Search Results for author:
Found 9 papers, 0 papers with code
Multi-Objective Decision Transformers for Offline Reinforcement Learning
Offline Reinforcement Learning (RL) is structured to derive policies from static trajectory data without requiring real-time environment interactions.
Neural network approaches to point lattice decoding
It is exponential in the space dimension $n$, which induces shallow neural networks of exponential size.
Deep Reinforcement Learning for Resource Constrained Multiclass Scheduling in Wireless Networks
The problem of resource constrained scheduling in a dynamic and heterogeneous wireless setting is considered here.
Cache Updating Strategy Minimizing the Age of Information with Time-Varying Files' Popularities
Inspired by this solution for the relaxed problem, we propose a practical cache updating strategy that meets all the constraints of the original problem.
Information Theory Information Theory
GraphCL: Contrastive Self-Supervised Learning of Graph Representations
We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner.
Distributed Resource Allocation Algorithms for Multi-Operator Cognitive Communication Systems
We address the problem of resource allocation (RA) in a cognitive radio (CR) communication system with multiple secondary operators sharing spectrum with an incumbent primary operator.
A lattice-based approach to the expressivity of deep ReLU neural networks
We prove that they can be computed by ReLU networks with quadratic depth and linear width in the space dimension.
On the CVP for the root lattices via folding with deep ReLU neural networks
Lattice decoding in Rn, known as the closest vector problem (CVP), becomes a classification problem in the fundamental parallelotope with a piecewise linear function defining the boundary.
Multilevel MIMO Detection with Deep Learning
A quasi-static flat multiple-antenna channel is considered.
