Sergey Gorinsky | IMDEA Networks Institute, Madrid |
Friday, November 12, 2021 | 14:00 (CET, 12:00 UTC)

register here: https://zoom.us/meeting/register/tJMkf-6uqToqGtBEFcMtNYXq-7c0husl_qOb

Abstract:
Content delivery networks (CDNs) distribute much of the Internet content by caching and serving the objects requested by users. A major goal of a CDN is to maximize the hit rates of its caches, thereby enabling faster content downloads to the users. Content caching involves two components: an admission algorithm to decide whether to cache an object and an eviction algorithm to decide which object to evict from the cache when it is full. In this paper, we focus on cache admission and propose an algorithm called RL-Cache that uses model-free reinforcement learning (RL) to decide whether or not to admit a requested object into the CDN’s cache. Unlike prior approaches that use a small set of criteria for decision making, RL-Cache weights a large set of features that include the object size, recency, and frequency of access. We develop a publicly available implementation of RL-Cache and perform an evaluation using production traces for the image, video, and web traffic classes from Akamai’s CDN. The evaluation shows that RL-Cache improves the hit rate in comparison with the state of the art and imposes only a modest resource overhead on the CDN servers. Further, RL-Cache is robust enough that it can be trained in one location and executed on request traces of the same or different traffic classes in other locations of the same geographic region.

Bio:
Sergey Gorinsky is a tenured Research Associate Professor at IMDEA Networks Institute in Madrid, Spain. He joined the institute in 2009 and leads the NetEcon (Network Economics) research group there. Dr. Gorinsky received his Ph.D. and M.S. degrees from the University of Texas at Austin, USA in 2003 and 1999 respectively and Engineer degree from Moscow Institute of Electronic Technology, Zelenograd, Russia in 1994. From 2003 to 2009, he served on the tenure-track faculty at Washington University in St. Louis, USA. In 2010-2014, Dr. Gorinsky was a Ramón y Cajal Fellow funded by the Spanish Government. Sergey Gorinsky graduated four Ph.D. students. The areas of his primary research interests are computer networking, distributed systems, and network economics. His work appeared at top conferences and journals such as SIGCOMM, CoNEXT, INFOCOM, Transactions on Networking, and Journal on Selected Areas in Communications. He served as a TPC chair of ICNP 2017 and other conferences, as well as a TPC member for a much broader conference population. Sergey Gorinsky contributed to conference organization in many roles, such as a general chair of SIGCOMM 2018 and ICNP 2020. He also served as an evaluator of research proposals and projects for the European Research Council (ERC StG), European Commission (Horizon 2020, FP7), COST Association, and numerous other funding agencies.

Werner Bailer | Joanneum Research, Graz | Friday, June 25, 2021 | 10:00 (CET, 08:00 UTC) | online

Abstract:

Artificial neural networks have been adopted for a broad range of tasks in multimedia analysis and processing, such as visual and acoustic classification, extraction of multimedia descriptors or image and video coding. The trained neural networks for these applications contain a large number of parameters (weights), resulting in a considerable size. Thus, transferring them to a number of clients using them in applications (e.g., mobile phones, smart cameras) benefits from a compressed representation of neural networks.

MPEG Neural Network Coding and Representation is the first international standard for efficient compression of neural networks (NNs). The standard is designed as a toolbox of compression methods, which can be used to create coding pipelines. It can be either used as an independent coding framework (with its own bitstream format) or together with external neural network formats and frameworks. For providing the highest degree of flexibility, the network compression methods operate per parameter tensor in order to always ensure proper decoding, even if no structure information is provided. The standard contains compression-efficient quantization and an arithmetic coding scheme (DeepCABAC) as core encoding and decoding technologies, as well as neural network parameter pre-processing methods like sparsification, pruning, low-rank decomposition, unification, local scaling and batch norm folding. NNR achieves a compression efficiency of more than 97% for transparent coding cases, i.e. without degrading classification quality, such as top-1 or top-5 accuracies.

This talk presents an overview of the context, technical features and characteristics of NN coding standard, and discusses ongoing topics such as incremental neural network representation.

Bio:

Werner Bailer is a Key Researcher at DIGITAL – Institute for Information and Communication Technologies at JOANNEUM RESEARCH in Graz, Austria. He received a degree in Media Technology and Design in 2002 for his diploma thesis on motion estimation and segmentation for film/video standards conversion. His research interests include audiovisual content analysis, multimedia retrieval and machine learning. He regularly contributes to standardization, among others in MPEG, where he co-chairs the ad-hoc group on neural network compression.

Benedek Kovács PhD | Senior Specialist, Ericsson R&D at Hungary | Friday, May 28, 2021 |

10:30 (CET, 08:30 UTC) |

Join on your computer or mobile app Click here to join the meeting

Join with a video conferencing device teams@video.meet.ericsson.net

Video Conference ID: 128 174 110 8 Alternate VTC dialing instructions

Abstract: We overview the edge computing status from a telecommunication networks perspective, give a definition, introduce an example. We discuss the different driving forces in the telecommunication and cloud industry and go thorugh the different solution proposals. We cover the networking, cloud and management aspects and show the different options using the example.