Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for April
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Tegan Brennan (University of California, Santa Barbara) - Software Side Channels
Thu, Apr 02, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Tegan Brennan, University of California, Santa Barbara
Talk Title: Software Side Channels
Series: CS Colloquium
Abstract: Side channels in software are a class of information leaks where non-functional side effects of software systems (such as execution time, memory usage or power consumption) can leak information about sensitive data. In this talk, I present my research on a new class of side-channel vulnerabilities: JIT-induced side channels. In contrast to side channels introduced at the source code level, JIT-induced side channels arise at runtime due to the behavior of just-in-time (JIT) compilation. I show the existence of this class of side channels across multiple runtimes, and I demonstrate JIT-induced timing channels in large, open source projects large enough in magnitude to be detected over the public internet. I also present an automated approach to inducing this type of side channel in programs. In evaluating my automated technique, I show that programs classified as side-channel free by four state-of-the-art side channel analysis tools are, in fact, vulnerable to JIT-induced side channels. Finally, I discuss my contributions towards scalable quantification of side-channel vulnerabilities through a caching framework for model-counting queries.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Tegan Brennan is a PhD candidate in Computer Science at the University of California, Santa Barbara. Her research is in software engineering, formal verification and computer security. She has worked extensively on side-channel vulnerabilities in software. Tegan is a recipient of an IGERT Fellowship in Network Science, an NCWIT Collegiate Award Honorable Mention in 2018 and an invited participant of the 2019 Rising Stars workshop. She has also interned twice with Amazon's Automated Reasoning Group.
Host: Chao Wang
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Vatsal Sharan (Stanford) - Modern Perspectives on Classical Learning Problems: Role of Memory and Data Amplification
Mon, Apr 06, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Vatsal Sharan, Stanford University
Talk Title: Modern Perspectives on Classical Learning Problems: Role of Memory and Data Amplification
Series: CS Colloquium
Abstract: This talk will discuss statistical and computation requirements---and how they interact---for three learning setups. In the first part, we inspect the role of memory in learning. We study how the total memory available to a learning algorithm affects the amount of data needed for learning (or optimization), beginning by considering the fundamental problem of linear regression. Next, we examine the role of long-term memory vs. short-term memory for the task of predicting the next observation in a sequence given the past observations. Finally, we explore the statistical requirements for the task of manufacturing more data---namely how to generate a larger set of samples from an unknown distribution. Can "amplifying" a dataset be easier than learning?
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Vatsal Sharan is a Ph.D. student at Stanford, advised by Greg Valiant. He is a part of the Theory group and the Statistical Machine Learning group, and his primary interests are in the theory and practice of machine learning.
Host: Shaddin Dughmi
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Zhiting Hu (Carnegie Mellon University) - Towards Training AI Agents with All Types of Experiences via a Single Algorithm
Tue, Apr 07, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Zhiting Hu, Carnegie Mellon University
Talk Title: Towards Training AI Agents with All Types of Experiences via a Single Algorithm
Series: CS Colloquium
Abstract: Training AI agents for complex problems, such as controllable content generation, requires integrating all sources of experiences (e.g. data, constraints, information from relevant tasks) in learning. Past decades of research has led to a multitude of learning algorithms for dealing with distinct experiences. However, the conventional approach to creating solutions based on such a bewildering marketplace of algorithms demands strong ML expertise and bespoke innovations. This talk will present an alternative approach from a unifying perspective. I will show that many of the popular algorithms in supervised learning, constraint-driven learning, reinforcement learning, etc, indeed share a common succinct formulation and can be reduced to a single algorithm that enables learning with different experiences in the same way. This allows us to create solutions by simply plugging arbitrary experiences in learning, and to systematically enable new learning capabilities by repurposing off-the-shelf algorithms.
Biography: Zhiting Hu is a Ph.D. student in the Machine Learning Department at CMU. He received his B.S. from Peking University. His research interests lie in the broad area of machine learning. His research was recognized with best demo nomination at ACL2019, best paper award at ICLR 2019 DRL workshop, outstanding paper award at ACL2016, and IBM Fellowship.
Host: Yan Liu
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Yuxiong Wang (Carnegie Mellon University) - Learning to Learn More with Less
Thu, Apr 09, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Yuxiong Wang, Carnegie Mellon University
Talk Title: Learning to Learn More with Less
Series: CS Colloquium
Abstract: Understanding how humans and machines learn from few examples remains a fundamental challenge. Humans are remarkably able to grasp a new concept from just few examples, or learn a new skill from just few trials. By contrast, state-of-the-art machine learning techniques typically require thousands of training examples and often break down if the training sample set is too small.
In this talk, I will discuss our efforts towards endowing visual learning systems with few-shot learning ability. Our key insight is that the visual world is well structured and highly predictable in feature, data, and model spaces. Such structures and regularities enable the systems to learn how to learn new tasks rapidly by reusing previous experience. I will focus on two topics to demonstrate how to leverage this idea of learning to learn, or meta-learning, to address a broad range of few-shot learning tasks: task-oriented generative modeling and meta-learning in model space. I will also discuss some ongoing work towards building machines that are able to operate in highly dynamic and open environments, making intelligent and independent decisions based on limited information.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Yuxiong Wang is a postdoctoral fellow in the Robotics Institute at Carnegie Mellon University. He received a Ph.D. in robotics from Carnegie Mellon University under the supervision of Martial Hebert in 2018. His research interests lie in computer vision, machine learning, and robotics, with a particular focus on few-shot learning and meta-learning. He has spent time at Facebook AI Research (FAIR), and has collaborated with researchers in other institutions, including NYU, UIUC, UC Berkeley, Cornell University, INRIA (France), and CSIC-UPC (Spain).
Host: Ramakant Nevatia
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Charith Mendis (MIT) - Modernizing Compiler Technology using Machine Learning
Mon, Apr 13, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Charith Mendis, MIT
Talk Title: Modernizing Compiler Technology using Machine Learning
Series: CS Colloquium
Abstract: Compilers are the workhorse that bridge the gap between human readable and machine executable code. The diversity of modern programs, along with the advent of new and complex hardware architectures, has strained the capabilities of current compilers, making development and maintenance of automatic program optimizations in compilers exceedingly challenging. In spite of this, modern compiler optimizations are still hand-crafted using technology that existed decades ago and usually make optimization decisions considering an abstract machine model. It is high time that we modernize our compiler toolchains using more automated decision procedures to make better optimization decisions while reducing the expertise required to build and maintain compiler optimizations.
In this talk, I will show how we can leverage the changes in the computing environment to modernize compiler optimizations, using auto-vectorization (automatic conversion of scalar code into vector code) as an example.
First, I will demonstrate how we can take advantage of modern solvers and computing platforms to perform vectorization. Modern compilers perform vectorization using hand-crafted algorithms, which typically only find local solutions under linear performance models. I present goSLP, which uses integer linear programming to find a globally optimal instruction packing strategy to achieve superior vectorization performance.
Next, I will discuss how to modernize the construction of compiler optimizations by automatically learning the optimization algorithm. I present Vemal, the first end-to-end learned vectorizer which eliminates the need for hand-writing an algorithm. The key is to formulate the optimization problem as a sequential decision making process in which all steps guarantee correctness of the resultant generated code. Not only does Vemal reduce the need for expert design and heuristics, but also it outperforms hand-crafted algorithms, reducing developer effort while increasing performance.
Finally, I will show how we can use data to learn better non-linear performance models, rather than the complex and incorrect hand-crafted models designed by experts, to enhance the decision procedure used in Vemal. I present Ithemal, the first learned cost model for predicting throughput of x86 code. Ithemal more than halves the error-rate of complex analytical models such as Intel's IACA.
Both Vemal and Ithemal achieve state-of-the-art results and pave the way towards developing more automated and modern compiler optimizations with minimal human burden.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Charith Mendis is a final year PhD student in Computer Science and Artificial Intelligence Laboratory at Massachusetts Institute of Technology. His research interests include Compilers, Machine Learning and Program Analysis. He completed his Master's degree at MIT for which he received the William A. Martin Thesis Prize and his bachelor's degree at University of Moratuwa, Sri Lanka for which he received the institute Gold Medal. Charith was the recipient of the best student paper award at IEEE Big Data conference and the best paper award at ML for Systems workshop at ISCA. He has published work at both top programming language venues such as PLDI and OOPSLA as well as at top machine learning venues such as ICML and NeurIPS. Charit's recent work on performance prediction is used at Google as part of their CPU modeling effort.
Host: Mukund Raghothaman
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: TBA
Tue, Apr 14, 2020 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: TBA, TBA
Talk Title: TBA
Series: CS Colloquium
Abstract: TBA
Biography: TBA
Host: Ramesh Govindan
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Hoda Heidari (Cornell University) - Distributive Justice for Machine Learning: An Interdisciplinary Perspective on Defining, Measuring, and Mitigating Algorithmic Unfairness
Thu, Apr 16, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Hoda Heidari, Cornell Universtiy
Talk Title: Distributive Justice for Machine Learning: An Interdisciplinary Perspective on Defining, Measuring, and Mitigating Algorithmic Unfairness
Series: CS Colloquium
Abstract: Automated decision-making tools are increasingly in charge of making high-stakes decisions for people-”in areas such as education, credit lending, criminal justice, and beyond. These tools can exhibit and exacerbate certain undesirable biases and disparately harm already disadvantaged and marginalized groups and individuals. In this talk, I will illustrate how we can bring together tools and methods from computer science, economics, and political philosophy to define, measure, and mitigate algorithmic unfairness in a principled manner. In particular, I will address two key questions:
- Given the appropriate notion of harm/benefit, how should we measure and bound unfairness? Existing notions of fairness focus on defining conditions of fairness, but they do not offer a proper measure of unfairness. In practice, however, designers often need to select the least unfair model among a feasible set of unfair alternatives. I present (income) inequality indices from economics as a unifying framework for measuring unfairness--both at the individual- and group-level. I propose the use of cardinal social welfare functions as an alternative measure of fairness behind a veil of ignorance and a computationally tractable method for bounding inequality.
- Given a specific decision-making context, how should we define fairness as the equality of some notion of harm/benefit across socially salient groups? First, I will offer a framework to think about this question normatively. I map the recently proposed notions of group-fairness to models of equality of opportunity. This mapping provides a unifying framework for understanding these notions, and importantly, allows us to spell out the moral assumptions underlying each one of them. Second, I give a descriptive answer to the question of "fairness as equality of what?". I mention a series of adaptive human-subject experiments we recently conducted to understand which existing notion best captures laypeople's perception of fairness.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Hoda Heidari is currently a Postdoctoral Associate at the Department of Computer Science at Cornell University, where she collaborates with Professors Jon Kleinberg, Karen Levy, and Solon Barocas through the AIPP (Artificial Intelligence, Policy, and Practice) initiative. Hoda's research is broadly concerned with the societal aspects of Artificial Intelligence, and in particular, the issues of unfairness and discrimination for Machine Learning. She utilizes tools and methods from Computer Science (Algorithms, AI, and ML) and Social Sciences (Economics and Political Philosophy) to quantify and mitigate the inequalities that arise when socially consequential decisions are automated.
Host: Aleksandra Korolova and Bistra Dilkina
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Seminar will be exclusively online (no in-room presentation) - CS Colloquium: Mathew Monfort (MIT) - Towards Understanding Moments in Time
Mon, Apr 20, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Mathew Monfort, MIT
Talk Title: Towards Understanding Moments in Time
Series: CS Colloquium
Abstract: When people observe events they are able to abstract key information and build concise summaries of what is happening. These summaries include the important contextual and semantic information (what, where, who and how) necessary for the observer to understand the event and how it relates to their current state. With this in mind, the descriptions people generate for videos of different dynamic events can greatly improve our understanding of the key information of interest for each event and help us learn rich representations that we can apply to a number of different tasks. Going a step further, taking sequences of events into consideration allows us to build an understanding of how observations can be abstracted into contextually meaningful descriptions useful for understanding the relationships between each event and higher-level goals. In this talk I will provide an overview of recent work in the area of video understanding and highlight details of how we can learn, and utilize, detailed video representations for improving our understanding of moments in time.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Mathew Monfort is a Research Scientist at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). He received a PhD. in computer science from the University of Illinois at Chicago in 2016, a M.S. in Computer Science from Florida State University in 2011 and a B.A. in Mathematics from Franklin and Marshall College in 2009. His research has included approached on applying machine learning methods to autonomous driving, inverse planning, video understanding and areas related to learning from human behavior.
Host: Ramakant Nevatia
Location: Seminar will be exclusively online (no in-room presentation)
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
