- talks - lists.cs.princeton.edu

CSML/CS/PSY Seminar: Brenden Lake, TODAY at 12:30pm
by Emily C. Lawrence 27 Feb '24

27 Feb '24

Departments of Psychology, Computer Science, and CSML Speaker: Brenden Lake, New York University Title: Towards more human-like learning in machines: Bridging the data and generalization gaps Day: Tuesday, February 27 Place: Computer Science Building Room 105 Time: 12:30-1:30 PM Lunch available from12:15 with RSVP to csml(a)princeton.edu Host: Tom Griffiths, Henry R. Luce Professor of Information Technology, Consciousness and Culture Event page: https://csml.princeton.edu/events/towards-more-human-learning-machines-brid… Webinar Registration: [ https://princeton.zoom.us/webinar/register/WN_aUfLfVQFSIqV2RDSYu4big | https://princeton.zoom.us/webinar/register/WN_aUfLfVQFSIqV2RDSYu4big ] Abstract: There is an enormous data gap between how AI systems and children learn: The best LLMs now learn language from text with a word count in the trillions, whereas it would take a child roughly 100K years to reach those numbers through speech (Frank, 2023, "Bridging the data gap"). There is also a clear generalization gap: whereas machines struggle with systematic generalization, children can excel. For instance, once a child learns how to "skip," they immediately know how to "skip twice" or "skip around the room with their hands up" due to their compositional skills. In this talk, I'll describe two case studies in addressing these gaps. 1) The data gap: We train deep neural networks from scratch (using DINO, CLIP, etc.), not on large-scale data from the web, but through the eyes and ears of a single child. Using head-mounted video recordings from a child as training data (<200 hours of video slices over 26 months), we show how deep neural networks can perform challenging visual tasks, acquire many word-referent mappings, generalize to novel visual referents, and achieve multi-modal alignment. Our results demonstrate how today's AI models are capable of learning key aspects of children's early knowledge from realistic input. 2) The generalization gap: Can neural networks capture human-like systematic generalization? We address a 35-year-old debate catalyzed by Fodor and Pylyshyn's classic article, which argued that standard neural networks are not viable models of the mind because they lack systematic compositionality -- the algebraic ability to understand and produce novel combinations from known components. We'll show how neural networks can achieve human-like systematic generalization when trained through meta-learning for compositionality (MLC), a new method for optimizing the compositional skills of neural networks through practice. With MLC, neural networks can match human performance and solve several machine learning benchmarks. Given these findings, we'll discuss the paths forward for building machines that learn, generalize, and interact in more human-like ways based on more natural input. For related articles visit: https://csml.princeton.edu/events/towards-more-human-learning-machines-brid… BIO: Brenden M. Lake is an Assistant Professor of Data Science and Psychology at New York University. He received his M.S. and B.S. in Symbolic Systems from Stanford University in 2009, and his Ph.D. in Cognitive Science from MIT in 2014. He was a postdoctoral Data Science Fellow at NYU from 2014-2017. Brenden is a recipient of the Robert J. Glushko Prize for Outstanding Doctoral Dissertation in Cognitive Science and the MIT Technology Review 35 Innovators Under 35. His research was also selected by Scientific American as one of the 10 most important advances of 2016. Brenden's research focuses on computational problems that are easier for people than they are for machines, such as learning new concepts from just a few examples, learning by asking questions, learning by generating new goals, and learning by producing novel combinations of known components.

1 0

Howard Yen will present his MSE talk "Long-Context Language Modeling with Parallel Context Encoding" at 1pm on March 7th, 2024 in the 1st floor conference room of CSML (26 Prospect Ave)
by Gradinfo 27 Feb '24

27 Feb '24

Howard Yen will present his MSE talk "Long-Context Language Modeling with Parallel Context Encoding" at 1pm on March 7th, 2024 in the 1st floor conference room of CSML (26 Prospect Ave). Advisor: Prof. Danqi Chen; Reader: Karthik Narasimhan Abstract: Extending large language models (LLMs) to process longer inputs is crucial for numerous applications. However, the considerable computational cost of transformers, coupled with limited generalization of positional encoding, restricts the size of their context window. We introduce Context Expansion with Parallel Encoding (CEPE), a framework that can be applied to any existing decoder-only LLMs to extend their context window. CEPE adopts a small encoder to process long inputs chunk by chunk and enables the frozen decoder to leverage additional contexts via cross-attention. CEPE is efficient, generalizable, and versatile: trained with 8K-token documents, CEPE extends the context window of LLAMA-2 to 128K tokens, offering 10x the throughput with only 1/6 of the memory. CEPE yields strong performance on language modeling and in-context learning. CEPE also excels in retrieval-augmented applications, while existing long-context models degenerate with retrieved contexts. We further introduce a CEPE variant that can extend the context window of instruction-tuned models with only unlabeled data, and showcase its effectiveness on LLAMA-2-CHAT, leading to a strong instruction-following model that can leverage very long context on downstream tasks. CS Grad Calendar: [ https://calendar.google.com/calendar/event?action=TEMPLATE&tmeid=MWhxOGEybz… | https://calendar.google.com/calendar/event?action=TEMPLATE&tmeid=MWhxOGEybz… ]

1 0

Princeton Robotics Seminar: Caitlin Mueller, Friday Feb 23
by Emily C. Lawrence 20 Feb '24

20 Feb '24

Speaker: [ http://digitalstructures.mit.edu/ | Caitlin Mueller ] , MIT Date: Friday, February 23, 2024 Time: 11am ET Location: Computer Science 105 Event page: [ https://robo.princeton.edu/seminar | https://robo.princeton.edu/seminar ] Title: Towards Robotic Construction of Sustainable Structures Abstract: Within the climate crisis, architecture and the built environment play an outsized role, both in contributions to current emissions and projections for the future. Standard design and construction practices are often wasteful, expensive, and exploitative, undermining a mission to create spaces of dignity, comfort, and delight. Within this context, this talk will present an alternative approach, focused on promoting design and construction methods that produce high-quality, low-carbon, and inexpensive outcomes, empowered by emerging advances in computational design and construction robotics. In addition to general methods, the talk will present a range of recent projects, including robotic planning and assembly of complex yet highly efficient truss structures, robotics-enabled fabrication of low-cost, low-carbon earthen and concrete structures, and algorithmic design and fabrication approaches for unconventional and circular material use. Bio: Caitlin Mueller is an Associate Professor at MIT's Department of Architecture and Department of Civil and Environmental Engineering, in the Building Technology Program, where she leads the Digital Structures research group. She works at the creative interface of architecture, structural engineering, and computation, and focuses on new computational design and digital fabrication methods for innovative, high-performance buildings and structures that empower a more sustainable and equitable future. Mueller holds three degrees from MIT in Architecture, Computation, and Building Technology, and one from Stanford in Structural Engineering. Her research is funded by federal agencies and industry partners, including the National Science Foundation, FEMA, the MIT Tata Center, the Dar Group, Holcim, Robert McNeel & Associates, and Altair Engineering. Mueller has won best paper awards from the International Association of Shell and Spatial Structures, the Symposium on Geometry Processing, and the Journal of Mechanical Design, and was awarded the ACADIA Innovative Research Award of Excellence by the Association for Computer Aided Design in Architecture in 2021 and the Diversity Achievement Award from the Association of Collegiate Schools of Architecture in 2022.

1 0

CS Distinguished Colloquium Speaker John Jumper: Monday, September 25 at 4:30
by Emily C. Lawrence 12 Feb '24

12 Feb '24

Speaker: John Jumper, DeepMind Date: Monday, September 25 Time: 4:30pm to 5:30pm Location: Friend Center 101 Host: Ellen Zhong Event page: [ https://www.cs.princeton.edu/events/26500 | https://www.cs.princeton.edu/events/26500 ] Title: Highly accurate protein structure prediction with deep learning Abstract: Our work on deep learning for biology, specifically the AlphaFold system, has demonstrated that neural networks are capable of highly accurate modeling of both protein structure and protein-protein interactions. In particular, the system shows a remarkable ability to extract chemical and evolutionary principles from experimental structural data. This computational tool has repeatedly shown the ability to not only predict accurate structures for novel sequences and novel folds but also to do unexpected tasks such as selecting stable protein designs or detecting protein disorder. In this lecture, I will discuss the context of this breakthrough in the machine learning principles, the diverse data and rigorous evaluation environment that enabled it to occur, and the many innovative ways in which the community is using these tools to do new types of science. I will also reflect on some surprising limitations -- insensitivity to mutations and the lack of context about the chemical environment of the proteins -- and how this may be traced back to the essential features of the training process. Finally, I will conclude with a discussion of some ideas on the future of machine learning in structure biology and how the experimental and computational communities can think about organizing their research and data to enable many more such breakthroughs in the future. Bio: John Jumper received his PhD in Chemistry from the University of Chicago, where he developed machine learning methods to simulate protein dynamics. Prior to that, he worked at D.E. Shaw Research on molecular dynamics simulations of protein dynamics and supercooled liquids. He also holds an MPhil in Physics from the University of Cambridge and a B.S. in Physics and Mathematics from Vanderbilt University. At DeepMind, John is leading the development of new methods to apply machine learning to protein biology.

1 13

ECE SEMINAR: Sara Fridovich-Keil, Wed. Feb 14 at 4:30pm
by Emily C. Lawrence 12 Feb '24

12 Feb '24

ECE SEMINAR Speaker: Sara Fridovich-Keil, Stanford University Title: White-Box Computational Imaging: Measurements to Images to Insights Date: Wednesday, February 14, 2024 Time: 4:30 PM Location: B205 Engineering Quadrangle Hosts: H. Vincent Poor and Sanjeev Kulkarni Abstract: Computation and machine learning hold tremendous potential to improve the quality and capabilities of imaging methods used across science, medicine, engineering, and art. Despite their impressive performance on benchmark datasets, however, deep learning methods are known to behave unpredictably on some real-world data, which limits their trusted adoption in safety-critical domains. Accordingly, in this talk I will describe white-box, interpretable methods for photorealistic volumetric reconstruction that match or exceed the performance of black-box neural alternatives. I will also present recent theoretical results that guarantee correct and efficient reconstruction using our white-box approach in nonlinear computed tomography. Bio: Sara Fridovich-Keil is a postdoctoral fellow at Stanford University, where she works with Mert Pilanci and Gordon Wetzstein on foundations and applications of machine learning and signal processing in computational imaging. She is currently supported by an NSF Mathematical Sciences Postdoctoral Research Fellowship. Sara received her PhD in electrical engineering and computer sciences in May 2023 from UC Berkeley, where she was advised by Ben Recht and supported by an NSF GRFP fellowship. Sara received her BSE in electrical engineering from Princeton University in 2018, where she was advised by Peter Ramadge and supported, in part, by a Barry Goldwater Scholarship.

1 0

Princeton Robotics Seminar: Elad Hazan, Friday Feb 9
by Emily C. Lawrence 06 Feb '24

06 Feb '24

Speaker: [ https://www.ehazan.com/ | Elad Hazan ] , Princeton Date: Friday, February 9, 2024 Time: 11am ET Location: Computer Science 105 Event page: [ https://robo.princeton.edu/seminar | https://robo.princeton.edu/seminar ] Title: The theory of online control and its application to robotics Abstract: In this talk we will discuss an emerging paradigm in differentiable reinforcement learning called “online nonstochastic control”. The new approach applies techniques from online convex optimization and convex relaxations to obtain new methods with provable guarantees for classical settings in optimal and robust control. Time permitting we will discuss recent extensions to nonlinear adaptive control and iterative planning, as well as model free reinforcement learning. This theory was, and continues to be, developed here in Princeton with numerous collaborators, including Naman Agarwal, Brian Bullins, Karan Singh, Max Simchowitz, Xinyi Chen, Ani Majumdar, Sham Kakade, Udaya Ghai, Edgar Minasyan, Paula Gradu, and many others. Bio: Elad Hazan is a professor of computer science at Princeton University. His research focuses on the design and analysis of algorithms for basic problems in machine learning and optimization. Amongst his contributions are the co-invention of the AdaGrad algorithm for deep learning, and the first sublinear-time algorithms for convex optimization. He is the recipient of the Bell Labs prize, the IBM Goldberg best paper award twice, in 2012 and 2008, a European Research Council grant, a Marie Curie fellowship and twice the Google Research Award. He served on the steering committee of the Association for Computational Learning and has been program chair for COLT 2015. In 2017 he co-founded In8 inc. focusing on efficient optimization and control, acquired by Google in 2018. He is the co-founder and director of Google AI Princeton.

1 0

MAE Seminar Series: Cynthia Sung, Friday 2/2
by Emily C. Lawrence 02 Feb '24

02 Feb '24

Speaker: [ https://sung.seas.upenn.edu/people/sung/ | Cynthia Sung ] , UPenn Date: Friday, February 2nd, 2024 Time: 12:30 PM ET Seminar: [ https://mae.princeton.edu/about-mae/events/computational-design-origami-and… | MAE Seminar Series ] Location: Bowen Hall Room 222 Title: Computational Design of Origami and Compliant Robots Abstract: Soft and compliant robots provide new opportunities for machines that are flexible, adaptable, safe, and robust. Origami-inspired engineering enables custom robots to be designed and fabricated within days, or even hours. These robots are capable of executing a variety of shape-changing and dynamical tasks by taking advantage of their folded shape and programmable mechanics. In this talk, I will show how the kinematics and compliance of a thin-shell mechanism can be designed algorithmically. I will also discuss how we can leverage these designs for better performance and simpler control, and how these approaches provide robots with capabilities such as dynamical hopping, swimming, and flight. Bio: Cynthia Sung is the Gabel Family Term Assistant Professor in the Department of Mechanical Engineering and Applied Mechanics (MEAM) and a member of the General Robotics, Automation, Sensing & Perception (GRASP) lab at the University of Pennsylvania. She received a Ph.D. in Electrical Engineering and Computer Science from MIT in 2016 and a B.S. in Mechanical Engineering from Rice University in 2011. Her research interests are computational methods for design automation of robotic systems, with a particular focus on origami-inspired and compliant robots. She is the recipient of a 2023 ONR Young Investigator award, a 2020 Johnson & Johnson Women in STEM2D Scholars Award, and a 2019 NSF CAREER award.

1 1

ORFE Distinguished Lecture Series: Yao Xie, Feb 6 at 4:30pm
by Emily C. Lawrence 02 Feb '24

02 Feb '24

=== 2/6/24 ORFE Distinguished Lecture Series=== DATE: Tuesday, February 6, 2024 TIME: 4:30pm LOCATION: Sherrerd 101 SPEAKER: Yao Xie, Georgia Tech TITLE: Generative models for statistical inference Abstract: We consider the problem of learning a continuous probability density function from data, a fundamental problem in statistics known as density estimation. It also arises in distributionally robust optimization (DRO), where the goal is to find the worst-case distribution to represent scenario departure from observations. Such a problem is known to be hard in high dimensions and incurs a significant computational challenge. In this talk, I will present a new approach to tackle these challenges, leveraging recent advances in neural-networks-based generative models, a type of machine learning model that aims to generate new samples following the underlying distributions of the observations. We develop a new flow-based generative model with guarantees, inspired by the celebrated Jordan-Kinderleherer-Otto (JKO) scheme, to represent the data distribution using a composition of a sequence of optimal transport maps applying to a source distribution (such as Gaussian). Our method can greatly reduce computational costs when achieving competitive performance over existing generative models. The connection of our JKO-flow method with proximal gradient descent in the Wasserstein-2 space enables us to prove a density learning guarantee with an exponential convergence rate. Besides density estimation, we also demonstrate that the JKO-flow generative model can be used in various applications, including adversarial learning, robust hypothesis testing, and data-driven differential privacy. Bio: Yao Xie is the Coca-Cola Foundation Chair, Professor at Georgia Institute of Technology in the H. Milton Stewart School of Industrial and Systems Engineering, and Associate Director of the Machine Learning Center. She received her Ph.D. in Electrical Engineering (minor in Mathematics) from Stanford University in 2012 and was a Research Scientist at Duke University. Her research lies at the intersection of statistics, machine learning, and optimization in providing theoretical guarantees and developing computationally efficient and statistically powerful methods for problems motivated by real-world applications. She received the National Science Foundation (NSF) CAREER Award in 2017, the INFORMS Wagner Prize Finalist in 2021, and the INFORMS Gaver Early Career Award for Excellence in Operations Research in 2022. She is currently an Associate Editor for IEEE Transactions on Information Theory, Journal of the American Statistical Association-Theory and Methods, Operations Research, Sequential Analysis: Design Methods and Applications, INFORMS Journal on Data Science, and an Area Chair of NeurIPS, ICML, and ICLR.

1 0

Uthsav Chitra will present his FPO "Algorithms for understanding the spatial and network organization of biological systems" on Friday, March 1, 2024 at 10:00 AM in COS 302 and Zoom.
by CS Grad Department 01 Feb '24

01 Feb '24

Uthsav Chitra will present his FPO "Algorithms for understanding the spatial and network organization of biological systems" on Friday, March 1, 2024 at 10:00 AM in COS 302 and Zoom. Location: Zoom link: https://princeton.zoom.us/j/99220301104 The members of Uthsav’s committee are as follows: Examiners: Ben Raphael (Adviser), Bernard Chazelle, Yuri Pritykin Readers: Ellen Zhong, Fei Chen (Harvard) Everyone is invited to attend his talk. Abstract follows below: Biological systems are characterized by their spatial organization and network interactions at a hierarchy of scales. For example, the spatial arrangement of different cells in a tissue underlies fundamental multicellular processes such as tissue differentiation and disease response, while interactions between genes/proteins comprise the biological pathways that regulate cellular state and function. Recent developments in high-throughput sequencing have enabled the systematic analysis of spatial and network processes in many complex biological systems including the brain and tumor microenvironment. However, such analyses are challenged by high levels of sparsity and/or noise in high-throughput sequencing datasets—underscoring the need for principled and rigorous computational methods for biological data analysis. In this dissertation, we present a collection of mathematical frameworks and machine learning algorithms for modeling the spatial and network organization of biological systems. First, we derive a model of discrete and continuous spatial variation in gene expression. We present two algorithms, Belayer and GASTON, which learn the parameters of this model using complex analysis and interpretable deep learning, respectively. Second, we present a mathematical framework for the identification of altered subnetworks, or subnetworks of a biological interaction network containing genes/proteins that are differentially expressed, highly mutated, or otherwise aberrant compared to other genes/proteins. We prove that many existing algorithms are statistically biased, resolving the open question of why these algorithms often identify very large subnetworks that are difficult to interpret. We derive two altered subnetwork identification algorithms, NetMix and NetMix2, which we show are asymptotically unbiased and outperform existing approaches in practice. Finally, we present two frameworks for learning and modeling higher-order interactions. We first derive a statistical framework for learning higher-order genetic interactions from experimental fitness data, unifying decades of existing work in the genetics literature. Then, we derive a theoretical framework for modeling random walks on hypergraphs that provably utilizes higher-order interactions in data, in contrast to many existing hypergraph methods which only utilize pairwise interactions. Taken together, the approaches in this dissertation provide a theoretical and practical foundation for overcoming the computational challenges of modeling complex biological systems.

1 0

ORFE Distinguished Lecture Series: Benjamin Recht tomorrow at 4:30pm
by Emily C. Lawrence 29 Jan '24

29 Jan '24

=== 1/30/24 ORFE Distinguished Lecture Series=== DATE: Tuesday, January 30, 2024 TIME: 4:30pm LOCATION: Sherrerd 101 SPEAKER: Benjamin Recht, UC Berkeley TITLE: Statistics When n Equals 1 Abstract: From large trials of treatments and diseases, 21st-century medicine embraces inferences about people from studies of populations. But such population inferences tell us little about what to do with any particular person. In this talk, I will first describe some of the drawbacks of applying population statistics to decision-making about individuals. As an alternative, I will outline how we might design treatments and interventions to help those individuals directly. I will present a series of parallel projects that link ideas from systems, optimization, control, and experiment design to draw inferences and inform such individualized decision making. Bio: Benjamin Recht is a Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. His research has focused on applying mathematical optimization and statistics to problems in data analysis and machine learning. He is currently studying histories, methods, and theories of scientific validity and experimental design.

1 0