- talks - lists.cs.princeton.edu

Donghun Lee will present his FPO, "Learning To Learn Optimally: A Practical Framework for Machine Learning Applications With Finite Time Horizon" on Tuesday, 4/23/2019 at 2pm in CS 105.
by Nicki Mahler 16 Apr '19

16 Apr '19

Donghun Lee will present his FPO, "Learning To Learn Optimally: A Practical Framework for Machine Learning Applications With Finite Time Horizon" on Tuesday, 4/23/2019 at 2pm in CS 105. The members of his committee are as follows: Examiners: Warren Powell (adviser), Ryan Adams, and Peter Ramadge (ELE); Readers: Mengdi Wang (ORFE), Yuxin Chen (ELE), and Elad Hazan. A copy of his thesis is available upon request. All are welcome to attend. Abstract follows below. Most machine learning algorithms with asymptotic guarantees leave nite time horizon issues such as initialization or tuning open to the end users, to whom the burden may cause undesirable outcome in practice where nite time horizon performance matters. As an inspirational case of the undesirable nite time behavior, we identify the nite time bias in Q-learning algorithm and present a method to alleviate the bias on-the- y. Motivated by the gap between the asymptotic guarantees and the practical burdens of machine learning, we investigate the problem of learning to learn, de ned as the problem of learning how to apply a given machine learning algorithm to solve a given task with a nite time horizon objective function. To address the problem more generally, we develop the framework of learning to learn optimally (LTLO), which models the problem of optimal application of a machine learning algorithm to a given task in a nite horizon. We demonstrate the use of the LTLO framework as a modeling tool for a real world problem via an example of learning to learn how to bid in sponsored search auctions. We show the practical bene t of using the LTLO framework as a baseline to construct meta-LQKG+, a knowledge gradient based LTLO algorithm designed to solve online hyperparameter optimization approximately with a few number of trials, and demonstrate the practical sample eciency of the algorithm. Answering to the need for a robust anytime LTLO algorithm, we develop online regularized knowledge gradient policy, which solves the problem of LTLO with high probability and has a sublinear regret bound.

1 0

Colloquium Speaker Amy Zhang, TODAY at 12:30pm
by Emily C. Lawrence 16 Apr '19

16 Apr '19

Colloquium Speaker Amy Zhang from Massachusetts Institute of Technology Tuesday, April 16 - 12:30pm Computer Science - Room 105 Host: Adam Finkelstein [ https://www.cs.princeton.edu/events/25825 | https://www.cs.princeton.edu/events/25825 ] Systems to Improve Online Discussion Discussions online are integral to everyday life, affecting how we learn, work, socialize, and participate in public society. Yet the systems that we use to conduct online discourse, whether they be email, chat, or forums, have changed little since their inception many decades ago. As more people participate and more venues for discourse migrate online, new problems have arisen, and old problems have intensified. People are still drowning in information and must now juggle dozens of disparate discussion silos in addition. Finally, an unfortunately significant proportion of this online interaction is unwanted or unpleasant, with clashing norms leading to people bickering or getting harassed into silence. My research in human-computer interaction is on reimagining outdated designs towards designing novel online discussion systems that fix what's broken about online discussion. To solve these problems, I develop tools that empower users and communities to have direct control over their experiences and information. These include: 1) summarization tools to make sense of large discussions, 2) annotation tools to situate conversations in the context of what is being discussed, as well as 3) moderation tools to give users more fine-grained control over content delivery. Bio: Amy X. Zhang is a graduate student at MIT’s Computer Science and Artificial Intelligence Laboratory, focusing on human-computer interaction and social computing, and a 2018-19 Fellow at the Harvard Berkman Klein Center. She has interned at Microsoft Research and Google Research, received awards at ACM CHI and CSCW, and featured in stories by ABC News, BBC, CBC, and more. She has an M.Phil. in CS at University of Cambridge on a Gates Fellowship and a B.S. in CS at Rutgers, where she captained the Division I Women’s tennis team. Her research is supported by a Google PhD Fellowship and an NSF Graduate Research Fellowship.

1 0

Reminder: Colloquium Speaker Amy Zhang, tomorrow at 12:30pm
by Emily C. Lawrence 15 Apr '19

15 Apr '19

Colloquium Speaker Amy Zhang from Massachusetts Institute of Technology Tuesday, April 16 - 12:30pm Computer Science - Room 105 Host: Adam Finkelstein [ https://www.cs.princeton.edu/events/25825 | https://www.cs.princeton.edu/events/25825 ] Systems to Improve Online Discussion Discussions online are integral to everyday life, affecting how we learn, work, socialize, and participate in public society. Yet the systems that we use to conduct online discourse, whether they be email, chat, or forums, have changed little since their inception many decades ago. As more people participate and more venues for discourse migrate online, new problems have arisen, and old problems have intensified. People are still drowning in information and must now juggle dozens of disparate discussion silos in addition. Finally, an unfortunately significant proportion of this online interaction is unwanted or unpleasant, with clashing norms leading to people bickering or getting harassed into silence. My research in human-computer interaction is on reimagining outdated designs towards designing novel online discussion systems that fix what's broken about online discussion. To solve these problems, I develop tools that empower users and communities to have direct control over their experiences and information. These include: 1) summarization tools to make sense of large discussions, 2) annotation tools to situate conversations in the context of what is being discussed, as well as 3) moderation tools to give users more fine-grained control over content delivery. Bio: Amy X. Zhang is a graduate student at MIT’s Computer Science and Artificial Intelligence Laboratory, focusing on human-computer interaction and social computing, and a 2018-19 Fellow at the Harvard Berkman Klein Center. She has interned at Microsoft Research and Google Research, received awards at ACM CHI and CSCW, and featured in stories by ABC News, BBC, CBC, and more. She has an M.Phil. in CS at University of Cambridge on a Gates Fellowship and a B.S. in CS at Rutgers, where she captained the Division I Women’s tennis team. Her research is supported by a Google PhD Fellowship and an NSF Graduate Research Fellowship.

1 0

Colloquium Speaker-James Bornholt, Thursday, April 18 at 12:30pm
by Emily C. Lawrence 12 Apr '19

12 Apr '19

Colloquium Speaker James Bornholt from University of Washington Thursday, April 18 - 12:30pm Computer Science - Room 105 Host: Margaret Martonosi [ https://www.cs.princeton.edu/events/25821 | https://www.cs.princeton.edu/events/25821 ] Optimizing the Automated Programming Stack The scale and pervasiveness of modern software poses a challenge for programmers: software reliability is more important than ever, but the complexity of computer systems continues to grow. Automated programming tools are powerful weapons for programmers to tackle this challenge: verifiers that check software correctness, and synthesizers that generate new correct-by-construction programs. These tools are most effective when they apply domain-specific optimizations, but doing so today requires considerable formal methods expertise. In this talk, I present a new application-driven approach to optimizing the automated programming stack underpinning modern domain-specific tools. I will demonstrate the importance of programming tools in the context of memory consistency models, which define the behavior of multiprocessor CPUs and whose subtleties often elude even experts. Our new tool, MemSynth , automatically synthesizes formal descriptions of memory consistency models from examples of CPU behavior. We have used MemSynth to synthesize descriptions of the x86 and PowerPC memory models, each of which previously required person-years of effort to describe by hand, and found several ambiguities and underspecifications in both architectures. I will then present symbolic profiling, a new technique we designed and implemented to help people identify the scalability bottlenecks in automated programming tools. These tools use symbolic evaluation, which evaluates all paths through a program, and is an execution model that defies both human intuition and standard profiling techniques. Symbolic profiling diagnoses scalability bottlenecks using a novel performance model for symbolic evaluation that accounts for all-paths execution. We have used symbolic profiling to find and fix performance issues in 8 state-of-the-art automated tools, improving their scalability by orders of magnitude, and our techniques have been adopted in industry. Finally, I will give a sense of the importance of future application-driven optimizations to the automated programming stack, with applications that inspire improvements to the stack and in turn beget even more powerful automated tools. James Bornholt is a Ph.D. candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Emina Torlak , Dan Grossman, and Luis Ceze . His research interests are in programming languages and formal methods, with a focus on automated program verification and synthesis. His work has received an ACM SIGPLAN Research Highlight, two IEEE Micro Top Picks selections, an OSDI best paper award, and a Facebook Ph.D. fellowship.

1 0

Colloquium Speaker Sarah Chasins, TODAY at 12:30pm
by Emily C. Lawrence 11 Apr '19

11 Apr '19

Colloquium Speaker Sarah Chasins from University of California, Berkeley Thursday, April 11 - 12:30pm Computer Science - Room 105 Host: Andrew Appel Democratizing Web Automation: Programming for Social Scientists and Other Domain Experts [ https://www.cs.princeton.edu/events/25842 | https://www.cs.princeton.edu/events/25842 ] We have promised social scientists a data revolution, but it hasn’t arrived. What stands between practitioners and the data-driven insights they want? Acquiring the data. In particular, acquiring the social media, online forum, and other web data that was supposed to help them produce big, rich, ecologically valid datasets. Web automation programming is resistant to high-level abstractions, so end-user programmers end up stymied by the need to reverse engineer website internals—DOM, JavaScript, AJAX. Programming by Demonstration (PBD) offered one promising avenue towards democratizing web automation. Unfortunately, as the web matured, the programs became too complex for PBD tools to synthesize, and web PBD progress stalled. In this talk, I’ll describe how I reformulated traditional web PBD around the insight that demonstrations are not always the easiest way for non-programmers to communicate their intent. By shifting from a purely Programming-By-Demonstration view to a Programming-By-X view that accepts a variety of user-friendly inputs, we can dramatically broaden the class of programs that come in reach for end-user programmers. My Helena ecosystem combines (i) usable PBD-based program drafting tools, (ii) learnable programing languages, and (iii) novel programming environment interactions. The end result: non-coders write Helena programs in 10 minutes that can handle the complexity of modern webpages, while coders attempt the same task and time out in an hour. I’ll conclude with predictions about the abstraction-resistant domains that will fall next—robotics, analysis of unstructured texts, image processing—and how hybrid PL-HCI breakthroughs will vastly expand access to programming. Bio: Sarah Chasins is a Ph.D. candidate at UC Berkeley, advised by Ras Bodik . Her research interests lie at the intersection of programming languages and human-computer interaction. Much of her work is shaped by ongoing collaborations with social scientists, data scientists, and other non-traditional programmers. She has been awarded an NSF graduate research fellowship and a first place award in the ACM Student Research Competition.

1 0

Colloquium Speaker Amy Zhang, Tuesday, April 16 at 12:30pm
by Emily C. Lawrence 10 Apr '19

10 Apr '19

Colloquium Speaker Amy Zhang from Massachusetts Institute of Technology Tuesday, April 16 - 12:30pm Computer Science - Room 105 Host: Adam Finkelstein [ https://www.cs.princeton.edu/events/25825 | https://www.cs.princeton.edu/events/25825 ] Systems to Improve Online Discussion Discussions online are integral to everyday life, affecting how we learn, work, socialize, and participate in public society. Yet the systems that we use to conduct online discourse, whether they be email, chat, or forums, have changed little since their inception many decades ago. As more people participate and more venues for discourse migrate online, new problems have arisen, and old problems have intensified. People are still drowning in information and must now juggle dozens of disparate discussion silos in addition. Finally, an unfortunately significant proportion of this online interaction is unwanted or unpleasant, with clashing norms leading to people bickering or getting harassed into silence. My research in human-computer interaction is on reimagining outdated designs towards designing novel online discussion systems that fix what's broken about online discussion. To solve these problems, I develop tools that empower users and communities to have direct control over their experiences and information. These include: 1) summarization tools to make sense of large discussions, 2) annotation tools to situate conversations in the context of what is being discussed, as well as 3) moderation tools to give users more fine-grained control over content delivery. Bio: Amy X. Zhang is a graduate student at MIT’s Computer Science and Artificial Intelligence Laboratory, focusing on human-computer interaction and social computing, and a 2018-19 Fellow at the Harvard Berkman Klein Center. She has interned at Microsoft Research and Google Research, received awards at ACM CHI and CSCW, and featured in stories by ABC News, BBC, CBC, and more. She has an M.Phil. in CS at University of Cambridge on a Gates Fellowship and a B.S. in CS at Rutgers, where she captained the Division I Women’s tennis team. Her research is supported by a Google PhD Fellowship and an NSF Graduate Research Fellowship.

1 0

Reminder: Colloquium Speaker Sarah Chasins, tomorrow at 12:30pm
by Emily C. Lawrence 10 Apr '19

10 Apr '19

Colloquium Speaker Sarah Chasins from University of California, Berkeley Thursday, April 11 - 12:30pm Computer Science - Room 105 Host: Andrew Appel Democratizing Web Automation: Programming for Social Scientists and Other Domain Experts [ https://www.cs.princeton.edu/events/25842 | https://www.cs.princeton.edu/events/25842 ] We have promised social scientists a data revolution, but it hasn’t arrived. What stands between practitioners and the data-driven insights they want? Acquiring the data. In particular, acquiring the social media, online forum, and other web data that was supposed to help them produce big, rich, ecologically valid datasets. Web automation programming is resistant to high-level abstractions, so end-user programmers end up stymied by the need to reverse engineer website internals—DOM, JavaScript, AJAX. Programming by Demonstration (PBD) offered one promising avenue towards democratizing web automation. Unfortunately, as the web matured, the programs became too complex for PBD tools to synthesize, and web PBD progress stalled. In this talk, I’ll describe how I reformulated traditional web PBD around the insight that demonstrations are not always the easiest way for non-programmers to communicate their intent. By shifting from a purely Programming-By-Demonstration view to a Programming-By-X view that accepts a variety of user-friendly inputs, we can dramatically broaden the class of programs that come in reach for end-user programmers. My Helena ecosystem combines (i) usable PBD-based program drafting tools, (ii) learnable programing languages, and (iii) novel programming environment interactions. The end result: non-coders write Helena programs in 10 minutes that can handle the complexity of modern webpages, while coders attempt the same task and time out in an hour. I’ll conclude with predictions about the abstraction-resistant domains that will fall next—robotics, analysis of unstructured texts, image processing—and how hybrid PL-HCI breakthroughs will vastly expand access to programming. Bio: Sarah Chasins is a Ph.D. candidate at UC Berkeley, advised by Ras Bodik . Her research interests lie at the intersection of programming languages and human-computer interaction. Much of her work is shaped by ongoing collaborations with social scientists, data scientists, and other non-traditional programmers. She has been awarded an NSF graduate research fellowship and a first place award in the ACM Student Research Competition.

1 0

Jonathan Lu will present his MSE thesis talk on Friday, April 12, 2019 at 11am in CS 302.
by Nicki Mahler 09 Apr '19

09 Apr '19

Jonathan Lu will present his MSE thesis talk on Friday, April 12, 2019 at 11am in CS 302. The members of his committee are Barbara Engelhardt (advisor) and Ben Raphael (reader). Everyone is invited to attend his talk. His talk title and abstract follows below. Title: Regularized Causal Network Inference from Gaussian Process Time Series Abstract: Many methods have been developed to infer causal networks from time series data, but are often insufficient for modern challenges, such as unevenly spaced time series and hundreds to thousands of possible causal variables. For example, single-cell genomics data consists of thousands of protein-coding genes, whose "pseudotime" trajectories are indexed continuously at varying intervals. Here we develop EncoreGP, a causal network inference method that uses Elastic net regression to discover causal relations between continuous time series trajectories (Gaussian Processes). EncoreGP uses impulse functions as causal kernels to bypass previous assumptions of equal timepoint spacing and discrete effects. It uses elastic net regularization to discover sparse, interpretable networks from high-dimensional data. We validate on multiple benchmark networks for bulk and single-cell genomics. While genomics is our focus, EncoreGP can be applied for causal network inference from any large set of time series with uneven timepoints.

1 0

Colloquium Speaker-Chris Maddison TODAY at 12:30pm
by Emily C. Lawrence 09 Apr '19

09 Apr '19

Colloquium Speaker Chris Maddison from University of Oxford Tuesday, April 9 - 12:30pm Computer Science - Room 105 Host: Ryan Adams AlphaGo and the Computational Challenges of Machine Learning [ http://www.cs.princeton.edu/events/25841 | http://www.cs.princeton.edu/events/25841 ] Many computational challenges in machine learning involve the three problems of optimization, integration, and fixed-point computation. These three can often be reduced to each other, so they may also provide distinct vantages on a single problem. In this talk, I present a small part of this picture through a discussion of my work on AlphaGo and two vignettes on my work on the interplay between optimization and Monte Carlo. AlphaGo is the first computer program to defeat a world-champion player, Lee Sedol , in the board game of Go. My work laid the groundwork of the neural net components of AlphaGo , and culminated in our Nature publication describing AlphaGo's algorithm, at whose core hide these three problems. In the first vignette, I present the Hamiltonian descent methods we introduced for first-order optimization. These methods are inspired by the Monte Carlo literature and can achieve fast linear convergence without strong convexity by using a non-standard kinetic energy to condition the optimization. In the second vignette I cover our A* Sampling method, which reduces the problem of Monte Carlo simulation to an optimization problem, and an application to gradient estimation in stochastic computation graphs. Bio: Chris Maddison is a PhD candidate in the Statistical Machine Learning Group in the Department of Statistics at the University of Oxford. He is an Open Philanthropy AI Fellow and spends two days a week as a Research Scientist at DeepMind. His research is broadly focused on the development of numerical methods for deep learning and machine learning. He has worked on methods for variational inference, numerical optimization, and Monte Carlo estimation with a specific focus on those that might work at scale with few assumptions. Chris received his MSc. from the University of Toronto. He received a NeurIPS Best Paper Award in 2014, and was one of the founding members of the AlphaGo project.

1 0

REMINDER: Colloquium Speaker-Chris Maddison tomorrow at 12:30pm
by Emily C. Lawrence 08 Apr '19

08 Apr '19

Colloquium Speaker Chris Maddison from University of Oxford Tuesday, April 9 - 12:30pm Computer Science - Room 105 Host: Ryan Adams AlphaGo and the Computational Challenges of Machine Learning [ http://www.cs.princeton.edu/events/25841 | http://www.cs.princeton.edu/events/25841 ] Many computational challenges in machine learning involve the three problems of optimization, integration, and fixed-point computation. These three can often be reduced to each other, so they may also provide distinct vantages on a single problem. In this talk, I present a small part of this picture through a discussion of my work on AlphaGo and two vignettes on my work on the interplay between optimization and Monte Carlo. AlphaGo is the first computer program to defeat a world-champion player, Lee Sedol , in the board game of Go. My work laid the groundwork of the neural net components of AlphaGo , and culminated in our Nature publication describing AlphaGo's algorithm, at whose core hide these three problems. In the first vignette, I present the Hamiltonian descent methods we introduced for first-order optimization. These methods are inspired by the Monte Carlo literature and can achieve fast linear convergence without strong convexity by using a non-standard kinetic energy to condition the optimization. In the second vignette I cover our A* Sampling method, which reduces the problem of Monte Carlo simulation to an optimization problem, and an application to gradient estimation in stochastic computation graphs. Bio: Chris Maddison is a PhD candidate in the Statistical Machine Learning Group in the Department of Statistics at the University of Oxford. He is an Open Philanthropy AI Fellow and spends two days a week as a Research Scientist at DeepMind. His research is broadly focused on the development of numerical methods for deep learning and machine learning. He has worked on methods for variational inference, numerical optimization, and Monte Carlo estimation with a specific focus on those that might work at scale with few assumptions. Chris received his MSc. from the University of Toronto. He received a NeurIPS Best Paper Award in 2014, and was one of the founding members of the AlphaGo project.

1 0