- talks - lists.cs.princeton.edu

Physics Seminar: David Pfau, Friday, April 5 at 4:30pm
by Emily C. Lawrence 28 Mar '24

28 Mar '24

Physics Seminar Speaker: David Pfau, Google DeepMind Date: Friday, April 5 Time: 4:30pm Location: Jadwin Hall, room A10 Event page: [ https://ml.physics.princeton.edu/ | https://ml.physics.princeton.edu/ ] Title: Computing Quantum Excited States with Deep Neural Networks Abstract: Excited states of quantum systems are relevant for photochemistry, quantum dots, semiconductors and more, but remain extremely challenging to calculate by conventional computational methods. In recent years tools from machine learning have found useful application in computational quantum mechanics, especially in making ground state calculations much more accurate. In this talk I will present a new algorithm for estimating the lowest excited states of a quantum system which works extremely well with deep neural networks. The method has no free parameters and requires no explicit orthogonalization of the different states, instead transforming the problem of finding excited states of a given system into that of finding the ground state of an expanded system. Expected values of arbitrary observables can be calculated including off-diagonal expectations between different states such as the transition dipole moment. We show that by combining this method with the FermiNet and Psiformer Ansatze we can accurately recover vertical excitation energies and oscillator strengths on molecules as large as benzene. Beyond the examples on molecules presented here we expect this technique will be of great interest for applications to atomic, nuclear, and condensed matter physics. Bio: David Pfau is a staff research scientist at Google DeepMind and a visiting professor at Imperial College London in the Department of Physics, where he supervises work on applications of deep learning to computational quantum mechanics. His research interests span artificial intelligence, machine learning and scientific computing. Prior to joining DeepMind, he was a PhD student at the Center for Theoretical Neuroscience at Columbia, where I worked on algorithms for analyzing and understanding high-dimensional data from neural recordings with Liam Paninski and nonparametric Bayesian methods for predicting time series data with Frank Wood. He also had a stint as a research assistant in the group of Mike DeWeese at UC Berkeley, jointly between Physics and the Redwood Center for Theoretical Neuroscience. His current research interests include applications of machine learning to computational physics and connections between differential geometry and unsupervised learning.

1 0

ECE Seminar: Gil Zussman, tomorrow at 4:30pm
by Emily C. Lawrence 27 Mar '24

27 Mar '24

ECE Seminar Speaker: Gil Zussman, Columbia University Day: March 28, 2024 Time: 4:30pm Location: B205, EQuad Hosts: Yasaman Ghasempour and Kaushik Sengupta Event Link [ https://ece.princeton.edu/events/cosmos-testbed-%E2%80%93-platform-advanced… | https://ece.princeton.edu/events/cosmos-testbed-%E2%80%93-platform-advanced… ] Title: The COSMOS Testbed – a Platform for Advanced Wireless, Edge Cloud, Optical, Smart Streetscapes, and International Experimentation Abstract: This talk will provide an overview of the COSMOS testbed (https://cosmos-lab.org), that is being deployed as part of the NSF Platforms for Advanced Wireless Research (PAWR) program, and briefly review various ongoing experiments in the areas of wireless, optical, edge cloud, and smart cities. COSMOS (Cloud-Enhanced Open Software-Defined Mobile-Wireless Testbed for City-Scale Deployment) is being deployed in West Harlem (New York City). It targets the technology "sweet spot" of ultra-high bandwidth and ultra-low latency, a capability that will enable a broad new class of applications including augmented/virtual reality and cloud-based autonomous vehicles. Realization of such high bandwidth/low latency wireless applications involves research not only on radio links, but also on the system as a whole including algorithmic aspects related to spectrum use, networking, and edge computing. We will present an overview of COSMOS' key enabling technologies, which include mmWave radios, software-defined radios, optical/SDN x-haul network, and edge cloud. We will then discuss the deployment and outreach efforts as well as the international component (COSMOS Interconnecting Continents - COSM-IC). Finally, we will describe various experiments that have been conducted in the testbed, including in the areas of edge cloud, mmWave wireless, full-duplex wireless, smart streetspaces, and optical communications/sensing. The COSMOS testbed design and deployment is joint work with the COSMOS team (https://cosmos-lab.org). Bio: Gil Zussman received the Ph.D. degree in Electrical Engineering from the Technion in 2004. Between 2004 and 2007 he was a Postdoctoral Associate at MIT. Since 2007 he has been with Columbia University where he is a Professor of Electrical Engineering and Computer Science (affiliated faculty), and member of Data Science Institute. His research interests are in the area of networking, and in particular in the areas of wireless, mobile, and resilient networks. Gil is an IEEE Fellow and received two Marie Curie fellowships, the Fulbright Fellowship, the DTRA Young Investigator Award, and the NSF CAREER Award. He is a co-recipient of seven best paper awards, including the ACM SIGMETRICS’06 Best Paper Award, the 2011 IEEE Communications Society Award for Advances in Communication, and the ACM CoNEXT’16 Best Paper Award.

1 0

TOMORROW 3/26/2024: ECE SEMINAR Yuandong Tian, Meta AI
by Emily C. Lawrence 25 Mar '24

25 Mar '24

ECE SEMINAR Speaker: Yuandong Tian, Meta AI Title: Towards Efficient, Effective and Explainable AI-guided Decision Making Date: Tuesday, March 26, 2024 Time: 4:30 PM Location: B205 Engineering Quadrangle Host: Jason Lee Abstract: Decision-making is ubiquitous in our everyday life and plays an essential role throughout the entire human history. With the emergence of strong or even superhuman Artificial Intelligence (AI), AI-guided decision making becomes a viable choice in situations that require fast yet precise decisions with overwhelming, fast-changing or intricate input, and limited prior experience and resources. Such a high bar demands our AI-guided decision making to be more effective, efficient and explainable. In this talk, I will cover our work ranging from superhuman Go bot to strategy finding in various industrial-level applications such as Antenna Design and Network Planning, from standard RL and optimization formulation to effective representations beyond pre-defined state/action spaces, and from blackbox to explainable improvement for LLMs training and inference. Bio: Yuandong Tian is a Research Scientist and Senior Manager in Meta AI Research (FAIR), working on more efficient training and inference of Large Language Models (LLMs), understanding of LLM, optimization and reinforcement learning. He has been the main mentor of recent works StreamingLLM and GaLore that improves the training and inference of LLM, and the project lead for OpenGo that beats professional players with a single GPU during inference. He is the first-author recipient of 2021 ICML Outstanding Paper Honorable Mentions and 2013 ICCV Marr Prize Honorable Mentions, and also received the 2022 CGO Distinguished Paper Award. Prior to that, he worked in Google Self-driving Car team in 2013-2014 and received a Ph.D in Robotics Institute, Carnegie Mellon University in 2013. He has been appointed as area chairs for NeurIPS, ICML, AAAI, CVPR and AIStats.

1 0

Princeton AI Alignment and Safety Seminar (PASS): TOMORROW at 2pm
by Emily C. Lawrence 25 Mar '24

25 Mar '24

Princeton AI Alignment and Safety Seminar (PASS) YouTube Series: [ https://pli.princeton.edu/events/2024/ai-preparedness | AI Preparedness ] [ https://madry.mit.edu/ | Aleksander Mądry ] Tuesday, March 26 2:00 - 3:00 pm [ https://www.youtube.com/watch?v=pe3XF0Qhx1M | View the livestream ] LINK FOR AUDIENCE TO SUBMIT QUESTIONS: [ http://tinyurl.com/pass-question | tinyurl.com/pass-question ] Abstract: The dramatic increase in the capabilities of our AI systems gives rise to major opportunities but also to risks. How can we prepare to fully take advantage of the former and mitigate the latter? In this talk, I will present my perspective on this challenge and discuss some of the relevant work of OpenAI’s Preparedness team. Bio: [ https://madry.mit.edu/ | Aleksander Mądry ] is the Head of Preparedness at OpenAI. The Preparedness effort is tasked with tracking, evaluating, forecasting, and helping protect against catastrophic risks related to frontier AI models. Aleksander is also a Professor of Computing at MIT (currently on leave), where he has been serving as the Director of the MIT Center for Deployable Machine Learning and a Faculty Co-Lead of the MIT AI Policy Forum. Stay informed and receive seminar reminders by joining our mailing list: [ https://tinyurl.com/pass-mailing | https://tinyurl.com/pass-mailing ] Organized by: [ https://pli.princeton.edu/ | Princeton Language and Intelligence ]

1 0

Kathy Chen will present her FPO "Decoding the sequence basis of gene regulation" on Tuesday, April 9, 2024 at 10:00 AM in Icahn 280 and Zoom.
by Grad Info 22 Mar '24

22 Mar '24

Kathy Chen will present her FPO "Decoding the sequence basis of gene regulation" on Tuesday, April 9, 2024 at 10:00 AM in Icahn 280 and Zoom. Location: Zoom link: https://princeton.zoom.us/j/95565860844?pwd=LzNkcHZ6bnVackxZRnZJSitXdW9NUT09 The members of Kathy's committee are as follows: Examiners: Olga Troyanskaya (Adviser), Mona Singh, Kai Li Readers: Ryan Adams, Jian Zhou (UT Southwestern) Everyone is invited to attend her talk. Abstract follows below: Deciphering the regulatory code of gene expression is a critical challenge in human genetics, instrumental to unlocking the potential of personalized medicine. Modern experimental technologies have resulted in an abundance of high-dimensional genome-wide data, revealing the complex system of epigenetic interactions encoded in the genome. The development of computational approaches which can leverage this vast data to model chromatin interactions globally offer a new understanding of how genomic sequences specify regulatory functions. Specifically, sequence-based deep learning models have become the de facto standard for learning the functional properties encoded in DNA sequences based on large sequencing datasets. These models are powerful tools for interpreting molecular and phenotypic effects, capable of predicting the impact of any noncoding variant in the human genome, even rare or never-before-observed variants, and systematically characterizing their consequences beyond what is tractable from experiments and quantitative genetics alone. In this thesis, we present two deep learning-based sequence models, which predict different epigenetic properties of the genome that contribute to transcriptional regulation. First, Sei is a framework for integrating human genetics data with sequence information to discover the regulatory basis of traits and diseases. Sei learns a vocabulary of regulatory activities, called sequence classes, using a model that predicts 21,907 chromatin profiles across >1,300 cell lines and tissues. Sequence classes provide a global classification and quantification of sequences and variants based on diverse regulatory activities, such as cell type-specific enhancers. Next, we developed a model Hedgehog, which enables the quantification of variation on methylation sites. Hedgehog predicts 296 continuous-valued methylation profiles across a range of cell types and tissues. Hedgehog is complementary to Sei and reveals new insights into the relationship between DNA methylation and other epigenetic modifications. Finally, we show how deep learning-based methods can be applied to elucidate the regulatory basis of human health and disease. Specifically, we use Sei to study the contribution of noncoding mutations in cancer. Collectively, we demonstrate novel frameworks for modeling the sequence dependencies of the epigenome and the capability of such approaches to delineate the regulatory mechanisms underlying complex diseases.

1 0

DeCenter Seminar: Eric Budish, Wed. March 27 at 4:30pm
by Emily C. Lawrence 21 Mar '24

21 Mar '24

The DeCenter is delighted to extend an invitation to a seminar featuring Eric Budish on March 27th at 4:30pm. The seminar will be held in the Friend Center Convocation Room, followed by a light reception. Talk Title : [ https://decenter.princeton.edu/events/decenter-seminar-4/ | Trust at Scale: The Economic Limits of Cryptocurrencies and Blockchains ] Abstract : Satoshi Nakamoto (2008) invented a new kind of economic system that does not need the support of government or rule of law. Trust and security instead arise from a combination of cryptography and economic incentives, all in a completely anonymous and decentralized system. This paper uses a simple three-equation argument to show that this new form of trust, while ingenious, is deeply economically limited. A zero-profits condition on the providers of blockchain trust and an incentive-compatibility condition on the system’s security against attack together imply an equilibrium constraint that the recurring, “flow” cost of blockchain trust must be large relative to the one-off, “stock”-like benefit of attacking the system. Moreover, this equilibrium cost of blockchain trust scales linearly with the value secured — which means that if cryptocurrencies and blockchains were to become more economically useful than they have been to date, then their costs would have to grow to absurd levels. There is a way out of the flow-stock argument, but it is premised on the risk of economic collapse, which is itself a serious problem – pick your poison. The key contrast between Nakamoto trust and traditional trust grounded in rule of law, and complementary sources such as reputations, relationships and collateral, is the economies of scale that arise from credible deterrence as in Hayek (1960) and Becker (1968): Society or a firm pays a fixed cost to enjoy trust over a large quantity of economic activity at low or zero marginal cost. Bio : Eric Budish is the Paul G. McDermott Professor of Economics and Entrepreneurship at the University of Chicago, Booth School of Business. He is also a Research Associate at the National Bureau of Economic Research, Co-Director of the Clark Center for Global Markets at Chicago Booth, and the Co-Director of the Chicago Booth Economics PhD Program. Budish is a leading researcher in the academic field of market design. He is best known for his market design inventions for financial exchanges and matching markets. He has also conducted influential research on market design theory, blockchains and cryptocurrencies, patents and innovation, event ticket markets, and various aspects of Covid-19 economic policy. Budish teaches an MBA class on competitive strategy and PhD classes on market design and the research and writing process. He received his PhD in Business Economics from Harvard University, his MPhil in Economics from Oxford (Nuffield College), and his BA in Economics and Philosophy from Amherst College. Budish gives frequent keynotes on his research and has received numerous academic awards including the Marshall Scholarship, the Sloan Fellowship, giving the joint AEA/AFA luncheon address, the Arrow award, and the AQR insight award.”

1 0

Princeton AI Alignment and Safety Seminar (PASS) with Audience Question Link
by Emily C. Lawrence 19 Mar '24

19 Mar '24

Princeton AI Alignment and Safety Seminar (PASS) Catastrophic misalignment of large language models [ https://paulfchristiano.com/ | Paul Christiano, Alignment Research Center ] Tuesday, March 19 2:00 - 3:00 pm [ https://bit.ly/3IHlz4h | View the livestream ] Link for Audience to Submit Questions: [ http://tinyurl.com/pass-question | tinyurl.com/pass-question ] LINK FOR AUDIENCE TO SUBMIT QUESTIONS: [ http://tinyurl.com/pass-question | tinyurl.com/pass-question ] Abstract: I’ll discuss two possible paths by which AI systems could be so misaligned that they attempt to deceive and disempower their human operators. I’ll review the current state of evidence about these risks, what we might hope to learn over the next few years, and how we could become confident that the risk is adequately managed. Bio: I run the [ http://alignmentresearchcenter.org/ | Alignment Research Center ] . I previously ran the language model alignment team at [ https://openai.com/ | OpenAI ] , and before that received my PhD from the [ http://theory.cs.berkeley.edu/ | theory group ] at UC Berkeley. You may be interested in my [ https://ai-alignment.com/ | writing about alignment ] , my [ http://sideways-view.com/ | blog ] , my [ https://scholar.google.com/citations?hl=en&user=B7oP0bIAAAAJ&view_op=list_w… | academic publications ] , or [ https://paulfchristiano.com/fun-and-games/ | fun and games ] . I am an advisor and board member at [ https://metr.org/ | METR ] , an external advisor to the [ https://www.gov.uk/government/publications/ai-safety-institute-overview/int… | UK AI Safety Institute ] , and a trustee of [ https://www.anthropic.com/index/anthropics-responsible-scaling-policy | Anthropic’s Long-Term Benefit Trust ] . Stay informed and receive seminar reminders by joining our mailing list: [ https://tinyurl.com/pass-mailing | https://tinyurl.com/pass-mailing ] Organized by: [ https://pli.princeton.edu/ | Princeton Language and Intelligence ]

1 0

Princeton Robotics Seminar: Ye Zhao, Friday March 22
by Emily C. Lawrence 19 Mar '24

19 Mar '24

Speaker: [ https://lab-idar.gatech.edu/ | Ye Zhao ] , GA Tech Date: Friday, March 22nd, 2024 Time: 11am ET Location: Computer Science 105 Event page: [ https://robo.princeton.edu/seminar | https://robo.princeton.edu/seminar ] PhD students and postdocs can [ https://docs.google.com/forms/d/e/1FAIpQLSdJT4YAF7or7kl5Ht7Op-a0syql4iRy_e1… | signup to join Ye for lunch here ] . There will also be a Robotics Social at 4:00 PM in the F-Wing Cafe Area - all are welcome to attend! Title: Unlocking Agility, Safety, and Resilience for Legged Navigation: Addressing Real-world Challenges in Uncertain Environments Abstract: While legged robots have made remarkable progress in dynamic balancing and locomotion, there remains substantial room for improvement in terms of safe navigation and decision-making capabilities. One major challenge stems from the difficulty of designing safe, resilient, and real-time planning and decision-making frameworks for these complex legged machines navigating unstructured environments. Symbolic planning and distributed trajectory optimization offer promising yet underexplored solutions. This talk will introduce three perspectives on enhancing safety and resilience in task and motion planning (TAMP) for agile legged navigation. First, we'll discuss hierarchically integrated TAMP for dynamic locomotion in environments susceptible to perturbations, focusing on robust recovery behaviors. Next, we'll cover our recent work on safe and socially acceptable legged navigation planning in environments that are partially observable and crowded with humans. Lastly, we'll delve into distributed contact-aware trajectory optimization methods achieving dynamic consensus for agile locomotion behaviors. Bio: Ye Zhao is an Assistant Professor at The George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology. He received his Ph.D. degree in Mechanical Engineering from The University of Texas at Austin in 2016. After that, he was a Postdoctoral Fellow at Agile Robotics Lab, Harvard University. At Georgia Tech, he leads the Laboratory for Intelligent Decision and Autonomous Robots. His research interest focuses on planning and decision-making algorithms of highly dynamic and contact-rich robots. He received the George W. Woodruff School Faculty Research Award at Georgia Tech in 2023, NSF CAREER Award in 2022, and ONR YIP Award in 2023. He serves as an Associate Editor of T-RO, TMECH, RA-L, and L-CSS. His co-authored work has received multiple paper awards, including the 2021 ICRA Best Automation Paper Award Finalist, the 2023 Best Paper Award at the NeurIPS Workshop on Touch Processing, and the 2016 IEEE-RAS Whole-Body Control Best Paper Award Finalist.

1 0

TODAY 3/18/2024 - ECE SEMINAR Zhijian Liu, MIT
by Emily C. Lawrence 18 Mar '24

18 Mar '24

ECE SEMINAR Speaker: Zhijian Liu, MIT Title: Efficient Deep Learning with Sparsity: Algorithms, Systems, and Applications Date: Monday, March 18, 2024 Time: 4:30 PM Location: B205 Engineering Quadrangle Host: Mengdi Wang Abstract: Machine learning is widely used across a broad spectrum of applications. However, behind its remarkable performance lies an increasing gap between the demand for and supply of computation. On the demand side, the computational costs of machine learning models have surged dramatically, driven by ever-larger input and model sizes. On the supply side, as Moore's Law slows down, hardware no longer delivers increasing performance within the same power budget. In this talk, I will discuss my research efforts to bridge this demand-supply gap through the lens of sparsity. I will begin by discussing my research on input sparsity. First, I will introduce algorithms that systematically eliminate the least important patches/tokens from dense input data, such as images, enabling up to 60% sparsity without any loss in accuracy. Then, I will present the system library that we have developed to effectively translate the theoretical savings from sparsity to practical speedups on hardware. Our system is up to 3 times faster than the leading industry solution from NVIDIA. Following this, I will touch on my research on model sparsity, highlighting a family of automated, hardware-aware model compression frameworks that surpass manual solutions in accuracy and reduce the design process from weeks of human efforts to mere hours of GPU computation. Finally, I will present several examples demonstrating the use of sparsity to accelerate computation-intensive AI applications, such as autonomous driving, language modeling, and high-energy physics. I will conclude this talk with an overview of my ongoing work and my vision towards building more efficient and accessible AI. Bio: Zhijian Liu is a Ph.D. candidate at MIT, advised by Song Han. His research focuses on efficient machine learning. He has developed efficient ML algorithms and provided them with effective system/algorithm support. He has also contributed to accelerating computation-intensive AI applications in computer vision, natural language processing, and scientific discovery. His work has been featured as oral and spotlight presentations at conferences such as NeurIPS, ICLR, and CVPR. He was selected as the recipient of the Qualcomm Innovation Fellowship and the NVIDIA Graduate Fellowship. He was also recognized as a Rising Star in ML and Systems by MLCommons and a Rising Star in Data Science by UChicago and UCSD. Previously, he was the founding research scientist at OmniML, which was acquired by NVIDIA.

1 0

Princeton AI Alignment and Safety Seminar (PASS): Tuesday, March 19 at 2pm
by Emily C. Lawrence 18 Mar '24

18 Mar '24

Princeton AI Alignment and Safety Seminar (PASS) Catastrophic misalignment of large language models [ https://paulfchristiano.com/ | Paul Christiano, Alignment Research Center ] Tuesday, March 19 2:00 - 3:00 pm [ https://bit.ly/3IHlz4h | View the livestream ] Abstract: I’ll discuss two possible paths by which AI systems could be so misaligned that they attempt to deceive and disempower their human operators. I’ll review the current state of evidence about these risks, what we might hope to learn over the next few years, and how we could become confident that the risk is adequately managed. Bio: I run the [ http://alignmentresearchcenter.org/ | Alignment Research Center ] . I previously ran the language model alignment team at [ https://openai.com/ | OpenAI ] , and before that received my PhD from the [ http://theory.cs.berkeley.edu/ | theory group ] at UC Berkeley. You may be interested in my [ https://ai-alignment.com/ | writing about alignment ] , my [ http://sideways-view.com/ | blog ] , my [ https://scholar.google.com/citations?hl=en&user=B7oP0bIAAAAJ&view_op=list_w… | academic publications ] , or [ https://paulfchristiano.com/fun-and-games/ | fun and games ] . I am an advisor and board member at [ https://metr.org/ | METR ] , an external advisor to the [ https://www.gov.uk/government/publications/ai-safety-institute-overview/int… | UK AI Safety Institute ] , and a trustee of [ https://www.anthropic.com/index/anthropics-responsible-scaling-policy | Anthropic’s Long-Term Benefit Trust ] . Stay informed and receive seminar reminders by joining our mailing list: [ https://tinyurl.com/pass-mailing | https://tinyurl.com/pass-mailing ] Organized by: [ https://pli.princeton.edu/ | Princeton Language and Intelligence ]

1 0