- talks - lists.cs.princeton.edu

GEO/AOS/HMEI Seminar: Elizabeth Barnes - Thursday, Nov 10
by Emily C. Lawrence 04 Nov '22

04 Nov '22

GEO/AOS/HMEI Thursday Seminar Series Speaker: Elizabeth A. Barnes, Professor, Dept. of Atmospheric Science, Colorado State University Date: Thursday, November 10, 2022 Time: 12:30 p.m. Location: Guyot 220 Title: “Explainable AI for Climate Science: Detection, Prediction and Discovery” Abstract: Earth’s climate is chaotic and noisy. Finding usable signals amidst all of the noise can be challenging. Here, I will demonstrate how explainable artificial intelligence (XAI) techniques can sift through vast amounts of climate data and push the bounds of scientific discovery. Examples include extracting robust indicator patterns of climate change and identifying Earth system states that lead to more predictable behavior weeks-to-years in advance. But machine learning models are only as capable as the scientists designing them. I will further discuss how climate science requires the crafting of domain specific XAI methods, both to gauge the trustworthiness of the XAI’s predictions and quantify uncertainty, but also to uncover predictable signals we didn't know were there. Explainable AI can open doors to scientific understanding — supporting scientists as we ask new questions about the coupled human-Earth system.

1 0

UPDATE: Math Department Colloquium - Wednesday, November 2, 2022
by Emily C. Lawrence 02 Nov '22

02 Nov '22

Today’s talk will be in-person only and will not be broadcasted over Zoom. [ https://www.math.princeton.edu/events/seminars/department-colloquium | DEPARTMENT COLLOQUIUM ] [ https://www.math.princeton.edu/events/algorithmic-spin-glass-theory-2022-11… | Andrea Montanari, Stanford University ] Algorithmic spin glass theory Wednesday, Nov 02 Fine Hall 314 / 4:30 PM - 5:30 PM *This Talk is In-Person Only* Mean field spin glasses are high-dimensional random functions with special exchangeability properties. These models were originally motivated by the study of disordered magnetic materials. However, it soon became clear that a large number of random optimization problems of interest in computer science and statistics fit this framework. Parisi's replica symmetry breaking (RSB) theory allows to determine the asymptotics of the optimal value of these problems. Can RSB shed light on relevant algorithmic questions as well? Here is a specific formalization of this question: Is there a polynomial time algorithm that outputs a feasible solution of these optimization problems whose value is, with high probability, within a factor \rho of the optimum? I will survey recent rigorous work that points at a remarkably precise answer for this question. Time permitting, I will talk about the problem of sampling from the Sherrington-Kirkpatrick Boltzmann measure. Based on joint work with Ahmed El Alaoui and Mark Sellke.

1 0

Math Department Colloquium - Wednesday, November 2, 2022
by Emily C. Lawrence 31 Oct '22

31 Oct '22

MATH DEPARTMENT COLLOQUIUM Andrea Montanari, Stanford University Algorithmic spin glass theory Wednesday, Nov 02 Fine Hall 314 / 4:30 PM - 5:30 PM In-Person and Online Talk Zoom Link: [ https://princeton.zoom.us/j/97792754638?pwd=MGFNcU5tMzZGczc5N0hpSTB6Y0hEUT09 | https://princeton.zoom.us/j/97792754638?pwd=MGFNcU5tMzZGczc5N0hpSTB6Y0hEUT09 ] Mean field spin glasses are high-dimensional random functions with special exchangeability properties. These models were originally motivated by the study of disordered magnetic materials. However, it soon became clear that a large number of random optimization problems of interest in computer science and statistics fit this framework. Parisi's replica symmetry breaking (RSB) theory allows to determine the asymptotics of the optimal value of these problems. Can RSB shed light on relevant algorithmic questions as well? Here is a specific formalization of this question: Is there a polynomial time algorithm that outputs a feasible solution of these optimization problems whose value is, with high probability, within a factor \rho of the optimum? I will survey recent rigorous work that points at a remarkably precise answer for this question. Time permitting, I will talk about the problem of sampling from the Sherrington-Kirkpatrick Boltzmann measure. BASED ON JOINT WORK WITH AHMED EL ALAOUI AND MARK SELLKE.

1 0

Princeton Robotics Seminar: Friday Oct 28 at 11am
by Emily C. Lawrence 25 Oct '22

25 Oct '22

Princeton Robotics Seminar Speaker: Tomás Lozano-Pérez, Professor of Computer Science & Engineering, MIT Date: Friday Oct 28, 2022 Time: 11am EDT Location: Computer Science 105 Event page: [ https://robo.princeton.edu/seminar | https://robo.princeton.edu/seminar ] Title: Generalization in Planning and Learning for Robotic Manipulation Abstract: An enduring goal of AI and robotics has been to build a robot capable of robustly performing a wide variety of tasks in a wide variety of environments; not by sequentially being programmed (or taught) to perform one task in one environment at a time, but rather by intelligently choosing appropriate actions for whatever task and environment it is facing. This goal remains a challenge. In this talk I’ll describe recent work in our lab aimed at the goal of general-purpose robot manipulation by integrating task-and-motion planning with various forms of model learning. In particular, I’ll describe approaches to manipulating objects without prior shape models, to acquiring composable sensorimotor skills, and to exploiting past experience for more efficient planning. Biography: Tomás Lozano-Pérez is Professor in EECS at MIT, and a member of CSAIL. He was a recipient of the 2011 IEEE Robotics Pioneer Award and a co-recipient of the 2021 IEEE Robotics and Automation Technical Field Award. He is a Fellow of the AAAI, ACM, and IEEE.

1 0

Yuanhao Wang will present his General Exam on Friday, October 21, 2022 at 12pm via Zoom.
by Nicki Mahler 20 Oct '22

20 Oct '22

Yuanhao Wang will present his General Exam on Friday, October 21, 2022 at 12pm via Zoom. Zoom link: [ https://princeton.zoom.us/j/4269281435 | https://princeton.zoom.us/j/4269281435 ] The members of his committee are as follows: Chi Jin (adviser), Huacheng Yu, and Jason Lee Abstract Reinforcement learning (RL) is an interactive decision making problem where an agent tries to maximize its cumulative reward through interacting with an unknown environment. RL has seen a surge of interest over the past decade, fueled primarily by its empirical success in a wide range of tasks, including Atari games, Go, robotics and dialogue systems. Motivated by and complementing empirical research, theoretical understanding of RL has also made substantial progress in the past few years. In the most basic case, tabular RL, minimax optimal algorithms have been identified and analyzed. Recent focus of research in the tabular case has shifted toward instance dependent bounds, adversarial settings and multi-agent RL. However, the tabular case fails to capture many real-world problems where the number of states is huge or infinite, in which case function approximation is necessary. In contrast to the usual supervised learning case where complexity measures such as VC dimension are able to characterize the feasibility of learning, the search for structural assumptions that would empower efficient RL remains inconclusive. It has been conjectured and recently proven that realizability alone is insufficient even for linear function approximation, making stronger conditions necessary. Several candidates include low Bellman rank, low witness rank and low Bellman-Eluder dimension, yet the picture is far from complete. My research focus would be on improving the theoretical understanding of RL by addressing some of the aforementioned challenges, such as those about multi-agent learning and function approximation RL. On the multi-agent side, I would like to investigate which solution concepts, such as rationalizability, no-regret and various equilibria, are attainable in RL. On the function approximation side, I hope to identify minimal structural assumptions that permit efficient RL. Reading List: [ https://docs.google.com/document/d/14rchqe0CO9DI9IvmXnFkNX4lf8HahLWtn1tAU0G… | https://docs.google.com/document/d/14rchqe0CO9DI9IvmXnFkNX4lf8HahLWtn1tAU0G… ] Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Civil & Environmental Engineering speaker: Andrea Castelletti, Tuesday, Nov 1
by Emily C. Lawrence 17 Oct '22

17 Oct '22

Civil & Environmental Engineering Speaker: Andrea Castelletti: Environmental Intelligence Lab, Politecnico di Milano Date: Tuesday, Nov 1, 2022 Time: 4:30PM Location: Louis Simpson, Room A71 Title: Machine Learning advancements for design of water and energy policies in a changing climate and society Abstract: Advances in environmental data monitoring and earth systems’ modeling have increasingly allowed us to accurately reproduce physical processes and their interactions at multiple scales, improving our ability to inform water and energy systems policy design. Yet, many process-based models are limited in predicting complex dynamics, which are the key to strategic planning, such as the impact of extreme weather and climate events or the mutual influence between humans and earth systems. Our work has shown that advanced data analytics and Machine Learning offer new opportunities to better characterize and model coupled human-earth system processes in a world in transition, ultimately supporting more equitable and efficient decision-making processes. In this talk, we provide an overview of recent advances in data-driven modeling and control of human-water-energy systems and showcase how Machine Learning techniques can help (i) infer natural and anthropogenic drivers of observed hydroclimatic patterns and improve their predictability in space and time, (ii) understand and conceptualize the mutual influences between human behaviors and water-energy systems; and (iii) design strategic planning and management policies optimizing multiple and conflicting objectives with different dynamics and informed by heterogeneous information. We recognize that this is a rapidly evolving research field, and we will also stimulate discussion around key challenges, including modeling decisions under uncertainty, model explain ability, data and computational requirements, model scalability, and transferability.

1 0

Princeton Robotics Seminar: Sarah Tang, Fri Oct 14
by Emily C. Lawrence 12 Oct '22

12 Oct '22

Princeton Robotics Seminar Speaker: [ https://www.sarahtang.net/ | Sarah Tang ] , Staff Software Engineer in Planning, Waymo Date: Friday Oct 14, 2022 Time: 11:00am EDT Location: Computer Science 105 Event page: [ https://robo.princeton.edu/seminar | https://robo.princeton.edu/seminar ] Title: Data-Centric ML for Autonomous Driving Abstract: Waymo is building the "World's Most Experienced Driver". This talk will discuss data challenges that arise when scaling machine learning systems with almost 1500 years worth of real-life human driving. Biography: Sarah is passionate about building robots that make intelligent decisions in complex, dynamic environments. She is currently a Staff Software Engineer on the Planner ML team at Waymo, where she is working to make driving safer, smarter, and more scalable with high-capacity models. In previous lives, she was the Tech Lead and Manager of the Motion Planning team at Nuro, where she led development of the decision making and trajectory optimization stack for major product milestones, including autonomous operation of their last-mile delivery robot without a driver nor a chase-car-operator in Arizona, California, and Texas. She was recognized in Business Insider’s 2021 list of “Rising stars in autonomous vehicles”. Sarah got her start in robotics as a member of Princeton's Great Class of 2013.

1 0

Sunayana Rane will present her General Exam "Correspondences between word learning in children and captioning models" on Friday, October 14, 2022 at 1:00 PM on Zoom.
by Louis W. Riehl 11 Oct '22

11 Oct '22

Sunayana Rane will present her General Exam "Correspondences between word learning in children and captioning models" on Friday, October 14, 2022 at 1:00 PM on Zoom. Zoom link: [ https://princeton.zoom.us/my/srane | https://princeton.zoom.us/my/srane ] Committee Members: Tom Griffiths (advisor), Olga Russakovsky, Karthik Narasimhan Abstract: For human children as well as machine learning systems, a key challenge in learning a word is linking the word to the visual phenomena it describes. Today I will present results from a project which aims to understand whether children and machine learning systems have developed similar mechanisms of solving this challenge. By organizing model output into word categories used to analyze child language learning data, we show a correspondence between word learning in children and the performance of image captioning models. Although captioning models are trained only on standard machine learning data, we find that their performance in producing words from a variety of word categories correlates with the age at which children acquire words from each of those categories. To explain why this correspondence exists, we show that the performance of captioning models is correlated with human judgments of the concreteness of words, suggesting that these models are capturing the complex real-world association between words and visual phenomena. Reading List: [ https://docs.google.com/document/d/1NJ4O8NIi2VyTCwKZVLuKgjIl35v8YpSurb_Qhb7… | https://docs.google.com/document/d/1NJ4O8NIi2VyTCwKZVLuKgjIl35v8YpSurb_Qhb7… ] g Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so. Louis Riehl Graduate Administrator Computer Science Department, CS213 Princeton University (609) 258-8014

1 0

Princeton Wireless Distinguished Seminar: Lajos Hanzo, Thursday Oct 13 at 12:30pm
by Emily C. Lawrence 11 Oct '22

11 Oct '22

Princeton Wireless Distinguished Seminar Series Speaker: Lajos Hanzo, University of Southampton, UK Title: Space, Air, Ground Integrated Networking from Single – To Multi-Component Pareto Optimization Day: October 13, 2022 Time: 12:30 pm EST (5:30 pm UK) Location: Zoom (Please Register) [ https://princeton.zoom.us/meeting/register/tJ0rdu6tqz4tEtZH5LmmVelIE-KL5dcw… | https://princeton.zoom.us/meeting/register/tJ0rdu6tqz4tEtZH5LmmVelIE-KL5dcw… ] Hosts: Kyle Jamieson & Yasaman Ghasempour Abstract: Thanks to the spectacular advances in signal processing and nano-technology, five wireless generations have been conceived over the past five decades. Indeed, near-capacity operation at an infinitesimally low error rate has become feasible and flawless multimedia communications is supported in areas of high traffic density, but how do we fill the huge coverage holes existing across the globe? As a promising system architecture, an integrated terrestrial, UAV-aided, airplane-assisted as well as satellite-based global coverage solution will be highlighted to pave the way for seamless next-generation service provision. However, these links exhibit strongly heterogeneous properties, hence requiring different enabling techniques. The joint optimization of the associated conflicting performance metrics of throughput, transmit power, latency, error probability, hand-over probability and link lifetime poses an extremely challenging problem. Explicitly, sophisticated multi-component system optimization is required for finding the Pareto-front of all optimal solutions, where none of the above-mentioned metric can be improved without degrading at least one of the others. Bio: Lajos Hanzo is a Fellow of the Royal Academy of Engineering (FREng), FIEEE, FIET and a EURASIP Fellow, Foreign Member of the Hungarian Academy of Science. He holds honorary Doctorates from the University of Edinburgh and the Technical University of Budapest. He co-authored 19 IEEE Press – John Wiley books and 2000+ research contributions at IEEE Xplore. For further information on his research in progress and associated publications, please refer to IEEE Xplore.

1 0

Haoyu Zhao will present his General Exam, "Coresets for Vertical Federated Learning" on Tuesday, October 11, 2022 at at 1:30 PM in via Zoom.
by Louis W. Riehl 07 Oct '22

07 Oct '22

Haoyu Zhao will present his General Exam, "Coresets for Vertical Federated Learning" on Tuesday, October 11, 2022 at at 1:30 PM in via Zoom. Zoom link: [ https://princeton.zoom.us/j/3247993054 | https://princeton.zoom.us/j/3247993054 ] Committee Members: Sanjeev Arora (advisor), Chi Jin, Elad Hazan Abstract: Vertical federated learning (VFL), where data features are stored in multiple parties distributively, is an important area in machine learning. However, the communication complexity for VFL is typically very high. In this paper, we propose a unified framework by constructing \emph{coresets} in a distributed fashion for communication-efficient VFL. We study two important learning tasks in the VFL setting: regularized linear regression and $k$-means clustering, and apply our coreset framework to both problems. We theoretically show that using coresets can drastically alleviate the communication complexity, while nearly maintain the solution quality. Numerical experiments are conducted to corroborate our theoretical findings. Reading List: [ https://docs.google.com/document/d/1lNANJqOijCA85TNVJ8p95BFrsnVVuP_EOth6T3A… | https://docs.google.com/document/d/1lNANJqOijCA85TNVJ8p95BFrsnVVuP_EOth6T3A… ] Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so. Louis Riehl Graduate Administrator Computer Science Department, CS213 Princeton University (609) 258-8014

1 0