Centre for Networked Intelligence

Dear all, Please note that there has been an update to the CNI seminar schedule. This talk has been rescheduled to Monday, 12 January, from 5:00 to 6:00 PM. ----------------------------------------------------------------------------------------------------------------- Dear All, Networks Seminar, supported by the Centre for Networked Intelligence, is a technical discussion forum in topics including but not limited to computer networks, machine learning, signal processing, and information theory. The seminar series has a webpage hosted at https://cni.iisc.ac.in/seminars/. You are invited to the following seminar held as part of this series. Title: On Some Ultra-Sharp Bounds in Queueing Systems Speaker: Professor Florin Ciucu, Professor, University of Warwick Time: 4:00 PM - 5:00 PM (IST) 5:00 PM - 6:00 PM (IST) Date: 13 January 2026 12 January 2026 Venue: GJ Hall and Online on Zoom Zoom link: https://us06web.zoom.us/j/83388976389?pwd=XcpO3GhLxsR14a7SVbPx33HQQa1jbt.1 Zoom Meeting ID: 833 8897 6389, Pass Code: NSSIISc YouTube Livestream: https://www.youtube.com/watch?v=Uf3J5TI_zNQ Webpage Link: <https://cni.iisc.ac.in/seminars/2026-01-13/> https://cni.iisc.ac.in/seminars/2026-01-12/ Abstract: The talk introduces two new classes of ultra-sharp bounds in queueing systems. The first is specific to the G/G/1 queue, with possibly correlated inter-arrivals; the main result is an exact expression for the distribution of the delay in terms of a series, whose terms are subject to elementary integration. Remarkably, the first few terms are sufficient to render ultra-sharp bounds improving upon state-of-the-art bounds by orders of magnitude. The second new class of bounds is specific to a tandem queueing network with general (i.e., not necessarily Poisson) arrivals and light-tailed service times. Besides showing for the first time that the end-to-end delay distribution is subject to a polynomial-exponential structure, explicit bounds computed in some special cases are shown to improve upon state-of-the-art results by many orders of magnitude. Bio: Florin Ciucu is a Professor in the CS Department at the University of Warwick. His research interests are stochastic analysis of communication networks and non-asymptotic analysis of stochastic bandits. He co-chaired ACM Sigmetrics 2024 and served on the Technical Program Committees of several other top conferences; currently he is on the Editorial Boards of the Performance Evaluation Journal and IEEE Transactions on Networking. Florin is a recipient of the ACM Sigmetrics 2005 Best Student Paper Award and IFIP Performance 2014 Best Paper Award. More details: https://www.dcs.warwick.ac.uk/~florin/ ALL ARE WELCOME. Thank you, CNI Seminar Series Organizing Committee.

Dear all, Please note that there has been an update to the CNI seminar schedule. This talk has been rescheduled to Tuesday, 13 January, from 5:00 to 6:00 PM. ----------------------------------------------------------------------------------------------------------------- Dear All, Networks Seminar, supported by the Centre for Networked Intelligence, is a technical discussion forum in topics including but not limited to computer networks, machine learning, signal processing, and information theory. The seminar series has a webpage hosted at https://cni.iisc.ac.in/seminars/. You are invited to the following seminar held as part of this series. Title: Learning with Minimal Human Feedback Speaker: Professor Alexandre Proutiere, Professor, KTH Royal Institute of Technology, Sweden Time: 4:00 PM - 5:00 PM (IST) 5:00 PM - 6:00 PM (IST) Date: 12 January 2026 13 January 2026 Venue: GJ Hall and Online on Zoom Zoom link: https://us06web.zoom.us/j/83388976389?pwd=XcpO3GhLxsR14a7SVbPx33HQQa1jbt.1 Zoom Meeting ID: 833 8897 6389, Pass Code: NSSIISc YouTube Livestream: https://www.youtube.com/watch?v=k_gA2MlKzTg Webpage Link: <https://cni.iisc.ac.in/seminars/2026-01-12/> https://cni.iisc.ac.in/seminars/2026-01-13/ Abstract: Many learning tasks, such as model alignment and fine-tuning, rely on costly human feedback, making it essential to minimize such interventions. In this talk, we formalize this challenge in the setting of online classification tasks, motivated by question-answering problems, and introduce the framework of online classification with expert guidance. For this problem, we propose algorithms tailored to both low- and high-budget regimes. We establish regret upper bounds for these algorithms by combining concentration-of-measure techniques with tools from convex geometry. Our approach is further validated through experiments, including evaluations on real-world question-answering datasets using embeddings derived from state-of-the-art large language models. Bio: Alexandre Proutiere is Professor in the Decision and Control Systems at KTH Royal Institute of Technology, Sweden. Before joining KTH in 2011, he was a researcher at Microsoft Research, and a research engineer at France Telecom R&D. He was an invited lecturer and researcher at the computer science department ENS Paris. His current research interests include probability, optimization, and machine learning. Education and awards: PhD in Applied Mathematics from Ecole Polytechnique, Graduated in Mathematiques from Ecole Normale Superieure, Engineering degree from Telecom Paris, Engineer from Corps des Mines. Awards: ACM Sigmetrics rising star award in 2009, ACM best papers awards at Sigmetrics 2004 and 2010, and Mobihoc 2009. ACM Sigmetrics test of time award in 2025. Recipient of an ERC consolidator grant 2012-2017. More details: https://people.kth.se/~alepro/ ALL ARE WELCOME. Thank you, CNI Seminar Series Organizing Committee.

Dear All, Networks Seminar, supported by the Centre for Networked Intelligence, is a technical discussion forum in topics including but not limited to computer networks, machine learning, signal processing, and information theory. The seminar series has a webpage hosted at https://cni.iisc.ac.in/seminars/. You are invited to the following seminar held as part of this series. Title: The Synergy Between Quality of Experience and Deep Reinforcement Learning for Uncoordinated Multi-Agent Resource Allocation in Cognitive Radio Network Speaker: Professor Andres Kwasinski, Professor, Rochester Institute of Technology, USA Time: 4:00 PM - 5:00 PM (IST) Date: 14 January 2026 Venue: GJ Hall and Online on Zoom Zoom link: https://us06web.zoom.us/j/83388976389?pwd=XcpO3GhLxsR14a7SVbPx33HQQa1jbt.1 Zoom Meeting ID: 833 8897 6389, Pass Code: NSSIISc YouTube Livestream: https://www.youtube.com/watch?v=-1aL9hRchag Webpage Link: https://cni.iisc.ac.in/seminars/2026-01-14/ Abstract: The paradigm of a cognitive radio is that of a wireless device capable of autonomously learning to derive from observations awareness of the wireless environment state and adapt its resource allocation accordingly. Reinforcement Learning (RL) offers a natural framework for realizing this paradigm, but it faces the challenge of long learning times when the operating scenario is one where the cognitive radios operate in a fully distributed and uncoordinated fashion. One approach to accelerate learning is for those cognitive radios that have already learned a representation of the environment and the results of its actions, to transfer their experience to those cognitive radios that are joining the network and have not learned yet. However, the experience learned by one cognitive radio may not be useful for another because they may each be carrying vastly different types of traffic. In this talk, I will discuss how representing the effect of resource allocation using certain Quality of Experience metrics makes the experience learned by one cognitive radio be agnostic to the traffic type and can be shared to other radios even if they are servicing traffic of a different type. For this to be possible, the Quality of Experience metric needs to measure the perceived quality for different traffic using the same scale. The result is that cognitive radios joining the network can learn faster experiencing a negligible loss in Quality of Experience. Bio: Andres Kwasinski is a Professor and Director of the Ph.D. program in Electrical and Computer Engineering at the Rochester Institute of Technology, Rochester, NY, USA. He has co-authored more than 110 peer-reviewed publications and four books published by Cambridge University Press and Wiley. His research interests include cognitive radios and wireless networks, cross-layer techniques in wireless communications, and smart infrastructures and networking. He currently serves on the Senior Editorial Board of the IEEE Signal Processing Magazine, where he has also been Area Editor and Associate Editor. He has previously served as an Editor for IEEE Transactions on Wireless Communications and IEEE Wireless Communications Letters. He received the Diploma in Electrical Engineering from the Buenos Aires Institute of Technology, Argentina, and the M.Sc. and Ph.D. degrees in Electrical and Computer Engineering from the University of Maryland, College Park, USA. Dr. Kwasinski is a Senior Member of the IEEE. More details: https://www.rit.edu/directory/axkeec-andres-kwasinski ALL ARE WELCOME. Thank you, CNI Seminar Series Organizing Committee.