• Publications
  • Influence
Multilevel Text Alignment with Cross-Document Attention
TLDR
This work proposes a new learning approach that equips previously established hierarchical attention encoders for representing documents with a cross-document attention component, enabling structural comparisons across different levels (document-to-document and sentence- to-document). Expand
A Reinforcement Learning Framework for Optimizing Age of Information in RF-Powered Communication Systems
TLDR
A deep reinforcement learning (DRL) algorithm is proposed that can learn the age-optimal policy in a computationally-efficient manner and characterize the structural properties of this policy analytically, and demonstrate that it has a threshold-based structure with respect to the AoI values for different processes. Expand
Plug and Play Autoencoders for Conditional Text Generation
TLDR
Evaluations on style transfer tasks both with and without sequence-to-sequence supervision show that the proposed plug and play Emb2Emb method performs better than or comparable to strong baselines while being up to four times faster. Expand
Non-linear Age of Information in a Discrete Time Queue: Stationary Distribution and Average Performance Analysis
TLDR
This paper considers a status update communication system consisting of a source-destination link with timeliness requirements and obtains a general formula of the stationary distribution of the AoI and a methodology for analyzing general non-linear age functions for this type of systems. Expand
Power Minimization in Wireless Sensor Networks With Constrained AoI Using Stochastic Optimization
TLDR
This paper forms an optimization problem to minimize the time average total transmit power of sensors by jointly optimizing the sampling action of each sensor, the transmit power allocation, and the subchannel assignment under the constraints on the maximum time average AoI and maximum power of each sensors. Expand
Human versus Machine Attention in Document Classification: A Dataset with Crowdsourced Annotations
TLDR
In conclusion, aspect-based sentiment analysis and attention mechanism are proposed as a methodology for document classification reference EPFL-CONF-222451 to improve quality and efficiency in the classification of documents. Expand
Optimal Policies for Status Update Generation in an IoT Device With Heterogeneous Traffic
TLDR
This work considers the problem of optimally controlling the status update generation process for a system with a source–destination pair that communicates via a wireless link and utilizes the framework of Markov decision processes to derive the optimal policy for the generation of status update packets. Expand
AoI-Optimal Joint Sampling and Updating for Wireless Powered Communication Systems
TLDR
This paper characterizes the structure of the Age of Information (AoI)-optimal policy in wireless powered communication systems while accounting for the time and energy costs of generating status updates at the source nodes and analytically demonstrates that the AoI-optimal Policy has a threshold-based structure w.r.t. the state variables. Expand
Online Age-Minimal Sampling Policy for RF-Powered IoT Networks
TLDR
This paper studies a real-time Internet of Things (IoT)-enabled monitoring system in which a source node is responsible for maintaining the freshness of information status at a destination node by sending update packets, and analytically establishes the monotonicity property of the value function associated with the MDP. Expand
Optimal Sampling Cost in Wireless Networks with Age of Information Constraints
TLDR
A dynamic algorithm is developed that takes decisions in a slot-by-slot basis for minimizing the time average cost of sampling and transmitting status updates by users over a wireless channel subject to average Age of Information constraints. Expand
...
1
2
3
4
...