18 citations · 24 across the 14 of their papers we have counts for
15 papers
Constrained Deep Reinforcement Learning for Fronthaul Compression Optimization
Axel Grönland, Alessio Russo, Yassir Jedra +2
In the Centralized-Radio Access Network (C-RAN) architecture, functions can be placed in the central or distributed locations. This architecture can offer higher capacity and cost…
Conformal Off-Policy Evaluation in Markov Decision Processes
Daniele Foffano, Alessio Russo, Alexandre Proutiere
Reinforcement Learning aims at identifying and evaluating efficient control policies from data. In many real-world applications, the learner is not allowed to experiment and cannot…
Network analysis on political election; populist vs social emergent behaviour
Andrea Russo, Vincenzo Miracula, Antonio Picone
Social networks play an important role in people's daily socialization, particularly through social media platforms, which have become key channels for communication and informatio…
Entropy-rate as prediction method for newspapers and information diffusion
Andrea Russo, Antonio Picone, Vincenzo Miracula +2
This paper aims to show how some popular topics on social networks can be used to predict online newspaper views, related to the topics. Newspapers site and many social networks, b…
On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure
Alessio Russo, Alexandre Proutiere
We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call repre…
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
Alessio Russo
In recent years, there has been a growing interest in the effects of data poisoning attacks on data-driven control methods. Poisoning attacks are well-known to the Machine Learning…
Model Based Residual Policy Learning with Applications to Antenna Control
Viktor Eriksson Möllerstedt, Alessio Russo, Maxime Bouton
Non-differentiable controllers and rule-based policies are widely used for controlling real systems such as telecommunication networks and robots. Specifically, parameters of mobil…
Self-Tuning Tube-based Model Predictive Control
Damianos Tranos, Alessio Russo, Alexandre Proutiere
We present Self-Tuning Tube-based Model Predictive Control (STT-MPC), an adaptive robust control algorithm for uncertain linear systems with additive disturbances based on the leas…
Tube-Based Zonotopic Data-Driven Predictive Control
Alessio Russo, Alexandre Proutiere
We present a novel tube-based data-driven predictive control method for linear systems affected by a bounded addictive disturbance. Our method leverages recent results in the reach…
Balancing detectability and performance of attacks on the control channel of Markov Decision Processes
Alessio Russo, Alexandre Proutiere
We investigate the problem of designing optimal stealthy poisoning attacks on the control channel of Markov decision processes (MDPs). This research is motivated by the recent inte…
Some Ethical Issues in the Review Process of Machine Learning Conferences
Alessio Russo
Recent successes in the Machine Learning community have led to a steep increase in the number of papers submitted to conferences. This increase made more prominent some of the issu…
Data-Driven Control and Data-Poisoning attacks in Buildings: the KTH Live-In Lab case study
Alessio Russo, Marco Molinari, Alexandre Proutiere
This work investigates the feasibility of using input-output data-driven control techniques for building control and their susceptibility to data-poisoning techniques. The analysis…
Poisoning Attacks against Data-Driven Control Methods
Alessio Russo, Alexandre Proutiere
This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the…
Minimizing Information Leakage of Abrupt Changes in Stochastic Systems
Alessio Russo, Alexandre Proutiere
This work investigates the problem of analyzing privacy of abrupt changes for general Markov processes. These processes may be affected by changes, or exogenous signals, that need…
Optimal Attacks on Reinforcement Learning Policies
Alessio Russo, Alexandre Proutiere
Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the p…