Past Events

We revisit the fundamental problem of physical layer communications, namely reproducing at one point a message selected at another point, to finally arrive at a trainable system that inherently learns to communicate and adapts to any channel environment. As such, we realize a data-driven system design, based on deep learning algorithms, leading to a universal framework that allows end-to-end optimization of the whole data-link without the need for prior mathematical modeling and analysis.

The application of supervised learning techniques for the design of the physical layer of a communication link is often impaired by the limited amount of pilot data available for each device; while the use of unsupervised learning is typically limited by the need to carry out a large number of training iterations. In this talk, meta-learning, or learning-to-learn, is introduced as a tool to alleviate these problems. The talk will consider an Internet-of-Things (IoT) scenario in which devices transmit sporadically using short packets with few pilot symbols over a fading channel.

no results

Many supervised learning methods are naturally cast as optimization problems. For prediction models which are linear in their parameters, this often leads to convex problems for which many guarantees exist. Models which are non-linear in their parameters such as neural networks lead to non-convex optimization problems for which guarantees are harder to obtain. In this talk, I will consider two-layer neural networks with homogeneous activation functions where the number of hidden neurons tends to infinity, and show how qualitative convergence guarantees may be derived.

In this talk, we will focus on the recently-emerged field of (adversarially) robust learning. This field began by the observation that modern learning models, despite the breakthrough performance, remain fragile to seemingly innocuous changes in the data such as small, norm-bounded perturbations of the input data. In response, various training methodologies have been developed for enhancing robustness. However, it is fair to say that our understanding in this field is still at its infancy and several key questions remain widely open. We will consider two such questions.

A welcome back meeting for new and returning students who are part of the Wireless Networking & Communications Group. Connect with WNCG faculty, staff, and students as we gear up to start a new academic year. Get a refresher on who we are and what we do, and catch up on the latest developments in WNCG research through a series of casual lightning pitch updates from some of your fellow researchers. Access: Zoom meeting details will be provided via email to the WNCG student list.

no results

Seminar time shown in CDT (UTC -5)

Join us for a special virtual installment of the ML Seminar Series: In this talk, we aim to quantify the robustness of distributed training against worst-case failures and adversarial nodes. We show that there is a gap between robustness guarantees, depending on whether adversarial nodes have full control of the hardware, the training data, or both. Using ideas from robust statistics and coding theory we establish robust and scalable training methods for centralized, parameter server systems.

Few-shot classification, the task of adapting a classifier to unseen classes given a small labeled dataset, is an important step on the path toward human-like machine learning. I will present what I think are some of the key advances and open questions in this area. I will then focus on the fundamental issue of overfitting in the few-shot scenario. Bayesian methods are well-suited to tackling this issue because they allow practitioners to specify prior beliefs and update those beliefs in light of observed data.