Past events

The computer science colloquium takes place on Mondays and Fridays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Arvind Narayanan (University of Minnesota), will be giving a talk titled "Measuring, Mapping and Predicting Commercial 5G Performance: A UE Perspective".

Abstract

With its touted ultra-high bandwidth and low latency, 5th generation (5G) wireless technology is envisaged to usher in a new smart and connected world. The goals of our research on 5G are two fold. First, we want to get empirical insights of network and application performance of commercial 5G under several realistic settings, and compare them with its predecessor (4G/LTE). Second, we want to identify novel challenges that are 5G-specific and propose mechanisms to overcome them.

My talk consists of three parts. In the first part, I will describe our measurement study of commercial 5G networks with special focus on millimeter wave (mmWave) 5G. It is to our knowledge a first comprehensive characterization of 5G network performance on smartphones by closely examining 5G service of three carriers (two mmWave carriers, one mid-band carrier) in three U.S. cities. This study finds that commercial mmWave 5G can achieve an impressive throughput of 2 Gbps. However, due to the known poor signal propagation characteristics of mmWave, 5G throughput perceived by the user equipment (UE) is highly sensitive to user mobility and obstructions resulting in a high number of 4G-5G handoffs. Such characteristics of mmWave 5G can make the throughput fluctuate frequently and wildly (between a range of 0 and 2 Gbps) which may confuse applications (e.g., the video bitrate adaptation) and bring highly inconsistent user experiences. Motivated by such insights, the second part of my talk will go beyond the basic measurement and describe Lumos5G - a novel and composable ML-based 5G throughput prediction framework that judiciously considers features and their combinations to make context-aware 5G throughput predictions. Through extensive on-field experiments and statistical analysis, we identify key UE-side factors affecting mmWave 5G performance. Besides geolocation, we quantitatively reveal several other UE-side contextual factors (such as geometric features between UE and 5G panel, mobility speed/mode, etc.) impact 5G throughput -- far more sophisticated than those impacting 4G/LTE. Instead of independently affecting the performance, we find these factors may cause complex interplay that is difficult to model analytically. We demonstrate that compared to existing approaches, Lumos5G is able to achieve 1.37x to 4.84x reduction in prediction error. This work can be viewed as a feasibility study for building what we envisage as a dynamic 5G performance map (akin to Google traffic map). In the third part, I will use our 18-months of experience conducting field experiments of commercial 5G to give my thoughts on the current 5G landscape and highlight both the research opportunities and challenges offered by the 5G ecosystem.

For more information, visit us @ https://5gophers.umn.edu

Biography

Arvind Narayanan is a Ph.D. Candidate in the Department of Computer Science & Engineering at the University of Minnesota, advised by Professor Zhi-Li Zhang and Professor Feng Qian. His research interests are broadly in the areas of emerging scalable network architectures (such as NFVs), 5G mobile networking, network data science and content distribution networks (CDNs). He has published papers in several top venues such as WWW, IMC, SIGCOMM, CoNEXT, APNET, Journal of Voice, GLOBECOM, ICDCS, etc. Arvind's recent work on 5G (including the publicly released datasets) has become the de facto baseline to understand and evaluate the evolution of commercial 5G's network performance. His work on DeepCache was the recipient of the Best Paper Award at SIGCOMM Workshop NetAI'18. Arvind completed his M.S. in Computer Science from the same department, and graduated with B.E. in Computer Engineering with highest distinction from the University of Mumbai where he was also awarded the Best Overall Student in his batch (1 out of 120).

The computer science colloquium takes place on Mondays and Fridays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Michał Dereziński (University of California, Berkeley), will be giving a talk titled "Bridging algorithmic and statistical randomness in machine learning".

Abstract

Randomness is a key resource in designing efficient algorithms, and it is also a fundamental modeling framework in statistics and machine learning. Methods that lie at the intersection of algorithmic and statistical randomness are at the forefront of modern data science. In this talk, I will discuss how statistical assumptions affect the bias-variance trade-offs and performance characteristics of randomized algorithms for, among others, linear regression, stochastic optimization, and dimensionality reduction. I will also present an efficient algorithmic framework, called joint sampling, which is used to both predict and improve the statistical performance of machine learning methods, by injecting carefully chosen correlations into randomized algorithms.

In the first part of the talk, I will focus on the phenomenon of inversion bias, which is a systematic bias caused by inverting random matrices. Inversion bias is a significant bottleneck in parallel and distributed approaches to linear regression, second order optimization, and a range of statistical estimation tasks. Here, I will introduce a joint sampling technique called Volume Sampling, which is the first method to eliminate inversion bias in model averaging. In the second part, I will demonstrate how the spectral properties of data distributions determine the statistical performance of machine learning algorithms, going beyond worst-case analysis and revealing new phase transitions in statistical learning. Along the way, I will highlight a class of joint sampling methods called Determinantal Point Processes (DPPs), popularized in machine learning over the past fifteen years as a tractable model of diversity. In particular, I will present a new algorithmic technique called Distortion-Free Intermediate Sampling, which drastically reduced the computational cost of DPPs, turning them into a practical tool for large-scale data science. 

Biography

Michał Dereziński is a postdoctoral fellow in the Department of Statistics at the University of California, Berkeley. Previously, he was a research fellow at the Simons Institute for the Theory of Computing (Fall 2018, Foundations of Data Science program). He obtained his Ph.D. in Computer Science at the University of California, Santa Cruz, advised by professor Manfred Warmuth, where he received the Best Dissertation Award for his work on sampling methods in statistical learning. Michał's current research is focused on developing scalable randomized algorithms with robust statistical guarantees for machine learning, data science and optimization. His work on reducing the cost of interpretability in dimensionality reduction received the Best Paper Award at the Thirty-fourth Conference on Neural Information Processing Systems. More information is available at: https://users.soe.ucsc.edu/~mderezin/.

For this spring 2021 seminar series, GroupLens has invited the author of a recent human-computer interaction paper to come chat about their work.

• This week's paper: To Live in Their Utopia: Why Algorithmic Systems Create Absurd Outcomes
• Author: Ali Alkhatib, Research Fellow at the Center for Applied Data Ethics at the University of San Francisco

The last day to receive a 25% tuition refund for canceling full semester classes is Monday, February 15.

View the full academic schedule on One Stop.

The computer science colloquium takes place on Mondays and Fridays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Sarah Dean (University of California, Berkeley), will be giving a talk titled "Reliable Machine Learning in Feedback Systems".

Abstract

Machine learning techniques have been successful for processing complex information, and thus they have the potential to play an important role in data-driven decision-making and control. However, ensuring the reliability of these methods in feedback systems remains a challenge, since classic statistical and algorithmic guarantees do not always hold.

In this talk, I will provide rigorous guarantees of safety and discovery in dynamical settings relevant to robotics and recommendation systems. I take a perspective based on reachability, to specify which parts of the state space the system avoids (safety) or can be driven to (discovery). For data-driven control, we show finite-sample performance and safety guarantees which highlight relevant properties of the system to be controlled. For recommendation systems, we introduce a novel metric of discovery and show that it can be efficiently computed. In closing, I discuss how the reachability perspective can be used to design social-digital systems with a variety of important values in mind.

Biography

Sarah is a PhD candidate in the Department of Electrical Engineering and Computer Science at UC Berkeley, advised by Ben Recht. She received her MS in EECS from Berkeley and BSE in Electrical Engineering and Math from the University of Pennsylvania. Sarah is interested in the interplay between optimization, machine learning, and dynamics in real-world systems. Her research focuses on developing principled data-driven methods for control and decision-making, inspired by applications in robotics, recommendation systems, and developmental economics. She is a co-founder of a transdisciplinary student group, Graduates for Engaged and Extended Scholarship in computing and Engineering, and the recipient of a Berkeley Fellowship and a NSF Graduate Research Fellowship.

The computer science colloquium takes place on Mondays and Fridays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Tianyi Zhou (University of Washington), will be giving a talk titled "Learning Like a Human: How, Why, and When".

Abstract

Machine learning (ML) can surpass humans on certain complicated yet specific tasks. However, most ML methods treat samples/tasks equally, e.g., by taking a random batch per step and repeating many epochs' training on all data, which may work promisingly on well-processed data using sufficient computation but is extraordinarily suboptimal and inefficient from human perspectives, since we would never teach children or students in such a way. On the contrary, human learning is more strategic and smarter in selecting/generating the training contents for different learning stages via experienced teachers, collaboration of learners, curiosity and diversity in exploration, tracking of learned knowledge and progress, distributing a task into sub-tasks, etc., which have been underexplored in ML. The selection and scheduling of data/tasks is another type of intelligence as important as the optimization of model parameters on given data/tasks. My recent work aims to bridge this gap between human and machine intelligence. As we entering a new era of hybrid intelligence between humans and machines, it is important to make AI not only perform like humans in outcome presentations but also benefit from human-like strategies in its training.

In this talk, I will present several curriculum learning techniques we developed for improving supervised/semi-supervised/self-supervised learning, robust learning with noisy data, reinforcement learning, ensemble learning, etc., especially when the data are imperfect and thus a curriculum can make a big difference. Firstly, I will show how to translate human strategies in curriculum generation to discrete-continuous hybrid optimizations, which are challenging to solve in general but we can develop efficient and provable algorithms using techniques from submodular and convex/non-convex optimization. Curiosity and diversity play important roles in these formulations. Secondly, we build both empirical and theoretical connections between curriculum learning and the training dynamics of ML models on individual samples. Empirically, we find that deep neural networks are fast in memorizing some data but also fast in forgetting some others, so we can accurately allocate those easily forgotten data using training dynamics in very early stages and make the future training only focus on them. Moreover, we find that the consistency of model output overtime for an unlabeled sample is a reliable indicator of its prediction correctness and delineates the forgetting effects on previously learned data. In addition, the learning speed on samples/tasks provides critical information for future exploration. These discoveries are consistent with human learning strategies and lead to more efficient curricula for a rich class of ML problems. Theoretically, we derive a data selection criterion solely from the optimization of learning dynamics in continuous time. Interestingly, the resulted curriculum matches the previous empirical observations and has a natural connection to the neural tangent kernel in recent deep learning theories.

Biography

Tianyi Zhou is a Ph.D. candidate in the Paul G. Allen School of Computer Science and Engineering at University of Washington, advised by Professor Jeff A. Bilmes. His research interests are in machine learning, optimization, and natural language processing. His recent research focuses on transferring human learning strategies to machine learning in the wild, especially when the data are unlabeled, redundant, noisy, biased, or are collected via interaction, e.g., how to automatically generate a curriculum of data/tasks during the course of training. The studied problems cover supervised/semi-supervised/self-supervised learning, robust learning with noisy data, reinforcement learning, meta-learning, ensemble method, spectral method, etc. He has published ~50 papers at NeurIPS, ICML, ICLR, AISTATS, NAACL, COLING, KDD, AAAI, IJCAI, Machine Learning (Springer), IEEE TIP, IEEE TNNLS, IEEE TKDE, etc., with ~2000 citations. He is the recipient of the Best Student Paper Award at ICDM 2013 and the 2020 IEEE Computer Society Technical Committee on Scalable Computing (TCSC) Most Influential Paper Award.

Save the date for the Spring 2021 CSE Virtual Career Fair. Mark your calendar for Tuesday, February 9, 2021 and start preparing over winter break.

Spring 2021 CSE Virtual Career Fair
Tuesday, February 9, 2021
11 a.m.-6 p.m. Central Time
Virtual fair platform: Career Fair Plus

Similar to the Fall 2020 fair, the Spring fair will be held via the virtual platform, Career Fair Plus. The platform provides features that will allow you to connect personally with employers.

Virtual Career Fair features

• No waiting in line! Students can pre-register for a time to speak with employers to video chat.
• Speak with employers from the comfort and safety of your home.
• Research employers prior to the fair, as well as during the fair by entering the employer's group chat and info session room.

Download the Career Fair Plus app

Download the Career Fair Plus App in the App Store for Apple devices or the Google Play Store for Android devices. Once downloaded, search for the University of Minnesota, then College of Science and Engineering Career Fair. Alternatively, you can view the event online.

You can use the app now to begin researching employers. Winter break is a great time to begin researching employers, and new employers are being added each day! Additional instructions on how to sign-up to speak with employers will be provided soon after the beginning of spring semester.

Get your resume ready and prepare for interviews

Visit the CSE Career Fair website for resume and cover letter writing guides, interviewing tips, advice from employers, and more.

Career counselors are also available over winter break for individual appointments. Please reach out by scheduling a virtual appointment or by sending an email to csecareer@umn.edu.

The last day to receive a 50% tuition refund for canceling full semester classes is Monday, February 8.

View the full academic schedule on One Stop.

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Alex Lamb (University of Montreal), will be giving a talk titled "Latent Data Augmentation and Modular Structure for Improved Generalization".

Abstract

Deep neural networks have seen dramatic improvements in performance, with much of this improvement being driven by new architectures and training algorithms with better inductive biases.  At the same time, the future of AI is systems which run in an open-ended way which run on data unlike what was seen during training and which can be drawn from a changing or adversarial distribution.  These problems also require a greater scale and time horizon for reasoning as well as consideration of a complex world system with many reused structures and subsystems.  This talk will survey some areas where deep networks can improve their biases as well as my research in this direction.  These algorithms dramatically change the behavior of deep networks, yet they are highly practical and easy to use, conforming to simple interfaces that allow them to easily be dropped into existing codebases.  

Biography

Alex Lamb is a PhD student at the University of Montreal advised by Yoshua Bengio and a recipient of the Twitch PhD Fellowship 2020.  His research is on the intersection of developing new algorithms for machine learning and new applications.  In the area of algorithms, he is particularly interested in (1) making deep networks more modular and richly structured and (2) improving the generalization performance of deep networks, especially across shifting domains.  He is particularly interested in techniques which use functional inspiration from the brain and psychology to improve performance on real tasks.  In terms of applications of Machine Learning, his most recent work has been on historical Japanese documents and has resulted in KuroNet, a publicly released service which generates automatic analysis and annotations to make classical Japanese documents (more) understandable to readers of modern Japanese.  

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Wei Hu (Princeton University), will be giving a talk titled "On the Foundations of Deep Learning: Over-parameterization, Generalization, and Representation Learning".

Abstract

Despite the phenomenal empirical successes of deep learning in many application domains, its underlying mathematical mechanisms remain poorly understood. Mysteriously, deep neural networks in practice can often fit training data perfectly and generalize remarkably well to unseen test data, despite highly non-convex optimization landscapes and significant over-parameterization. Moreover, deep neural networks show extraordinary ability to perform representation learning: feature representation extracted from a neural network can be useful for other related tasks.

In this talk, I will present our recent progress on the theoretical foundations of deep learning. First, I will show that gradient descent on deep linear neural networks induces an implicit regularization effect towards low rank, which explains the surprising generalization behavior of deep linear networks for the low-rank matrix completion problem. Next, turning to nonlinear deep neural networks, I will talk about a line of studies on wide neural networks, where by drawing a connection to the neural tangent kernels, we can answer various questions such as how training loss is minimized, why trained network can generalize, and why certain component in the network architecture is useful; we also use theoretical insights to design a new simple and effective method for training on noisily labeled datasets. Finally, I will analyze the statistical aspect of representation learning, and identify conditions that enable efficient use of training data, bypassing a known hurdle in the i.i.d. tasks setting.

Biography

Wei Hu is a PhD candidate in the Department of Computer Science at Princeton University, advised by Sanjeev Arora. Previously, he obtained his B.E. in Computer Science from Tsinghua University. He has also spent time as a research intern at research labs of Google and Microsoft. His current research interest is broadly in the theoretical foundations of modern machine learning. In particular, his main focus is on obtaining solid theoretical understanding of deep learning, as well as using theoretical insights to design practical and principled machine learning methods.