March 2019 - talks - lists.cs.princeton.edu

Colloquium Speaker-Jason Lee TODAY at 12:30pm
by Emily C. Lawrence 11 Mar '19

11 Mar '19

Colloquium Speaker Jason Lee from University of Southern California Monday, March 11 - 12:30pm Computer Science - Room 105 Host: Elad Hazan [ https://www.cs.princeton.edu/events/25822 | https://www.cs.princeton.edu/events/25822 ] On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization Deep Learning has had phenomenal empirical successes in many domains including computer vision, natural language processing, and speech recognition. To consolidate and boost the empirical success, we need to develop a more systematic and deeper understanding of the elusive principles of deep learning. In this talk, I will provide analysis of several elements of deep learning including non-convex optimization, overparametrization, and generalization error. First, we show that gradient descent and many other algorithms are guaranteed to converge to a local minimizer of the loss. For several interesting problems including the matrix completion problem, this guarantees that we converge to a global minimum. Then we will show that gradient descent converges to a global minimizer for deep overparametrized networks. Finally, we analyze the generalization error by showing that a subtle combination of SGD, logistic loss, and architecture combine to promote large margin classifiers, which are guaranteed to have low generalization error. Together, these results show that on overparametrized deep networks SGD finds solution of both low train and test error. Bio: Jason Lee is an assistant professor in Data Sciences and Operations at the University of Southern California. Prior to that, he was a postdoctoral researcher at UC Berkeley working with Michael Jordan. Jason received his PhD at Stanford University advised by Trevor Hastie and Jonathan Taylor. His research interests are in statistics, machine learning, and optimization. Lately, he has worked on the foundations of deep learning, non-convex optimization algorithm, and adaptive statistical inference. He has received a Sloan Research Fellowship in 2019 and NIPS Best Student Paper Award for his work.

1 0

Reminder: Colloquium Speaker-Jason Lee tomorrow at 12:30pm
by Emily C. Lawrence 10 Mar '19

10 Mar '19

Colloquium Speaker Jason Lee from University of Southern California Monday, March 11 - 12:30pm Computer Science - Room 105 Host: Elad Hazan [ https://www.cs.princeton.edu/events/25822 | https://www.cs.princeton.edu/events/25822 ] On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization Deep Learning has had phenomenal empirical successes in many domains including computer vision, natural language processing, and speech recognition. To consolidate and boost the empirical success, we need to develop a more systematic and deeper understanding of the elusive principles of deep learning. In this talk, I will provide analysis of several elements of deep learning including non-convex optimization, overparametrization, and generalization error. First, we show that gradient descent and many other algorithms are guaranteed to converge to a local minimizer of the loss. For several interesting problems including the matrix completion problem, this guarantees that we converge to a global minimum. Then we will show that gradient descent converges to a global minimizer for deep overparametrized networks. Finally, we analyze the generalization error by showing that a subtle combination of SGD, logistic loss, and architecture combine to promote large margin classifiers, which are guaranteed to have low generalization error. Together, these results show that on overparametrized deep networks SGD finds solution of both low train and test error. Bio: Jason Lee is an assistant professor in Data Sciences and Operations at the University of Southern California. Prior to that, he was a postdoctoral researcher at UC Berkeley working with Michael Jordan. Jason received his PhD at Stanford University advised by Trevor Hastie and Jonathan Taylor. His research interests are in statistics, machine learning, and optimization. Lately, he has worked on the foundations of deep learning, non-convex optimization algorithm, and adaptive statistical inference. He has received a Sloan Research Fellowship in 2019 and NIPS Best Student Paper Award for his work.

1 0

Fwd: ACM Princeton Chapter - Mar. 14 meeting and upcoming March events
by Jennifer Rexford 07 Mar '19

07 Mar '19

> > From: Dennis Mancl <dmancl(a)ACM.ORG> > Subject: ACM Princeton Chapter - Mar. 14 meeting and upcoming March events > Date: March 7, 2019 at 2:48:34 PM EST > To: PRINCETON-ACM-NOTICE(a)LISTSERV.ACM.ORG > Reply-To: Dennis Mancl <dmancl(a)ACM.ORG> > > Upcoming Princeton ACM / IEEE Computer Society Meetings and Events > > Thursday Mar. 14 - "Bias in Face Recognition: Definitions, Magnitude, Mitigation," Patrick Grother, National Institute of Standards and Techology > > Friday Mar. 22 - IT Professional Conference at TCF (at The College of New Jersey) -- see http://PrincetonACM.acm.org/tcfpro for list of speakers and registration information > > ----- > > PRINCETON ACM / IEEE-CS CHAPTERS > MARCH 2019 JOINT MEETING > > Bias in Face Recognition: Definitions, Magnitude, Mitigation > > As the poster-child of the AI revolution, face recognition has undergone a period of rapid improvement to the point that individuals can be readily identified when a single photograph is searched against a database containing tens of millions of faces. This task is non-trivial. Algorithms are fully proprietary and not commoditized as some are far more accurate than others. Yet all fail more or less gracefully when fed poor photographs, when a subject changes appearance with age, and on images for certain sub-populations. This latter aspect constitutes an existential threat to use of face recognition as end users, system owners, algorithm developers, and regulators struggle to understand the problem, its magnitude and impact. > > The talk will give an overview of face recognition applications and technology, then describe how and where biometric systems fail and the range of demographic influences. The talk will review recent publications, and give a preview of an upcoming government report on demographic effects in face recognition. The talk will define metrics, give extensive empirical results for contemporary leading commercial algorithms, make conjectures to explain the observations, and discuss impact and possible mitigation. > > Patrick Grother is a scientist at the National Institute of Standards and Technology responsible for biometric algorithm evaluation, and biometric performance testing standardization. He leads evaluations of face and iris recognition algorithms at NIST. Patrick has worked in image processing, pattern recognition, optics and biometrics. > > Date: Thursday March 14, 2019, 8:00pm > (refreshments at 7:30pm) > Place: Princeton University Computer Science Building > Small Auditorium, Room CS 105 > 35 Olden Street, Princeton NJ > Information: Dennis Mancl (908) 285-1066 > On-line meeting notice: http://PrincetonACM.acm.org/meetings/mtg1903.pdf > > All ACM / IEEE-CS meetings are open to the public. Students and their parents are welcome. There is no admission charge. > > A pre-meeting dinner is held at 6:00 p.m. at Ruby Tuesday's Restaurant on Route 1. Please send email to princetonacm(a)gmail.org in advance if you plan to attend the dinner. > > ===================== > > Future Princeton ACM / IEEE Computer Society Meetings > > NOTE: The location for all of our regular monthly meetings -- Computer Science Building at Princeton University. All monthly meetings are at 8pm. > > Saturday Mar. 16 - IEEE Integrated STEM Education Conference (at McDonnell Hall, Princeton University) > http://ewh.ieee.org/conf/stem > > Friday Mar. 22 - IT Professional Conference at TCF (at The College of New Jersey) > ** Registration is now open ** > $135 (Professionals), $35 (students and senior citizens) > http://PrincetonACM.acm.org/tcfpro > > Saturday Mar. 23 - Trenton Computer Festival (at The College of New Jersey) > http://www.tcf-nj.org > > Thursday Apr. 11 - "Natural Language Processing at the National Library of Medicine," Dina Demner-Fushman, National Library of Medicine > http://PrincetonACM.acm.org/meetings/mtg1904.pdf > (NOTE: this meeting is the SECOND Thursday of April) > > Thursday May 16 - Annual Dinner Meeting (at Grafton House, Hamilton Township) > > June TBA - Annual Elections and Planning Meeting

1 0

Unsolved Data Problems: Wednesday, March 13 at 4:30
by Emily C. Lawrence 07 Mar '19

07 Mar '19

Wednesday, March 13 4:30 – 5:30 pm Computer Science, Rm 105 [ https://cdh.princeton.edu/events/2019/03/unsolved-data-problems/ | https://cdh.princeton.edu/events/2019/03/unsolved-data-problems/ ] Unsolved Data Problems will introduce faculty and students in the computer and data sciences to the untapped research possibilities inherent in humanities data. A panel of Princeton faculty - Meredith Martin (English), Marina Rustow (History and Near Eastern Studies) and Dan Trueman (Music) - will discuss some of Princeton’s landmark digital humanities projects, and the challenges they’ve faced when transforming historical, multilingual and experimental source material into data and code. Projects discussed include the Princeton Prosody Archive, the Princeton Geniza Lab, and bitKlavier . Jennifer Rexford and Brian Kernighan (Computer Science) will moderate the panel. Help discover innovative algorithmic solutions to these unsolved computational problems. This panel will be of particular interest to researchers working in the fields of: computer vision, natural language processing, machine learning, and audio/music engineering. This event is collaboratively organized by the Center for Digital Humanities, the Department of Computer Science and the Center for Statistics and Machine Learning.

1 0

Colloquium Speaker-Jason Lee, Monday, March 11 at 12:30pm
by Emily C. Lawrence 06 Mar '19

06 Mar '19

Colloquium Speaker Jason Lee from University of Southern California Monday, March 11 - 12:30pm Computer Science - Room 105 Host: Elad Hazan [ https://www.cs.princeton.edu/events/25822 | https://www.cs.princeton.edu/events/25822 ] On the Foundations of Deep Learning: SGD, Overparametrization , and Generalization Deep Learning has had phenomenal empirical successes in many domains including computer vision, natural language processing, and speech recognition. To consolidate and boost the empirical success, we need to develop a more systematic and deeper understanding of the elusive principles of deep learning. In this talk, I will provide analysis of several elements of deep learning including non-convex optimization, overparametrization , and generalization error. First, we show that gradient descent and many other algorithms are guaranteed to converge to a local minimizer of the loss. For several interesting problems including the matrix completion problem, this guarantees that we converge to a global minimum. Then we will show that gradient descent converges to a global minimizer for deep overparametrized networks. Finally, we analyze the generalization error by showing that a subtle combination of SGD, logistic loss, and architecture combine to promote large margin classifiers, which are guaranteed to have low generalization error. Together, these results show that on overparametrized deep networks SGD finds solution of both low train and test error. Bio: Jason Lee is an assistant professor in Data Sciences and Operations at the University of Southern California. Prior to that, he was a postdoctoral researcher at UC Berkeley working with Michael Jordan. Jason received his PhD at Stanford University advised by Trevor Hastie and Jonathan Taylor. His research interests are in statistics, machine learning, and optimization. Lately, he has worked on the foundations of deep learning, non-convex optimization algorithm, and adaptive statistical inference. He has received a Sloan Research Fellowship in 2019 and NIPS Best Student Paper Award for his work.

1 0

Marcela Melara will present her Pre FPO "Novel Systems for Intra-Process Least Privilege and Isolation" on Monday, March 11, 2019 at 2pm in CS 105
by Nicki Mahler 05 Mar '19

05 Mar '19

Marcela Melara will present her Pre FPO on Monday, March 11, 2019 at 2pm in CS 105. The members of her committee are as follows: Michael Freedman (adviser), Mic Bowman (Intel Labs), Amit Levy, Wyatt Lloyd, and Prateek Mittal All are welcome to attend. The talk title and abstract follow below. Title: Novel Systems for Intra-Process Least Privilege and Isolation Abstract: Third-party libraries reduce software development costs and effort. Designed for flexible reuse, libraries implement a small set of features, allowing developers to build applications by combining libraries that provide the desired functionality. However, third-party code also poses a great risk: because the source code is rarely inspected or even accessible by the application developer, bugs or vulnerabilities that can leak sensitive data may go unnoticed. Yet, existing data protection tools are insufficient because they do not enforce least privilege, restricting each library’s access to only those data it needs for its functionality. Prior proposals have addressed this issue with two main approaches: (1) running application components in separate processes for strong isolation, or (2) tracking individual data objects throughout the application to prevent unprivileged components from disclosing sensitive information. However, these approaches see limited adoption because they introduce significant integration complexity and performance overhead. This thesis proposes two systems for enforcing intra-process least privilege: both strongly isolate data within a single process address space while restricting access at the granularity of individual library functions. We first present Pyronia, a privilege separation system for language runtimes that targets IoT device applications. To protect sensitive OS resources and in-memory data objects, Pyronia combines three access control techniques: system call interposition, stack inspection, and memory protection domains. Developers then specify data access rules only for directly imported third-party functions in a central policy. We next present Griffin, a memory access control system for Intel SGX cloud applications. Intel SGX enables developers to run sensitive code inside an enclave, a hardware-protected memory region within an application’s address space. However, in practice, developers often include untrusted third-party libraries in the enclave, giving them unfettered access to all in-enclave data. Griffin leverages Intel memory protection keys (MPK) to partition an enclave and assign per-compartment access rules. As part of their SGX policy, developers declare sensitive data objects and access privileges for in-enclave functions. Griffin then automatically confines these data objects in MPK compartments. Pyronia and Griffin demonstrate the effectiveness of intra-process least privilege, reducing the performance impact on applications, and easing integration efforts for developers.

1 0

TODAY in B205 E-Quad - R. Srikant, University of Illinois at Urbana-Champaign
by Emily Lawrence 05 Mar '19

05 Mar '19

EE SEMINAR SERIES Speaker: R. Srikant, University of Illinois at Urbana-Champaign Title: Queues and Qs Day: Tuesday, March 5, 2019 Time: 4:30 pm Room: B205 Engineering Quadrangle Host: Prof. H. Vincent Poor Data Science relies on scalable resource allocation algorithms to operate data centers consisting of massive numbers of servers, as well as machine learning algorithms to extract information from data. In the first part of the talk, we will consider a resource allocation problem that arises in data centers and show that there exist low-complexity algorithms which use queue-length information to maximize throughput while ensuring that the packet delays do not scale with the size of the data center. Our result resolved a long-standing open conjecture at the intersection of probability, algorithms, and networks. In the second part of the talk, we will consider a reinforcement learning algorithm to estimate the Q-function of a given policy. We will present the first comprehensive finite-time performance bounds for the algorithm, which can potentially be used to characterize its sample complexity. The first part is joint work with Siva Theja Maguluri and the second part is joint work with Lei Ying. Bio: R. Srikant is the Fredric G. and Elizabeth H. Nearing Endowed Professor of Electrical and Computer Engineering and the Coordinated Science Lab at the University of Illinois at Urbana-Champaign. His research interests are in the areas of applied probability and stochastic networks, with applications to machine learning, cloud computing, and communication networks. He is the recipient of the 2019 IEEE Koji Kobayashi Computers and Communications Award and the 2015 IEEE INFOCOM Achievement Award. He has also received several Best Paper awards, including the 2017 Applied Probability Society Best Publication Award and the 2015 IEEE INFOCOM Best Paper Award. He was the Editor-in-Chief of the IEEE/ACM Transactions on Networking from 2013-2017. This seminar is supported with funds from the Korhammer Lecture Series

1 0

Colloquium Speaker-Tianqi Chen, TODAY at 12:30pm
by Emily C. Lawrence 05 Mar '19

05 Mar '19

Colloquium Speaker Tianqi Chen from the University of Washington Tuesday, March 5 - 12:30pm Computer Science - Room 105 Host: Ryan Adams [ http://www.cs.princeton.edu/events/25820 | http://www.cs.princeton.edu/events/25820 ] Learning-based Learning Systems Data, models, and computing are the three pillars that enable machine learning to solve real-world problems at scale. Making progress on these three domains requires not only disruptive algorithmic advances but also systems innovations that can continue to squeeze more efficiency out of modern hardware. Learning systems are in the center of every intelligent application nowadays. However, the ever-growing demand for applications and hardware specialization creates a huge engineering burden for these systems, most of which rely on heuristics or manual optimization. In this talk, I will present a new approach that uses machine learning to automate system optimizations. I will describe our approach in the context of deep learning deployment problem. I will first discuss how to design invariant representations that can lead to transferable statistical cost models, and apply these representations to optimize tensor programs used in deep learning applications. I will then describe the system improvements we made to enable diverse hardware backends . TVM, our end-to-end system, delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned deep learning frameworks. Finally, I will discuss how to generalize our approach to do full-stack optimization of the model, system, hardware jointly, and how to build systems to support life-long evolution of intelligent applications. Bio: Tianqi Chen is a Ph.D. candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, working with Carlos Guestrin on the intersection of machine learning and systems. He has created three major learning systems that are widely adopted: XGBoost , TVM, and MXNet (co-creator). He is a recipient of the Google Ph.D. Fellowship in Machine Learning.

1 0

Reminder: Colloquium Speaker-Tianqi Chen, tomorrow at 12:30pm
by Emily C. Lawrence 04 Mar '19

04 Mar '19

Colloquium Speaker Tianqi Chen from the University of Washington Tuesday, March 5 - 12:30pm Computer Science - Room 105 Host: Ryan Adams [ http://www.cs.princeton.edu/events/25820 | http://www.cs.princeton.edu/events/25820 ] Learning-based Learning Systems Data, models, and computing are the three pillars that enable machine learning to solve real-world problems at scale. Making progress on these three domains requires not only disruptive algorithmic advances but also systems innovations that can continue to squeeze more efficiency out of modern hardware. Learning systems are in the center of every intelligent application nowadays. However, the ever-growing demand for applications and hardware specialization creates a huge engineering burden for these systems, most of which rely on heuristics or manual optimization. In this talk, I will present a new approach that uses machine learning to automate system optimizations. I will describe our approach in the context of deep learning deployment problem. I will first discuss how to design invariant representations that can lead to transferable statistical cost models, and apply these representations to optimize tensor programs used in deep learning applications. I will then describe the system improvements we made to enable diverse hardware backends . TVM, our end-to-end system, delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned deep learning frameworks. Finally, I will discuss how to generalize our approach to do full-stack optimization of the model, system, hardware jointly, and how to build systems to support life-long evolution of intelligent applications. Bio: Tianqi Chen is a Ph.D. candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, working with Carlos Guestrin on the intersection of machine learning and systems. He has created three major learning systems that are widely adopted: XGBoost , TVM, and MXNet (co-creator). He is a recipient of the Google Ph.D. Fellowship in Machine Learning.

1 0

EE and CS Speaker-Stephen Tu, 3/7 at 12:30pm
by Emily C. Lawrence 01 Mar '19

01 Mar '19

EE and CS Speaker Stephen Tu from University of California, Berkeley Thursday, March 7 - 12:30pm Computer Science - Room 105 Hosts: Ryan Adams, CS and Yuxin Chen, EE [ https://www.cs.princeton.edu/events/25824 | https://www.cs.princeton.edu/events/25824 ] Safe and Reliable Reinforcement Learning for Continuous Control Many autonomous systems such as self-driving cars, unmanned aerial vehicles, and personalized robotic assistants are inherently complex. In order to deal with this complexity, practitioners are increasingly turning towards data-driven learning techniques such as reinforcement learning (RL) for designing sophisticated control policies. However, there are currently two fundamental issues that limit the widespread deployment RL: sample inefficiency and the lack of formal safety guarantees. In this talk, I will propose solutions for both these issues in the context of continuous control tasks. In particular, I will show that in the widely applicable setting where the dynamics are linear, model-based algorithms which exploit this structure are substantially more sample efficient than model-free algorithms, such as the widely used policy gradient method. Furthermore, I will describe a new model-based algorithm which comes with provable safety guarantees and is computationally efficient, relying only on convex programming. I will conclude the talk by discussing the next steps towards safe and reliable deployment of reinforcement learning. Bio: Stephen Tu is a PhD student in Electrical Engineering and Computer Sciences at the University of California, Berkeley advised by Benjamin Recht . His research interests are in machine learning, control theory, optimization, and statistics. Recently, he has focused on providing safety and performance guarantees for reinforcement learning algorithms in continuous settings. He is supported by a Google PhD fellowship in machine learning.

1 0