- talks - lists.cs.princeton.edu

Mary Hogan will present her FPO "Language Expressiveness Under Extreme Scarcity in Programmable Data Planes" on Thursday, May 9th at 1pm in Friend 125 (and zoom).
by Gradinfo 09 Apr '24

09 Apr '24

Mary Hogan will present her FPO "Language Expressiveness Under Extreme Scarcity in Programmable Data Planes" on Thursday, May 9th at 1pm in Friend 125 (and zoom). [ https://princeton.zoom.us/j/3627976305 | https://princeton.zoom.us/j/3627976305 ] Committee: Jen Rexford (advisor), Maria Apostolaki (examiner), Ravi Netravali (examiner), Dave Walker (reader), Shir Landau Feibish (reader) Title: Language Expressiveness Under Extreme Scarcity in Programmable Data Planes Abstract: Today's networks must run a vast array of sophisticated applications, and the network devices that implement these applications need to operate at high speeds (100+Gbps) and be flexible enough to adapt applications to changing requirements. Programmable network devices have emerged as a way to customize network functionality, while guaranteeing high-speed processing. Writing applications for programmable devices, however, is notoriously difficult. Deploying these applications often requires tedious optimization of their layout, with programmers manually writing, compiling, and testing an implementation, adjusting the design, and repeating. In my research, I aim to simplify the development process with high-level frameworks that allow programmers to define general, parameterized network algorithms and automatically optimize their various parameters. I will first discuss P4All, an extension of an existing programming language that allows programmers to define elastic data structures that stretch automatically to optimally use available resources. These data structures are defined using symbolic primitives (that parameterize the size and shape of the structure) and objective functions (that quantify the value gained or lost as that shape changes). I will then present Parasol, which extends the ideas of P4All by allowing for much more general parameters, whose optimization is tailored to particular network conditions using a representative traffic trace.

1 0

Marcelo Orenes Vera will present his FPO "Navigating Heterogeneity and Scalability in Modern Chip Design" on Friday, May 3rd, 2024 at 11am in CS 105.
by Gradinfo 08 Apr '24

08 Apr '24

Marcelo Orenes Vera will present his FPO "Navigating Heterogeneity and Scalability in Modern Chip Design" on Friday, May 3rd, 2024 at 11am in CS 105. The members of his committee are as follows: Examiners: Margaret Martonosi (adviser), David Wentzlaff, and Aarti Gupta Readers: Kai Li and Jonathan Balkind (University of California Santa Barbara) All are welcome to attend. Please see below for the talk abstract. Computing systems have become ubiquitous in the modern world but their design is far from one-size-fits-all. From battery-powered devices to supercomputers, deployment requirements are a primary driver of heterogeneity in computer design. As modern systems rely on parallelism and specialization to achieve their performance and power goals, new challenges arise. The system's complexity grows with the number of distinct hardware modules, complicating the verification of correct and secure behavior. Moreover, expanding parallelization across more processing units (PUs) increases the pressure on the memory hierarchy and inter-PU network, which results in severe bottlenecks for applications traversing graph-like data structures with indirect memory accesses (IMAs). These challenges call for re-thinking software abstractions and hardware designs to achieve scalable and efficient systems, as well as introducing robust methodologies to ensure their correctness. My dissertation aims to tackle these challenges with three main thrusts. First, to facilitate hardware designers applying formal verification to their modules, this dissertation introduces AutoSVA, a toolflow that generates formal verification testbenches from module interface annotations. Testbenches generated with AutoSVA have uncovered bugs in open-source projects, including a widely used RISC-V CPU. Second, to alleviate IMA latency without increasing verification complexity, this dissertation introduces MAPLE, a network-connected memory-access engine that supports data pipelining and prefetching without requiring PU modifications. As such, off-the-shelf PUs can offload IMAs to MAPLE, and consume data via software-managed queues. Using MAPLE effectively mitigates memory latency, providing 2x speedups over software- and hardware-only prefetching. Third, to further the scalability of graph and sparse workloads, this dissertation co-designs scale-out architectures with a data-centric execution model, Dalorex, where IMAs are split into tasks that only access a confined address range and execute at the PU with dedicated access to that memory range. The parallelization of breadth-first-search on a billion-edge graph across a million PUs results in nearly an order of magnitude faster runtimes than Graph500's top entries. By introducing novel hardware designs, execution models, and verification tools, this dissertation contributes towards addressing the challenges posed by the increasing demand for high-performance, energy-efficient, and cost-effective computing systems.

1 0

Mike He will present his General Exam "Equality Saturation: Term Extraction and an Application to Network Synthesis" on April 16th, 2024 at 10:30am in CS 401 and Zoom.
by Nicki Mahler 08 Apr '24

08 Apr '24

Mike He will present his General Exam "Equality Saturation: Term Extraction and an Application to Network Synthesis" on April 16th, 2024 at 10:30am in CS 401 and Zoom. Zoom link: https://princeton.zoom.us/my/deyuan Committee Members: Aarti Gupta (adviser), Andrew Appel, and Mae Milano Link to Abstract and Reading List: [ https://docs.google.com/document/d/1hiZgxT9Jj0U_V83oK9eTD9siDWR0wdVKXE3BSkn… | https://docs.google.com/document/d/1hiZgxT9Jj0U_V83oK9eTD9siDWR0wdVKXE3BSkn… ] [ https://docs.google.com/document/d/1hiZgxT9Jj0U_V83oK9eTD9siDWR0wdVKXE3BSkn… | Abst ] [ https://docs.google.com/document/d/1hiZgxT9Jj0U_V83oK9eTD9siDWR0wdVKXE3BSkn… | ract ] Equality saturation is a recent technique that mitigates the phase ordering problem in compilers. Instead of performing destructive rewrite rules over the input program, equality saturation memorizes all the equivalent representations compactly in a data structure called e-graph (equality graphs) and executes multiple rewrite rules simultaneously over e-graphs. Designing an efficient algorithm for term extraction from e-graphs is challenging because the candidate space can be exponentially large and candidate terms can be cyclic. We present a Weighted Partial MaxSAT encoding of the extraction problem by identifying cycles in the e-graph and encoding acyclic constraints with Tseitin transformation to avoid extracting cyclic terms. Our evaluation of real-world workload shows a ~3x speed-up in comparison with extraction with the ILP encoding. Next, we present a case study of applying equality saturation to resource synthesis for packet programs. We propose CatsTail, a packet program compilation pipeline that leverages equality saturation to find feasible ALU mappings to reconfigurable switches. We benchmarked CatsTail using real-world switch programs and compared its synthesis performance with a previous work CaT. CatsTail shows comparable stage utilization optimality while being up to two orders of magnitude faster than CaT in resource synthesis for real-world P4 programs. Finally, if time permits, we will talk about an ongoing project of automated invariant synthesis for distributed systems. [ https://docs.google.com/document/d/1hiZgxT9Jj0U_V83oK9eTD9siDWR0wdVKXE3BSkn… | Reading List ] Textbooks Software Foundations, [ https://softwarefoundations.cis.upenn.edu/lf-current/index.html | Vol 1 ] , [ https://softwarefoundations.cis.upenn.edu/plf-current/index.html | Vol 2 ] Chapters 1~11 Logic in Computer Science, Chapters 1, 2, 3.1-3.5, 4, 6.1 Papers Equality Saturation and its Applications 1. [ https://dl.acm.org/doi/10.1145/3434304 | egg: Fast and extensible equality saturation ] (POPL’21) 2. [ https://arxiv.org/abs/2105.09377 | Pure Tensor Program Rewriting via Access Patterns ] (MAPS’21) 3. [ https://dl.acm.org/doi/abs/10.1145/3582016.3582036 | CaT: A Solver-Aided Compiler for Packet-Processing Pipelines ] (ASPLOS’23) 4. [ https://www.usenix.org/conference/nsdi22/presentation/li-yifan | Cetus: Releasing P4 Programmers from the Chore of Trial and Error Compiling ] (NSDI’22) Verification for Distributed Systems 1. [ https://www.cis.upenn.edu/~alur/SyGuS13.pdf | Syntax-guided Synthesis ] (FMCAD’13) 2. [ https://www.usenix.org/conference/osdi22/presentation/yao | DuoAI: Fast, Automated Inference of Inductive Invariants for Verifying Distributed Protocols ] (OSDI’22) 3. [ https://dl.acm.org/doi/pdf/10.1145/3622876 | Message Chain Invariant for Distributed System Verification ] (OOPSLA’23) 4. [ https://homes.cs.washington.edu/~ztatlock/pubs/verdi-wilcox-pldi15.pdf | Verdi: A Framework for Implementing and Formally Verifying Distributed Systems ] (PLDI’15) Formal Methods Background 1. [ https://dl.acm.org/doi/10.1145/1592434.1592438 | Software model checking ] (ACM Computing Survey) [ https://people.eecs.berkeley.edu/~sseshia/pubdir/SMT-BookChapter.pdf | Satisfiability Modulo Theories. Handbook of Model Checking ] (2018)

1 0

Angelina Wang will present her FPO "Operationalizing Responsible Machine Learning: From Equality Towards Equity" on Monday, May 6, 2024 at 2:30 PM in CS 402.
by CS Grad Department 06 Apr '24

06 Apr '24

Angelina Wang will present her FPO " Operationalizing Responsible Machine Learning: From Equality Towards Equity " on Monday, May 6, 2024 at 2:30 PM in CS 402 . Location: CS 402 The members of Angelina ’s committee are as follows: Examiners: Olga Russakovsky (Adviser), Arvind Narayanan , Solon Barocas (Cornell) Readers: Aleksandra Korolova , Janet Vertesi A copy of her thesis is available upon request. Please email gradinfo(a)cs.princeton.edu if you would like a copy of the thesis. Everyone is invited to attend her talk. Abstract follows below: With the widespread proliferation of machine learning, there arises both the opportunity for societal benefit as well as the risk of harm. Approaching responsible machine learning is challenging because technical approaches may prioritize a mathematical definition of fairness that correlates poorly to real-world constructs of fairness due to too many layers of abstraction. Conversely, social approaches that engage with prescriptive theories may produce findings that are too abstract to effectively translate into practice. In my research, I bridge these approaches and utilize social implications to guide technical work. I will discuss three research directions that show how, despite the technically convenient approach of considering equality acontextually, a stronger engagement with societal context allows us to operationalize a more equitable formulation. First, I will introduce a dataset tool that we developed to analyze complex, socially-grounded forms of visual bias. Then, I will provide empirical evidence to support how we should incorporate societal context in bringing intersectionality into machine learning. Finally, I will discuss how in the excitement of using LLMs for tasks like human participant replacement, we have neglected to consider the importance of human positionality. Overall, I will explore how we can expand a narrow focus on equality in responsible machine learning to encompass a broader understanding of equity that substantively engages with societal context.

1 0

Uma Girish will present her FPO "Quantum versus Classical Communication and Query Complexity" on Thursday, May 2nd, 2024 at 11am in CS 201.
by Gradinfo 05 Apr '24

05 Apr '24

Uma Girish will present her FPO "Quantum versus Classical Communication and Query Complexity" on Thursday, May 2nd, 2024 at 11am in CS 201. The members of her committee are as follows: Examiners: Ran Raz (adviser), Mark Braverman and Gillat Kol Readers: Matt Weinberg and Huacheng Yu All are welcome to attend. Please see abstract below. Understanding the relative power of quantum versus classical computation is a fascinating and important problem in modern science on which there is likely to be much research and progress in the next few decades. While quantum algorithms are widely believed to exponentially outperform classical algorithms, there are very few settings in which this has been unconditionally proved. Communication complexity and query complexity are striking examples of such settings, where we can mathematically prove that quantum algorithms exponentially outperform classical algorithms. In this thesis we study the advantages of quantum over classical in these settings and present new and improved quantum speedups over classical. Among several results, we achieve state-of-the-art quantum speedups in communication complexity, using quantum protocols that are efficiently implementable, and using noisy quantum protocols where all qubits except for one are maximally noisy. We also study the power of entanglement and demonstrate in various ways that a slight increase in the entanglement can provide exponential savings in the communication complexity. We also study the power of adaptive queries in quantum query complexity and show that each successive round of quantum queries can yield super-exponential speedups in the number of quantum queries.

1 0

Princeton Robotics Seminar: Friday @ 11 AM (Changliu Liu) and 12:30 PM (Claire Tomlin)
by Emily C. Lawrence 02 Apr '24

02 Apr '24

Join us Friday 4/5 for two fantastic robotics speakers! Speaker: Prof. [ http://icontrol.ri.cmu.edu/ | Changliu Liu ] , CMU Date: Friday, April 5th, 2024 Time: 11:00 AM Room: Computer Science 105 Princeton Robotics Seminar Students: [ https://forms.gle/rK7HNHkKeVqRB4sKA | Sign-up for lunch with the speaker here ] (12:00 - 1:30 PM.) Title: Ensuring Robot Safety Through Safety Index Synthesis Abstract: Safety Index is a special class of high order control barrier functions. Its purpose is to ensure forward invariance within a user-specified safe set and achieve finite time convergence to that set. Synthesizing a valid safety index poses significant challenges, particularly when dealing with control limits, uncertainties, and time-varying dynamics. In this talk, I will introduce a variety of approaches that can be used for safety index synthesis, including a rule-based method, an evolutionary optimization-based approach, a constrained reinforcement learning-based approach, an adversarial optimization-based approach, as well as sum of square programming. The parameterization of the safety index can either take an analytical form or be a neural network. I will conclude the talk by highlighting the limitations of existing work and discuss potential future directions, including integrating formal verification into neural safety index synthesis. Bio: Dr. Changliu Liu is an assistant professor in the Robotics Institute, School of Computer Science, Carnegie Mellon University (CMU), where she leads the Intelligent Control Lab. Prior to joining CMU, Dr. Liu was a postdoc at Stanford Intelligent Systems Laboratory. She received her Ph.D. in Engineering together with Master degrees in Engineering and Mathematics from University of California at Berkeley and her bachelor degrees in Engineering and Economics from Tsinghua University. Her research interests lie in the design and verification of intelligent systems with applications to manufacturing and transportation. She published the book “Designing robot behavior in human-robot interactions” with CRC Press in 2019. She is the founder of the International Neural Network Verification Competition launched in 2020. Her work has been recognized by NSF Career Award, Amazon Research Award, Ford URP Award, Advanced Robotics for Manufacturing Champion Award, and many best/outstanding paper awards. Speaker: Prof. [ http://hybrid.eecs.berkeley.edu/ | Claire Tomlin ] , UC Berkeley Date: Friday, April 5th, 2024 Time: 12:30 PM Room: Bowen Hall 222 MAE Baetjer Colloquium Lunch will be served at 12:00 PM. Students: To meet with Claire Tomlin, please email Julia L. Brav at [ mailto:jbrav@princeton.edu | jbrav(a)princeton.edu ] no later than 5:00PM on Wednesday, April 3, and indicate your department. Title: Safe Learning in Control Abstract: In many applications of autonomy in robotics, guarantees that constraints are satisfied throughout the learning process are paramount. We present a controller synthesis technique based on the computation of reachable sets, using optimal control and game theory. Then, we present methods for combining reachability with learning-based methods, to enable performance improvement while maintaining safety, and to move towards safe robot control with learned models of the dynamics and the environment. We will discuss different interaction models with other agents, and some implications of model vs. learning-based predictions. Bio: Claire Tomlin is the James and Katherine Lau Professor and Chair of the Department of Electrical Engineering and Computer Sciences at UC Berkeley. She was an Assistant, Associate, and Full Professor at Stanford from 1998-2007, and in 2005 she joined Berkeley. Claire works in hybrid systems and control and integrates machine learning methods with control theoretic methods in the field of safe learning. She works in the applications of air traffic and unmanned air vehicle systems. She is a MacArthur Fellow, and a member of the National Academy of Engineering and the American Academy of Arts and Sciences.

1 0

DeCenter Seminar: Andrew Miller, 4/3/24 4:30pm
by Emily C. Lawrence 29 Mar '24

29 Mar '24

[ https://decenter.princeton.edu/ | The DeCenter ] is delighted to extend an invitation to a seminar featuring Andrew Miller on Wednesday April 3rd at 4:30pm . The seminar will be held in room 105 of the Computer Science Building . There will be a light reception to follow. Talk Title: [ https://decenter.princeton.edu/events/decenter-seminar-privacy-preserving-s… | Privacy Preserving Smart Contracts ] Abstract: While smart contracts have catalyzed an exciting burst of permissionless innovation, they are held back by their inability to operate on private data. Fortunately, there are several techniques for addressing this, including hardware (TEEs) and cryptography (MPC, FHE, ZKP). I’ll explain all of these and how they fit together to build private smart contracts, including how they’re used in upcoming projects, Flashbots SUAVE and Cycles credit network. Bio: Andrew Miller is an Associate Professor at the University of Illinois, Urbana-Champaign, in [ https://www.ece.illinois.edu/ | Electrical and Computer Engineering ] and affiliate in [ https://cs.illinois.edu/ | Computer Science ] . He is also an Associate Director of the [ http://initc3.org/ | Initiative for Cryptocurrencies and Contracts (IC3) ] and a board member of the [ http://z.cash.foundation/ | Zcash Foundation ] . Andrew received his Ph.D. from the University of Maryland [ http://www.cyber.umd.edu/ | Cybersecurity Center ] . Additionally, he is the Director of the [ https://decentralize.ece.illinois.edu/ | Decentralized Systems Lab at UIUC! ] His research interests are broadly in computer security and focused on the design of secure decentralized systems and cryptocurrencies. He combines techniques from programming languages, cryptography, and distributed computing.”

1 0

William Pierson Field Lecture: Inioluwa Deborah Raji, Friday, Apr 5 at 1:30pm
by Emily C. Lawrence 28 Mar '24

28 Mar '24

William Pierson Field Lecture Speaker: Inioluwa Deborah Raji, University of California, Berkeley and the Mozilla Foundation Location: Robertson Hall 001 Date: Friday, April 5 Time: 1:30-2:50pm Host: Prof. Lydia Liu Event page: [ https://www.cs.princeton.edu/events/26615 | https://www.cs.princeton.edu/events/26615 ] Title: Audits and Accountability in the Age of Artificial Intelligence Inioluwa Deborah Raji is a Nigerian-Canadian computer scientist and activist who works on algorithmic bias, AI accountability, and algorithmic auditing. She is a Mozilla fellow and Ph.D. student in computer science at University of California, Berkeley, who is interested in questions on algorithmic auditing and evaluation. In the past, she worked closely with the Algorithmic Justice League initiative to highlight bias in deployed AI products. She has also worked with Googleʼs Ethical AI team and been a research fellow at the Partnership on AI and AI Now Institute at New York University working on various projects to operationalize ethical considerations in ML engineering practice. In 2000 was named to Forbes 30 Under 30 and MIT Tech Review 35 Under 35 Innovators. Raji’s lecture will be followed by a fireside chat with Lydia Liu, assistant professor of computer science.

1 0

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