known that several machine learning models are susceptible ...
When selfish users share a road network and minimize their individual tr...
Empirical Risk Minimization (ERM) algorithms are widely used in a variet...
Federated learning is a distributed paradigm that aims at training model...
We consider a decentralized stochastic learning problem where data point...
The vulnerability of deep neural networks to small, adversarially design...
We study convex empirical risk minimization for high-dimensional inferen...
With recent advancements in edge computing capabilities, there has been ...
Federated learning is a new distributed machine learning approach, where...
Road congestion induces significant costs across the world, and road net...
We study the performance of a wide class of convex optimization-based
es...
We consider a decentralized learning problem, where a set of computing n...
In modern distributed computing systems, unpredictable and unreliable
in...
Autonomous vehicles have the potential to increase the capacity of roads...
We focus on the commonly used synchronous Gradient Descent paradigm for
...
Traffic congestion has large economic and social costs. The introduction...
It is by now well-known that small adversarial perturbations can induce
...
In this work we propose a macroscopic model for studying routing on netw...
The emerging technology enabling autonomy in vehicles has led to a varie...
We consider the problem of decentralized consensus optimization, where t...
There is a growing interest in development of in-network dispersed compu...
It is by now well-known that small adversarial perturbations can induce
...
Many distributed graph computing systems have been developed recently fo...
Deep neural networks represent the state of the art in machine learning ...