- talks - lists.cs.princeton.edu

Jordan Fix will present his Pre-FPO on Monday, November 7th, 2016 at 4pm in CS 401
by Nicki Gotsis 07 Nov '16

07 Nov '16

Jordan Fix will present his Pre-FPO on Monday, November 7th, 2016 at 4pm in CS 401. The members of his committee are: Advisor: David August Non-readers: David Wentzlaff, Margaret Martonosi Readers: Andrew Appel, David Callahan (Facebook) Everyone is invited to attend his talk. Abstract: Speculation with transactional memory (TM) systems helps programmers and compilers produce profitable thread-level parallel programs. Prior work shows that supporting transactions that span multiple threads, rather than requiring transactions be contained within a single thread, enables new types of speculative parallelization techniques for both programmers and parallelizing compilers. The only prior TM systems with this multithreaded transactional (MTX) support are software-based TM (STM) systems. Unfortunately, these systems are notorious for their high overheads when validating speculative memory operations, which often make otherwise good parallelization unprofitable. Thus, parallelized programs using these prior STM systems with MTX support were forced to overcome this problem through significant manual effort by the programmer to optimize away most of this speculation validation. Unfortunately, compiler technology and static analyses have not proven strong enough to relieve the programmer of this burden. This thesis presents the first complete design and implementation of a hardware TM (HTM) system with MTX support. This system provides low overhead speculation validation, enabling the aforementioned new types of speculative parallelization techniques to achieve good performance even with high amounts of speculation validation. Profitable parallelization of complex programs can be achieved even with maximal speculation validation of every load and store inside transactions of tens to hundreds of millions of instructions, thus making parallelization less laborious and more feasible for both programmers and compilers. In addition to supporting MTXs, transactions in this system are more resilient than in many other prior works. Transactions avoid false misspeculation due to branch misprediction; provide for large read and write sets that commit in a lazy fashion; and allow for context switches (and thread migration) due to common operations such as preemption or virtual memory management. This allows the system to accommodate the large and long running transactions that are needed to parallelize complex programs. Across 6 SPEC benchmarks a geomean speedup of 2.11X over sequential execution is achieved on a multicore machine with 4 cores, while increasing energy usage by 10%.

1 1

Colloquium Speaker Adam Kalai, today, 12:30pm
by Nicole E. Wagenblast 07 Nov '16

07 Nov '16

Colloquium Speaker Adam Kalai, Microsoft Research Monday, November 7, 2016 - 12:30pm Computer Science 105 Meta-unsupervised-learning: a principled approach to unsupervised learning Unsupervised Learning and exploratory data analysis are among the most important and yet murkiest areas within machine learning. Debates rage even about how to choose which objective function to optimize. We introduce a principled data-driven approach: “meta-unsupervised-learning” using a collection of related or unrelated learning problems. We present simple agnostic models and algorithms illustrating how the meta approach circumvents impossibility results for novel "meta" problems such as meta-clustering, meta-outlier-removal, meta-feature-selection, and meta-embedding. We also present empirical results showing how the meta approach improves over standard techniques for problems such as outlier removal and choosing a clustering algorithm and a number of clusters. We also train an unsupervised neural network that learns from prior supervised classification problems drawn from learning problems at openml.org. Joint work with Vikas Garg from MIT Adam Tauman Kalai received his BA from Harvard, and MA and PhD under the supervision of Avrim Blum from CMU. After an NSF postdoctoral fellowship at M.I.T. with Santosh Vempala, he served as an assistant professor at the Toyota Technological institute at Chicago and then at Georgia Tech. He is now a Principal Researcher at Microsoft Research New England. His honors include an NSF CAREER award and an Alfred P. Sloan fellowship. His research focuses on machine learning, human computation, and algorithms.

1 0

Colloquium Speaker Adam Kalai, Monday Nov 7, 12:30pm- reminder
by Nicole E. Wagenblast 06 Nov '16

06 Nov '16

Colloquium Speaker Adam Kalai, Microsoft Research Monday, November 7, 2016 - 12:30pm Computer Science 105 Meta-unsupervised-learning: a principled approach to unsupervised learning Unsupervised Learning and exploratory data analysis are among the most important and yet murkiest areas within machine learning. Debates rage even about how to choose which objective function to optimize. We introduce a principled data-driven approach: “meta-unsupervised-learning” using a collection of related or unrelated learning problems. We present simple agnostic models and algorithms illustrating how the meta approach circumvents impossibility results for novel "meta" problems such as meta-clustering, meta-outlier-removal, meta-feature-selection, and meta-embedding. We also present empirical results showing how the meta approach improves over standard techniques for problems such as outlier removal and choosing a clustering algorithm and a number of clusters. We also train an unsupervised neural network that learns from prior supervised classification problems drawn from learning problems at openml.org. Joint work with Vikas Garg from MIT Adam Tauman Kalai received his BA from Harvard, and MA and PhD under the supervision of Avrim Blum from CMU. After an NSF postdoctoral fellowship at M.I.T. with Santosh Vempala, he served as an assistant professor at the Toyota Technological institute at Chicago and then at Georgia Tech. He is now a Principal Researcher at Microsoft Research New England. His honors include an NSF CAREER award and an Alfred P. Sloan fellowship. His research focuses on machine learning, human computation, and algorithms.

1 0

Colloquium Speaker Adam Kalai, Monday Nov 7, 12:30pm
by Nicole E. Wagenblast 01 Nov '16

01 Nov '16

Colloquium Speaker Adam Kalai, Microsoft Research Monday, November 7, 2016 - 12:30pm Computer Science 105 Meta-unsupervised-learning: a principled approach to unsupervised learning Unsupervised Learning and exploratory data analysis are among the most important and yet murkiest areas within machine learning. Debates rage even about how to choose which objective function to optimize. We introduce a principled data-driven approach: “meta-unsupervised-learning” using a collection of related or unrelated learning problems. We present simple agnostic models and algorithms illustrating how the meta approach circumvents impossibility results for novel "meta" problems such as meta-clustering, meta-outlier-removal, meta-feature-selection, and meta-embedding. We also present empirical results showing how the meta approach improves over standard techniques for problems such as outlier removal and choosing a clustering algorithm and a number of clusters. We also train an unsupervised neural network that learns from prior supervised classification problems drawn from learning problems at openml.org. Joint work with Vikas Garg from MIT Adam Tauman Kalai received his BA from Harvard, and MA and PhD under the supervision of Avrim Blum from CMU. After an NSF postdoctoral fellowship at M.I.T. with Santosh Vempala, he served as an assistant professor at the Toyota Technological institute at Chicago and then at Georgia Tech. He is now a Principal Researcher at Microsoft Research New England. His honors include an NSF CAREER award and an Alfred P. Sloan fellowship. His research focuses on machine learning, human computation, and algorithms.

1 0

Rajesh Ranganath will present his Pre-FPO on Monday, October 31, 2016 at 11:15am in CS 401.
by Nicki Gotsis 28 Oct '16

28 Oct '16

Rajesh Ranganath will present his Pre-FPO on Monday, October 31, 2016 at 11:15am in CS 401. The members of his committee are as follows: David Blei (adviser), Sanjeev Arora, Barbara Englehardt, and Peter Orbanz (Columbia Univ.) Title and Abstract follow below. Title: Black Box Variational Inference and Deep Generative Models Abstract: To model data we desire to express assumptions, infer hidden structure, make predictions, and simulate new data. Probabilistic generative models provide a common toolkit to meet these challenges. In this talk, I will discuss deep exponential families (DEFs). DEFs are a class of latent variable models built from exponential families inspired by the hidden structure used in deep neural networks. We show results on text, and we show how to compose DEFs to build a model for pairwise recommendations. Key to working with probabilistic generative models is computing the posterior: a typically tedious task. In the second half of the talk, I will present black box variational inference, a method to approximate the posterior with minimal model-specific analysis. This family of generic inference algorithms makes approximating the posterior of deep exponential families and other models possible.

1 0

Colloquium Speaker Jonathan Mayer, today, 12:30pm CONVOCATION ROOM
by Nicole E. Wagenblast 25 Oct '16

25 Oct '16

Colloquium Speaker Dr. Jonathan Mayer, Stanford University Tuesday, October 25, 2016 - 12:30pm Friend Center Convocation Room Constitutional Malware The United States government hacks computer systems, for law enforcement purposes. As encryption becomes more pervasive, and as anonymization tools become easier to use, the government will foreseeably increase its resort to malware. This article provides a comprehensive examination of how federal law regulates law enforcement hacking. The article's first contribution is descriptive. It explains why and how law enforcement agencies hack computer systems, and it offers a framework for examining critical steps in the operation of government malware. The article's next contributions are doctrinal, analyzing the appropriate legal procedures for law enforcement hacking. About half of courts have, surprisingly, concluded that government malware does not necessarily implicate constitutional privacy protections. The article argues that law enforcement hacking constitutes a Fourth Amendment "search," and presumptively requires a warrant and associated protections. The article also makes theoretical contributions. Government malware is the latest flashpoint for electronic surveillance, and it illuminates longstanding scholarly debates about the Fourth Amendment. Law enforcement hacking is a case study in how the three branches of government articulate surveillance regulation, the inherent challenges of rebalancing privacy law to account for new technology, and the relationship between statutory and constitutional privacy protections. Jonathan Mayer is Chief Technologist of the Federal Communications Commission Enforcement Bureau, where he works to protect the security and privacy of America's telecommunications infrastructure. Jonathan is also a Cybersecurity Fellow at Stanford University, where he is completing a Ph.D. in computer science and received a J.D. in 2013.

1 0

Colloquium Speaker- Ruslan Salakhutdinov, today, 12:30pm
by Nicole E. Wagenblast 21 Oct '16

21 Oct '16

Colloquium Speaker Ruslan Salakhutdinov, Carnegie Mellon University Friday, October 21, 2016 - 12:30pm Computer Science 105 Learning Multimodal Deep Models Building intelligent systems that are capable of extracting meaningful representations from high-dimensional data lies at the core of solving many Artificial Intelligence tasks, including visual object recognition, information retrieval, speech perception, and language understanding. In this talk I will first introduce a broad class of deep learning models and show that they can learn useful hierarchical representations from large volumes of high-dimensional data with applications in information retrieval, object recognition, and speech perception. I will next introduce deep models that are capable of extracting a unified representation that fuses together multiple data modalities as well as present the Reverse Annealed Importance Sampling Estimator (RAISE) for evaluating these deep generative models. Finally, I will discuss models that can generate natural language descriptions (captions) of images, as well as generate images from captions using attention mechanism. I will show that on several tasks, including modelling images and text, these models significantly improve upon many of the existing techniques. Ruslan Salakhutdinov received his PhD in computer science from the University of Toronto in 2009. After spending two post-doctoral years at the Massachusetts Institute of Technology Artificial Intelligence Lab, he joined the University of Toronto as an Assistant Professor in the Departments of Statistics and Computer Science. In 2016 he joined the Machine Learning Department at Carnegie Mellon University as an Associate Professor. Ruslan's primary interests lie in deep learning, machine learning, and large-scale optimization. He is an action editor of the Journal of Machine Learning Research and served on the senior programme committee of several learning conferences including NIPS and ICML. He is an Alfred P. Sloan Research Fellow, Microsoft Research Faculty Fellow, Canada Research Chair in Statistical Machine Learning, a recipient of the Early Researcher Award, Google Faculty Award, Nvidia's Pioneers of AI award, and is a Senior Fellow of the Canadian Institute for Advanced Research.

1 0

ACM/IEEE Computer Graphics Film Show - October 20, 2016
by Nicole E. Wagenblast 20 Oct '16

20 Oct '16

The Princeton ACM / IEEE-CS chapters kick off our season of meetings with the annual computer graphics film show, featuring the latest and greatest computer animations direct from the ACM SIGGRAPH conference held this summer. These films were selected for the juried Computer Animation Festival at the conference, to demonstrate advancements in graphics research, highlight creative visual effects, educate with scientific visualizations, and show the many uses of real-time game rendering engines. These graphics were created by large organizations and individuals, professional animators and students, on high-end supercomputers and ordinary personal computers. Come and enjoy our most popular meeting of each year! As in the past few years, we will be co-celebrating Martin Gardner's 102nd birthday by hosting a Celebration of Mind party (see http://www.g4g-com.org) as part of our meeting. Gardner (1914-2010) was the editor of the Mathematical Games column of Scientific American from 1956-1981. Plan to arrive at 7:30pm for refreshments and a special guest speaker, with the graphics video show starting around 8:15pm. All Princeton ACM / IEEE-CS meetings are open to the public. Students and their parents are welcome. There is no admission charge, and refreshments are served. Date: Thursday, October 20, 2016, 8:15 pm (Refreshments, networking, and G4G at 7:30 pm) Place: Friend Center Auditorium, Room 101, Princeton University, Olden & William Streets On-line info: http://PrincetonACM.acm.org

1 0

Sergiy Popovych will present his general exam on Monday, October 24, 3:30pm in CS 301.
by Nicki Gotsis 20 Oct '16

20 Oct '16

Sergiy Popovych will present his general exam on Monday, October 24, 3:30pm in CS 301. The members of his committee are David August (adviser), Nick Feamster, and Arvind Narayanan. His abstract and reading list are below. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. __________________________________ As has been demonstrated time and again, almost all systems can be compromised. Connecting to an external network through a unidirectional gateway physically disallows any outgoing traffic, and thus prevents data theft. Existing unidirectional gateways act as stateless links, only supporting inherently unidirectional applications. In an attempt to support applications that require request/response behavior (e.g. web browsing), Starlight adds a second, bidirectionally connected machine not entrusted with sensitive information, which improves usability. However, with Starlight an attacker can observe user actions on the external machine, which enables him to learn information about the enterprise, as well as mount attacks targeting the user (e.g. phishing) . This work proposes Moonshine, a system that uses content prefetching in order to prevent user-caused leakage, and presents usability and security evaluation of this approach. Books: * Ross J. Anderson. 2008. Security Engineering: A Guide to Building Dependable Distributed Systems (2 ed.). Wiley Publishing. (Chapters 1, 3, 6, 8, 13, 21) * Asaf Shabtai, Yuval Elovici, Lior Rokach. 2012. A Survey of Data Leakage Detection and Prevention Solutions. Springer US. Papers: * R. T. Barker and C. J. Cheese. "The application of data diodes for securely connecting nuclear power plant safety systems to the corporate IT network". System Safety, incorporating the Cyber Security Conference, 7th IET International Conference on, Edinburgh, 2012. * B. S. Jeon and J. C. Na. "A study of cyber security policy in industrial control system using data diodes", 18th International Conference on Advanced Communication Technology (ICACT), Pyeongchang, 2016. * Eric Byres. The air gap: SCADA's enduring security myth. Communications, 2013. * Arthur Gervais, Reza Shokri, Adish Singla, Srdjan Capkun, and Vincent Lenders. "Quantifying Web-Search Privacy". In Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security , 2014. * M. Anderson, C. North, J. Griffin, R. Milner, J. Yesberg and K. Yiu. "Starlight: Interactive Link". Computer Security Applications Conference, 12th Annual, San Diego, CA, 1996. * Shuo Chen, Rui Wang, XiaoFeng Wang, and Kehuan Zhang. "Side-Channel Leaks in Web Applications: A Reality Today, a Challenge Tomorrow". In Proceedings of the 2010 IEEE Symposium on Security and Privacy, 2010. * Bracha Shapira, Yuval Elovici, Adlay Meshiach, and Tsvi Kuflik. "PRAW - A PRivAcy model for the Web" Research Articles. J. Am. Soc. Inf. Sci. Technol, 2005. * Panagiotis Papadopoulos, Antonis Papadogiannakis, Michalis Polychronakis, Apostolis Zarras, Thorsten Holz, and Evangelos P. Markatos. "k-subscription: privacy-preserving microblogging browsing through obfuscation". In Proceedings of the 29th Annual Computer Security Applications Conference, 2013.

1 1

Reminder: Colloquium Speaker- Ruslan Salakhutdinov, Fri Oct 21, 12:30pm
by Nicole E. Wagenblast 20 Oct '16

20 Oct '16

Colloquium Speaker Ruslan Salakhutdinov, Carnegie Mellon University Friday, October 21, 2016 - 12:30pm Computer Science 105 Learning Multimodal Deep Models Building intelligent systems that are capable of extracting meaningful representations from high-dimensional data lies at the core of solving many Artificial Intelligence tasks, including visual object recognition, information retrieval, speech perception, and language understanding. In this talk I will first introduce a broad class of deep learning models and show that they can learn useful hierarchical representations from large volumes of high-dimensional data with applications in information retrieval, object recognition, and speech perception. I will next introduce deep models that are capable of extracting a unified representation that fuses together multiple data modalities as well as present the Reverse Annealed Importance Sampling Estimator (RAISE) for evaluating these deep generative models. Finally, I will discuss models that can generate natural language descriptions (captions) of images, as well as generate images from captions using attention mechanism. I will show that on several tasks, including modelling images and text, these models significantly improve upon many of the existing techniques. Ruslan Salakhutdinov received his PhD in computer science from the University of Toronto in 2009. After spending two post-doctoral years at the Massachusetts Institute of Technology Artificial Intelligence Lab, he joined the University of Toronto as an Assistant Professor in the Departments of Statistics and Computer Science. In 2016 he joined the Machine Learning Department at Carnegie Mellon University as an Associate Professor. Ruslan's primary interests lie in deep learning, machine learning, and large-scale optimization. He is an action editor of the Journal of Machine Learning Research and served on the senior programme committee of several learning conferences including NIPS and ICML. He is an Alfred P. Sloan Research Fellow, Microsoft Research Faculty Fellow, Canada Research Chair in Statistical Machine Learning, a recipient of the Early Researcher Award, Google Faculty Award, Nvidia's Pioneers of AI award, and is a Senior Fellow of the Canadian Institute for Advanced Research.

1 0