The 22nd International Conference on Runtime Verification (RV'22), will take place as part of the Computational Logic Autumn Summit (CLAS 2022) in Tbilisi, Georgia, from September 28-30, 2022.
The RV 2022 conference is sponsored by:
|Conference:||28-30 September 2022|
Proceedings are now available online at Springer
Program: see program in EasyChair (tentative)
Accepted Papers: please see the list of accepted papers.
Keynote speakers (click to unfold abstracts):
Serdar Tasiran, Amazon Web Services, US:
Runtime Monitoring of Distributed Systems at Amazon Web Services
Learning by Bootstrapping of Latents
We will discuss self-supervised representation learning and a new paradigm for it based on bootstrapping of latents. We first present BYOL for images, which relies on two neural networks, referred to as online and target, that interact and learn from each other: From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While prior methods had intrinsically relied on negative pairs, BYOL achieved a new state of the art without them. We will also describe follow-ups of BYOL that we have explored within DeepMind, BGRL for graphs, MYOW for new uncharted domains such as neural readings, and BraVe for videos. We finally apply the paradigm to reinforcement learning and discuss curiosity-driven exploration when the rewards are sparse or absent. For this setting, we give a brand new algorithm BYOL-Explore that jointly learns a world representation, the world dynamics, and an exploration policy.
Bio: Michal is a machine learning scientist in DeepMind Paris, tenured researcher at Inria, and the lecturer of the master course Graphs in Machine Learning at l’ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. This means reducing the “intelligence” that humans need to input into the system and minimizing the data that humans need to spend inspecting, classifying, or “tuning” the algorithms. That is why he is working in domains that are able to deal with minimal feedback, such as deep reinforcement learning and self-supervised learning. He received his Ph.D. in 2011 from the University of Pittsburgh under the supervision of Miloš Hauskrecht and after was a postdoc of Rémi Munos before taking a permanent position at Inria in 2012 and at DeepMind in 2019.
Hybrid Setup: Although we hope that it will be possible for most participants to attend CLAS physically, like many other events at CLAS, RV 2022 will be hybrid.
Runtime verification is concerned with the monitoring and analysis of the runtime behaviour of software and hardware systems. Runtime verification techniques are crucial for system correctness, reliability, and robustness; they provide an additional level of rigor and effectiveness compared to conventional testing and are generally more practical than exhaustive formal verification. Runtime verification can be used prior to deployment, for testing, verification, and debugging purposes, and after deployment for ensuring reliability, safety, and security and for providing fault containment and recovery as well as online system repair.
The topics of the conference include, but are not limited to:
Application areas of runtime verification include cyber-physical systems, autonomous systems, safety/mission critical systems, enterprise and systems software, cloud systems, reactive control systems, health management and diagnosis systems, and system security and privacy.
Please see the Call for Papers for details.