- talks - lists.cs.princeton.edu

CS and CITP Colloquium Speaker Rediet Abebe, Mon Mar 9 at 12:30pm
by Emily C. Lawrence 03 Mar '20

03 Mar '20

CS and CITP Colloquium Speaker Rediet Abebe, Harvard Society of Fellows Monday, March 9 - 12:30pm Computer Science - Room 105 Host: Arvind Narayanan [ https://www.cs.princeton.edu/events/25922 | https://www.cs.princeton.edu/events/25922 ] Title: Designing Algorithms for Social Good Algorithmic and artificial intelligence techniques show immense potential to deepen our understanding of socioeconomic inequality and inform interventions designed to improve access to opportunity. Interventions aimed at historically under-served communities are made particularly challenging by the fact that disadvantage and inequality are multifaceted, notoriously difficult to measure, and reinforced by feedback loops in underlying structures. In this talk, we develop and analyze algorithmic and computational techniques to address these issues through two types of interventions: one in the form of allocating scarce societal resources and another in the form of improving access to information. We examine the ways in which techniques from algorithms, discrete optimization, and network and computational science can combat different forms of disadvantage, including susceptibility to income shocks, disparities in access to health information, and social segregation. We discuss current policy and practice informed by this work and close with a discussion of an emerging research area -- Mechanism Design for Social Good (MD4SG, http://md4sg.com/) -- around the use of algorithms, optimization, and mechanism design to address this category of problems. Bio: Rediet Abebe is a Junior Fellow at the Harvard Society of Fellows. She holds a Ph.D. in computer science from Cornell University, where she was advised by Jon Kleinberg, as well as an M.S. in applied mathematics from Harvard University, an M.A. in mathematics from the University of Cambridge, and a B.A. in mathematics from Harvard College. Her research is in the fields of algorithms and AI, with a focus on discrete algorithms, optimization, network and computational science, and their applications to equity and social good concerns. As part of this research agenda, Abebe co-founded Mechanism Design for Social Good (MD4SG), a multi-institutional, interdisciplinary initiative working to improve access to opportunity. This initiative has participants from over 100 institutions in 20 countries and has been supported by Schmidt Futures, the MacArthur Foundation, and the Institute for New Economic Thinking. Abebe's work has informed policy and practice at various organizations, including the Ethiopian Ministry of Education and the National Institutes of Health. In 2019, she served on the NIH Advisory Committee to the Director Working Group on AI (https://acd.od.nih.gov/working-groups/ai.html), whose recommendations were unanimously approved by the General Director's advisory committee. Abebe was recently recognized by the 2019 MIT Technology Review’s 35 Innovators Under 35 award and honored as a one to watch by the 2018 Bloomberg 50 list. She has presented her research in venues such as the National Academy of Sciences, the United Nations, and the Museum of Modern Art. Her work has been covered by outlets including Forbes, the Boston Globe, and the Washington Post. In 2017 Abebe co-founded Black in AI (https://blackinai.github.io/), a non-profit organization tackling diversity and inclusion issues in the field. Her research is deeply influenced by her upbringing in her hometown of Addis Ababa, Ethiopia. This talk is being co-sponsored by CITP and the Department of Computer Science.

1 0

Distinguished Colloquium Speaker-Daniel Jackson, TODAY at 12:30pm
by Emily C. Lawrence 02 Mar '20

02 Mar '20

CS Distinguished Colloquium Speaker Daniel Jackson, CSAIL, Massachusetts Institute of Technology Monday, March 2 - 12:30pm Computer Science - Room 105 Host: Jennifer Rexford [ https://www.cs.princeton.edu/events/25913 | https://www.cs.princeton.edu/events/25913 ] Title: A New Abstraction for Software Design The internal design of software—how the code is structured—is powered by familiar abstractions (such as abstract types, classes and modules). But the external design—how the software actually behaves—is usually viewed informally, without the guidance of robust abstractions. For the last few years, I have been exploring a new abstraction that can shape how we think about software applications and systems, and that provides a way to organize behaviors, encapsulate reusable ideas, and evaluate designs. In this talk, I’ll define this abstraction and show how it can be used to explain a variety of flaws in familiar applications. I’ll also present some general principles that attempt to capture some key aspects of good software design. Bio: Daniel Jackson is a professor of computer science and MacVicar teaching fellow at MIT, and associate director of the Computer Science and Artificial Intelligence Laboratory. His research has focused primarily on software modeling and design, most notably the Alloy modeling language. He is also a photographer whose most recent project brings to light the experiences of those with depression and other mental health issues ( [ http://portraitsofresilience.com/ | http://portraitsofresilience.com ] ).

1 0

Reminder: Distinguished Colloquium Speaker-Daniel Jackson tomorrow at 12:30pm
by Emily C. Lawrence 01 Mar '20

01 Mar '20

CS Distinguished Colloquium Speaker Daniel Jackson, CSAIL, Massachusetts Institute of Technology Monday, March 2 - 12:30pm Computer Science - Room 105 Host: Jennifer Rexford [ https://www.cs.princeton.edu/events/25913 | https://www.cs.princeton.edu/events/25913 ] Title: A New Abstraction for Software Design The internal design of software—how the code is structured—is powered by familiar abstractions (such as abstract types, classes and modules). But the external design—how the software actually behaves—is usually viewed informally, without the guidance of robust abstractions. For the last few years, I have been exploring a new abstraction that can shape how we think about software applications and systems, and that provides a way to organize behaviors, encapsulate reusable ideas, and evaluate designs. In this talk, I’ll define this abstraction and show how it can be used to explain a variety of flaws in familiar applications. I’ll also present some general principles that attempt to capture some key aspects of good software design. Bio: Daniel Jackson is a professor of computer science and MacVicar teaching fellow at MIT, and associate director of the Computer Science and Artificial Intelligence Laboratory. His research has focused primarily on software modeling and design, most notably the Alloy modeling language. He is also a photographer whose most recent project brings to light the experiences of those with depression and other mental health issues ( [ http://portraitsofresilience.com/ | http://portraitsofresilience.com ] ).

1 0

Jordan Ash will present his Pre FPO "Towards Flexible Active and Online Learning With Neural Networks" on Friday, March 6, 2020 at 1pm in CS 302
by Nicki Mahler 28 Feb '20

28 Feb '20

Jordan Ash will present his Pre FPO "Towards Flexible Active and Online Learning With Neural Networks" on Friday, March 6, 2020 at 1pm in CS 302. The members of his committee are as follows: Ryan Adams (Adviser); Readers: Ryan Adams and Rob Schapire (MSR); Examiners: Barbara Engelhardt, Szymon Rusinkiewicz, and Akshay Krishnamurthy (MSR) Everyone is invited to attend his talk. The talk title and abstract follow below. Title: Towards Flexible Active and Online Learning With Neural Networks Abstract: Deep learning has elicited breakthrough successes on a wide array of machine learning tasks. Outside of the fully-supervised regime, however, many deep learning algorithms are brittle and unable to reliably perform across model architectures, dataset types, and optimization parameters. As a consequence, these algorithms are not easily usable by non-machine-learning experts, limiting their ability to meaningfully impact science and society. This talk consists of two parts. First, I’ll overview an in-progress project involving machine learning for 3D printing. I will then move to the main part of the talk, and address some nuanced pathologies around the use of deep learning for active and passive online learning. I propose a practical active learning approach for neural networks that is robust to environmental variables: Batch Active learning by Diverse Gradient Embeddings (BADGE). I also discuss the deleterious generalization effects of warm-starting the optimization of neural networks in sequential environments, why this is a major problem for deep learning, and provide a simple solution.

1 0

Colloquium Speaker Omid Abari, Thurs Mar 5 at 12:30pm
by Emily C. Lawrence 28 Feb '20

28 Feb '20

CS Colloquium Speaker Omid Abari, University of Waterloo Thursday, March 5 - 12:30pm Computer Science - Room 105 Host: Kyle Jamieson [ https://www.cs.princeton.edu/events/25921 | https://www.cs.princeton.edu/events/25921 ] Title: Software-Hardware Systems for the Internet of Things Recently, there has been a huge interest in Internet of Things ( IoT ) systems, which bring the digital world into the physical world around us. However, barriers still remain to realizing the dream applications of IoT . One of the biggest challenges in building IoT systems is the huge diversity of their demands and constraints (size, energy, latency, throughput, etc.). For example, virtual reality and gaming applications require multiple gigabits-per-second throughput and millisecond latency. Tiny sensors spread around a greenhouse or smart home must be low-cost and batteryless to be sustainable in the long run. Today's networking technologies fall short in supporting these IoT applications with a hugely diverse set of constraints and demands. As such, they require distinct innovative solutions. In this talk, I will describe how we can design a new class of networking technologies for IoT by designing software and hardware jointly, with an understanding of the intended application. In particular, I will present two examples of our solutions. The first solution tackles the throughput limitations of existing IoT networks by developing new millimeter wave devices and protocols, enabling many new IoT applications, such as untethered high-quality virtual reality. The second solution tackles the energy imitations of IoT networks by introducing new wireless devices that can sense and communicate without requiring any batteries. I demonstrate how our solution is applicable in multiple, diverse domains such as HCI, medical, and agriculture. I will conclude the talk with future directions in IoT research, both in terms of technologies and applications. Bio: Omid Abari is an Assistant Professor at the University of Waterloo, School of Computer Science. He received his Ph.D. in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology (MIT) in 2018. His research interests are in the area of computer networks and mobile systems, with applications to the Internet of Things ( IoT ). He is currently leading the Intelligent Connectivity (ICON) Lab, where his team focuses on the design and implementation of novel softwarehardware systems that deliver ubiquitous sensing, communication and computing at scale. His work has been selected for GetMobile research highlights (2018, 2019), and been featured by several media outlets, including Wired, TechCrunch, Engadget , IEEE Spectrum, and ACM Tech News.

1 0

CS and CITP Colloquium Speaker Aleksandra Korolova, TODAY at 12:30pm
by Emily C. Lawrence 25 Feb '20

25 Feb '20

CS and CITP Colloquium Speaker Aleksandra Korolova , University of Southern California Tuesday, February 25 - 12:30pm Computer Science - Room 105 Host: Jonathan Mayer [ https://www.cs.princeton.edu/events/25931 | https://www.cs.princeton.edu/events/25931 ] Title: Aligning the web ecosystem with societal values via measurements, definitions and algorithms The web ecosystem relies on data- and algorithms- driven innovation and monetization. In this talk, I will explore the challenges and opportunities for making these practices aligned with societal values such as privacy and fairness. I will first describe our work in applying differential privacy for development of data-driven product features without requiring raw data collection from users. I will then present our work on systematically identifying new societal concerns posed by current implementations of targeted advertising systems such as: privacy violations, manipulation of the vulnerable, discrimination, and creation of informational filter bubbles. I will conclude by discussing how such measurements, combined with definitions and algorithms, particularly from the fields of differential privacy and algorithmic fairness, can provide a language for reasoning about trade-offs between utility, privacy, and fairness, and give solution approaches to both computer scientists and policy makers. Bio: Aleksandra Korolova is a WiSE Gabilan Assistant Professor of Computer Science at USC, where she researches algorithms and technologies that enable data-driven innovations while preserving privacy and fairness. Prior to joining USC, Aleksandra was a research scientist at Google. Aleksandra received her PhD in Computer Science from Stanford University. Her PhD thesis, which focused on protecting privacy when mining and sharing user data, has been recognized by the Arthur L. Samuel Thesis Award 2011-2012, for the best PhD thesis in the Computer Science Department at Stanford. Aleksandra is also a co-winner of the 2011 PET Award for outstanding research in privacy enhancing technologies for exposing privacy violations of microtargeted advertising and a runner-up for the 2015 PET Award for RAPPOR, the first commercial deployment of differential privacy. Aleksandra's most recent work, on discrimination in ad delivery, has received CSCW Honorable Mention Award and Recognition of Contribution to Diversity and Inclusion, was cited in Facebook's Civil Rights Audit Report, and invited for a briefing for Members of the House Financial Services Committee. This talk is being co-sponsored by CITP and the Department of Computer Science.

1 0

Distinguished Colloquium Speaker-Daniel Jackson, Mon March 2 at 12:30pm
by Emily C. Lawrence 25 Feb '20

25 Feb '20

CS Distinguished Colloquium Speaker Daniel Jackson, CSAIL, Massachusetts Institute of Technology Monday, March 2 - 12:30pm Computer Science - Room 105 Host: Jennifer Rexford [ https://www.cs.princeton.edu/events/25913 | https://www.cs.princeton.edu/events/25913 ] Title: A New Abstraction for Software Design The internal design of software—how the code is structured—is powered by familiar abstractions (such as abstract types, classes and modules). But the external design—how the software actually behaves—is usually viewed informally, without the guidance of robust abstractions. For the last few years, I have been exploring a new abstraction that can shape how we think about software applications and systems, and that provides a way to organize behaviors, encapsulate reusable ideas, and evaluate designs. In this talk, I’ll define this abstraction and show how it can be used to explain a variety of flaws in familiar applications. I’ll also present some general principles that attempt to capture some key aspects of good software design. Bio: Daniel Jackson is a professor of computer science and MacVicar teaching fellow at MIT, and associate director of the Computer Science and Artificial Intelligence Laboratory. His research has focused primarily on software modeling and design, most notably the Alloy modeling language. He is also a photographer whose most recent project brings to light the experiences of those with depression and other mental health issues ( [ http://portraitsofresilience.com/ | http://portraitsofresilience.com ] ).

1 0

Colloquium Speaker Dylan Hadfield-Menell, TODAY at 12:30pm
by Emily C. Lawrence 24 Feb '20

24 Feb '20

CS Colloquium Speaker Dylan Hadfield- Menell , University of California, Berkeley Monday, February 24 - 12:30pm Computer Science - Room 105 Host: Tom Griffiths [ https://www.cs.princeton.edu/events/25920 | https://www.cs.princeton.edu/events/25920 ] Title: The Value Alignment Problem in Artificial Intelligence Much of our success in artificial intelligence stems from the adoption of a simple paradigm: specify an objective or goal, and then use optimization algorithms to identify a behavior (or predictor) that optimally achieves this goal. This has been true since the early days of AI (e.g., search algorithms such as A* that aim to find the optimal path to a goal state), and this paradigm is common to AI, statistics, control theory, operations research, and economics. Loosely speaking, the field has evaluated the intelligence of an AI system by how efficiently and effectively it optimizes for its objective. This talk will provide an overview of my thesis work, which proposes and explores the consequences of a simple, but consequential, shift in perspective: we should measure the intelligence of an AI system by its ability to optimize for our objectives. In an ideal world, these measurements would be the same -- all we have to do is write down the correct objective! This is easier said than done: misalignment between the behavior a system designer actually wants and the behavior incentivized by the reward or loss functions they specify is routine, it is commonly observed in a wide variety of practical applications, and fundamental, as a consequence of limited human cognitive capacity. This talk will build up a formal model of this value alignment problem as a cooperative human-robot interaction: an assistance game of partial information between a human principal and an autonomous agent. It will begin with a discussion of a simple instantiation of this game where the human designer takes one action, write down a proxy objective, and the robot attempts to optimize for the true objective by treating the observed proxy as evidence about the intended goal. Next, I will generalize this model to introduce Cooperative Inverse Reinforcement Learning, a general and formal model of this assistance game, and discuss the design of efficient algorithms to solve it. The talk will conclude with a discussion of directions for further research including applications to content recommendation and home robotics, the development of reliable and robust design environments for AI objectives, and the theoretical study of AI regulation by society as a value alignment problem with multiple human principals. Bio: Dylan is a final year Ph.D. student at UC Berkeley, advised by Anca Dragan, Pieter Abbeel , and Stuart Russell. His research focuses on the value alignment problem in artificial intelligence. His goal is to design algorithms that learn about and pursue the intended goal of their users, designers, and society in general. His recent work has focused on algorithms for human-robot interaction with unknown preferences and reliability engineering for learning systems.

1 0

Reminder: CS and CITP Colloquium Speaker Aleksandra Korolova, tomorrow at 12:30pm
by Emily C. Lawrence 24 Feb '20

24 Feb '20

CS and CITP Colloquium Speaker Aleksandra Korolova , University of Southern California Tuesday, February 25 - 12:30pm Computer Science - Room 105 Host: Jonathan Mayer [ https://www.cs.princeton.edu/events/25931 | https://www.cs.princeton.edu/events/25931 ] Title: Aligning the web ecosystem with societal values via measurements, definitions and algorithms The web ecosystem relies on data- and algorithms- driven innovation and monetization. In this talk, I will explore the challenges and opportunities for making these practices aligned with societal values such as privacy and fairness. I will first describe our work in applying differential privacy for development of data-driven product features without requiring raw data collection from users. I will then present our work on systematically identifying new societal concerns posed by current implementations of targeted advertising systems such as: privacy violations, manipulation of the vulnerable, discrimination, and creation of informational filter bubbles. I will conclude by discussing how such measurements, combined with definitions and algorithms, particularly from the fields of differential privacy and algorithmic fairness, can provide a language for reasoning about trade-offs between utility, privacy, and fairness, and give solution approaches to both computer scientists and policy makers. Bio: Aleksandra Korolova is a WiSE Gabilan Assistant Professor of Computer Science at USC, where she researches algorithms and technologies that enable data-driven innovations while preserving privacy and fairness. Prior to joining USC, Aleksandra was a research scientist at Google. Aleksandra received her PhD in Computer Science from Stanford University. Her PhD thesis, which focused on protecting privacy when mining and sharing user data, has been recognized by the Arthur L. Samuel Thesis Award 2011-2012, for the best PhD thesis in the Computer Science Department at Stanford. Aleksandra is also a co-winner of the 2011 PET Award for outstanding research in privacy enhancing technologies for exposing privacy violations of microtargeted advertising and a runner-up for the 2015 PET Award for RAPPOR, the first commercial deployment of differential privacy. Aleksandra's most recent work, on discrimination in ad delivery, has received CSCW Honorable Mention Award and Recognition of Contribution to Diversity and Inclusion, was cited in Facebook's Civil Rights Audit Report, and invited for a briefing for Members of the House Financial Services Committee. This talk is being co-sponsored by CITP and the Department of Computer Science.

1 0

Reminder: Colloquium Speaker Dylan Hadfield-Menell, tomorrow at 12:30pm
by Emily C. Lawrence 23 Feb '20

23 Feb '20

CS Colloquium Speaker Dylan Hadfield- Menell , University of California, Berkeley Monday, February 24 - 12:30pm Computer Science - Room 105 Host: Tom Griffiths [ https://www.cs.princeton.edu/events/25920 | https://www.cs.princeton.edu/events/25920 ] Title: The Value Alignment Problem in Artificial Intelligence Much of our success in artificial intelligence stems from the adoption of a simple paradigm: specify an objective or goal, and then use optimization algorithms to identify a behavior (or predictor) that optimally achieves this goal. This has been true since the early days of AI (e.g., search algorithms such as A* that aim to find the optimal path to a goal state), and this paradigm is common to AI, statistics, control theory, operations research, and economics. Loosely speaking, the field has evaluated the intelligence of an AI system by how efficiently and effectively it optimizes for its objective. This talk will provide an overview of my thesis work, which proposes and explores the consequences of a simple, but consequential, shift in perspective: we should measure the intelligence of an AI system by its ability to optimize for our objectives. In an ideal world, these measurements would be the same -- all we have to do is write down the correct objective! This is easier said than done: misalignment between the behavior a system designer actually wants and the behavior incentivized by the reward or loss functions they specify is routine, it is commonly observed in a wide variety of practical applications, and fundamental, as a consequence of limited human cognitive capacity. This talk will build up a formal model of this value alignment problem as a cooperative human-robot interaction: an assistance game of partial information between a human principal and an autonomous agent. It will begin with a discussion of a simple instantiation of this game where the human designer takes one action, write down a proxy objective, and the robot attempts to optimize for the true objective by treating the observed proxy as evidence about the intended goal. Next, I will generalize this model to introduce Cooperative Inverse Reinforcement Learning, a general and formal model of this assistance game, and discuss the design of efficient algorithms to solve it. The talk will conclude with a discussion of directions for further research including applications to content recommendation and home robotics, the development of reliable and robust design environments for AI objectives, and the theoretical study of AI regulation by society as a value alignment problem with multiple human principals. Bio: Dylan is a final year Ph.D. student at UC Berkeley, advised by Anca Dragan, Pieter Abbeel , and Stuart Russell. His research focuses on the value alignment problem in artificial intelligence. His goal is to design algorithms that learn about and pursue the intended goal of their users, designers, and society in general. His recent work has focused on algorithms for human-robot interaction with unknown preferences and reliability engineering for learning systems.

1 0