arXiv subjects

Rolf Stadler

Publications and source records attributed to Rolf Stadler.

22 records · Page 2Linked to original sources

arXiv2020

Online feature selection for rapid, low-overhead learning in networked systems

Data-driven functions for operation and management often require measurements collected through monitoring for model training and prediction. The number of data sources can be very large, which requires a significant communication and computing overhead to continuously extract and collect this data, as well as to train and update the machine-learning models. We present an online algorithm, called OSFS, that selects a small feature set from a large number of available data sources, which allows for rapid, low-overhead, and effective learning and prediction. OSFS is instantiated with a feature ranking algorithm and applies the concept of a stable feature set, which we introduce in the paper. We perform extensive, experimental evaluation of our method on data from an in-house testbed. We find that OSFS requires several hundreds measurements to reduce the number of data sources by two orders of magnitude, from which models are trained with acceptable prediction accuracy. While our method is heuristic and can be improved in many ways, the results clearly suggests that many learning tasks do not require a lengthy monitoring phase and expensive offline training.

cs.LG↗

arXiv2020

Finding Effective Security Strategies through Reinforcement Learning and Self-Play

We present a method to automatically find security strategies for the use case of intrusion prevention. Following this method, we model the interaction between an attacker and a defender as a Markov game and let attack and defense strategies evolve through reinforcement learning and self-play without human intervention. Using a simple infrastructure configuration, we demonstrate that effective security strategies can emerge from self-play. This shows that self-play, which has been applied in other domains with great success, can be effective in the context of network security. Inspection of the converged policies show that the emerged policies reflect common-sense knowledge and are similar to strategies of humans. Moreover, we address known challenges of reinforcement learning in this domain and present an approach that uses function approximation, an opponent pool, and an autoregressive policy representation. Through evaluations we show that our method is superior to two baseline methods but that policy convergence in self-play remains a challenge.

cs.LG↗

arXiv2015

Predicting SLA Violations in Real Time using Online Machine Learning

Detecting faults and SLA violations in a timely manner is critical for telecom providers, in order to avoid loss in business, revenue and reputation. At the same time predicting SLA violations for user services in telecom environments is difficult, due to time-varying user demands and infrastructure load conditions. In this paper, we propose a service-agnostic online learning approach, whereby the behavior of the system is learned on the fly, in order to predict client-side SLA violations. The approach uses device-level metrics, which are collected in a streaming fashion on the server side. Our results show that the approach can produce highly accurate predictions (>90% classification accuracy and < 10% false alarm rate) in scenarios where SLA violations are predicted for a video-on-demand service under changing load patterns. The paper also highlight the limitations of traditional offline learning methods, which perform significantly worse in many of the considered scenarios.

cs.NI↗

arXiv2010

The Accuracy of Tree-based Counting in Dynamic Networks

Tree-based protocols are ubiquitous in distributed systems. They are flexible, they perform generally well, and, in static conditions, their analysis is mostly simple. Under churn, however, node joins and failures can have complex global effects on the tree overlays, making analysis surprisingly subtle. To our knowledge, few prior analytic results for performance estimation of tree based protocols under churn are currently known. We study a simple Bellman-Ford-like protocol which performs network size estimation over a tree-shaped overlay. A continuous time Markov model is constructed which allows key protocol characteristics to be estimated, including the expected number of nodes at a given (perceived) distance to the root and, for each such node, the expected (perceived) size of the subnetwork rooted at that node. We validate the model by simulation, using a range of network sizes, node degrees, and churn-to-protocol rates, with convincing results.

cs.DC↗