Select a calendar:
Filter October Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for October
-
PhD Defense - Anil Ramakrishna
Wed, Oct 02, 2019 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Anil Ramakrishna
Committee:
Shri Narayanan (chair)
Aiichiro Nakano
Morteza Dehghani
Location: RTH 320
Time: October 2nd, 12 pm.
Title: Computational Models for Multidimensional Annotations of Affect
Abstract: Affect is an integral aspect of human psychology, it acts as a regulator for all our interactions with external stimuli. Affect includes several related concepts such as sentiment, emotion as well as as higher order constructs such as mood and humor. By its nature, it is highly subjective, with different stimuli leading to different responses in people due to varying personal and cultural artifacts. For example, a specific image or audio clip may evoke different emotions in people depending on their personality. Computational modeling of affective dimensions is an important problem in Artificial Intelligence (AI). It covers a variety of tasks such as sentiment analysis, emotion recognition and opinion mining, which often involve supervised training of models using a large number of labeled data instances. However, training labels are difficult to obtain due to the inherent subjectivity of these constructs. Typical approaches to obtain the training labels include collecting opinions from expert or naive annotators, followed by a suitable aggregation.
In this dissertation, we will present our contributions towards building computational models for noisy annotations of affect, specifically in the aggregation of multidimensional annotations. We propose latent variable models to capture annotator behaviors using additive Gaussian noise and matrix factorization, leading to more accurate estimates of the underlying ground truth. We then apply the joint matrix factorization model to the task of sentence level estimation of psycholinguistic normatives. Finally, we highlight our ongoing efforts in estimating agreement on multidimensional annotations.
Location: Ronald Tutor Hall of Engineering (RTH) - 320
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
Computer Science & Data Science Progressive Degree Information Session
Wed, Oct 02, 2019 @ 05:00 PM - 06:30 PM
Thomas Lord Department of Computer Science
Workshops & Infosessions
Viterbi Graduate Admissions and the Computer Science Department will be presenting information about the progressive degree program (accelerated BS+MS) on Wednesday, October 2nd at 5pm in RTH-211. If you are a first year, sophomore, or junior interested in applying for the progressive degree program please join us! Advisors will be available to answer your questions after the presentations.
PDP Fall 2019 Application Deadlines:
Early Application Deadline: Friday September 27, 2019
Final Application Deadline: Wednesday December 18, 2019
http://viterbiundergrad.usc.edu/future/pdp/Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: Undergrad
Contact: Ryan Rozan
-
Theory Lunch
Thu, Oct 10, 2019 @ 12:15 PM - 02:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Grigory Yaroslavtsev, Assistant Professor of Statistics at Indiana University
Talk Title: Advances in Hierarchical Clustering of Vector Data
Abstract: Compared to the highly successful flat clustering (e.g. k-means), despite its important role and applications in data analysis, hierarchical clustering has been lacking in rigorous algorithmic studies until late due to absence of rigorous objectives. Since 2016, a sequence of works has emerged and gave novel algorithms for this problem in the general metric setting. This was enabled by a breakthrough by Dasgupta, who introduced a formal objective into the study of hierarchical clustering.
In this talk I will give an overview of our recent progress on models and scalable algorithms for hierarchical clustering applicable specifically to high-dimensional vector data, including embedding vectors arising from deep learning. I will first discuss various linkage-based algorithms (single-linkage, average-linkage) and their formal properties with respect to various objectives. I will then introduce a new projection-based approximation algorithm for vector data. The talk will be self-contained and does not assume prior knowledge of clustering methods.
Host: Shaddin Dughmi
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Cherie Carter
-
Computer Science General Faculty Meeting
Wed, Oct 16, 2019 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Michelson Center for Convergent Bioscience (MCB) - 101
Audiences: Invited Faculty Only
Contact: Assistant to CS chair
-
CAIS Seminar: Kayla de la Haye (University of Southern California) - Promoting Healthy Eating through Local and Global Social Networks
Wed, Oct 16, 2019 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Kayla de la Haye, University of Southern California
Talk Title: Promoting Healthy Eating through Local and Global Social Networks
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Poor diets are a major cause of common 'lifestyle' diseases such as obesity, diabetes, and heart disease. Although eating is often conceptualized as an individual behavior, the evidence shows that it is shaped by social and environmental forces that are insufficiently addressed in many interventions. This talk describes how complex social networks of family, friends, peers, and community stakeholders influence what people eat, and how interventions and policy can target "social architecture" to promote healthy nutrition. I emphasize the important role of innovative network and data science methods, big data, and transdisciplinary team science to advance this work.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. de la Haye works to promote health and prevent disease by applying social network analysis and systems science. Her research, funded by the NIH, the NSF, and the DoD, targets family and community social networks to promote healthy eating and prevent childhood obesity, and to understand the role of social networks in group problem solving in families, teams, and coalitions. She is Treasurer of the International Network of Social Network Analysis (INSNA), and in 2018, she received the INSNA Freeman Award for significant contributions to the study of social structure.
URL: www.kayladelahaye.com
Twitter: @kayladelahaye
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Ahmed Eldawy (University of California, Riverside) - Interactive Data Exploration as a Service
Tue, Oct 22, 2019 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ahmed Eldawy, University of California, Riverside
Talk Title: Interactive Data Exploration as a Service
Series: Computer Science Colloquium
Abstract: Recently, there has been a tremendous growth in data collection from various sources such as satellites, IoT sensors, smartphones, autonomous cars, and others. At the same time, there is a move for open data led by governments, non-profit organizations, and industry which makes hundreds of thousands of datasets publicly available. This abundance of publicly available open data led to the new data revolution where everyone is interested in exploring this data to look for interesting patterns and innovative findings. While computer scientists and data scientists know how to process this data, no one is out to help citizen scientists, those with little to no knowledge about programming and data management.
This talk describes a new approach to provide citizen scientists with interactive data exploration as a service (IDEAS). The goal is to allow anyone to start exploring those publicly available datasets without a costly process of installing and learning data processing tools or even downloading the datasets of interest. This system will act as an ice breaker that will help engaging more citizen scientists into the field of data science. The main challenge is how to provide real-time processing for hundreds of thousands and petabytes of datasets through a simple interface. This talk describes three modules related to this system, synoptic computation, incremental indexing, and interactive visualization. The synoptic computation module scales up the query processing by providing a real-time approximate answer over small-size synopses of the data such as samples and histograms. The incremental indexing module works in the background and incrementally organizes the data over a cluster of machines to speed up the query processing. Finally, the interactive visualization module presents the results in a visual format which allows the users to inspect the query answers. Preliminary results on the proposed system show that it can bridge the gap between the user requirements for interactivity and the increasing volume of big spatial data.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Ahmed Eldawy is an Assistant Professor of Computer Science at the University of California, Riverside. His research interests lie in the broad area of databases with a focus on big data management and spatial data processing. Ahmed is the main inventor of SpatialHadoop, the most comprehensive open source system for big spatial data management. Ahmed has many collaborators in industrial research labs including Microsoft Research and IBM Watson. He was awarded the Quality Metrics Fellowship in 2016, Doctoral Dissertation Fellowship in 2015, and Best Poster Runner-up award in ICDE 2014. His work is supported by the National Science Foundation (NSF) and the US Department of Agriculture (USDA).
Host: Shahram Ghandeharizadeh
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
PhD Defense - Abdullah Alfarrarjeh
Wed, Oct 23, 2019 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Abdullah Alfarrarjeh
Committee:
Cyrus Shahabi (chair)
Aiichiro Nakano
C.-C. Jay Kuo
Location: PHE 325
Time: October 23rd, 10 am.
Title: Enabling Spatial-Visual Search for Geospatial Image Databases
Abstract:
Due to continuous advances in camera technologies as well as camera-enabled devices (e.g., CCTV, smartphone, vehicle blackbox, and GoPro), urban streets have been documented by massive amounts of images. Moreover, nowadays, images are typically tagged with spatial metadata due to various sensors (e.g., GPS and digital compass) attached to or embedded in cameras. Such images are known as geo-tagged images. The availability of such geographical context of images enables emerging several image-based smart city applications. Developing such smart city applications requires searching for images, among the massive amounts of collected images, especially to be used for training various machine learning algorithms. Thus, there is an immense need for a data management system for geo-tagged images.
Towards this end, it is paramount to build a data management system that organizes the images in structures that enable searching and retrieving the images efficiently and accurately. On one hand, the data management system should overcome the challenge of lacking an accurate spatial representation of legacy images that were collected without spatial metadata, as well as representing the content of an image accurately using an enriched visual descriptor. On the other hand, the system should also enable efficient storage of images utilizing both their spatial and visual properties and thus their retrieval based on spatial-visual queries. To address these challenges we present a system which includes three integrated modules: a) modeling an image spatially by its scene location using a data-centric approach, b) extending the visual representation of an image with the feature set of multiple similar images located in its vicinity, and c) designing index structures that expedite the evaluation of spatial-visual queries.
Location: 325
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
Theory Lunch
Thu, Oct 24, 2019 @ 12:15 PM - 02:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Prithviraj Prabhu, Graduate Students at USC
Talk Title: Google's Recent Attempts in Quantum Supremacy
Abstract: A talk about Goolge' s recent attempts in quantum supremacy and the controversy surrounding it.
Host: Shaddin Dughmi
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Cherie Carter
-
Careers in Data Infosession
Mon, Oct 28, 2019 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science, USC Viterbi School of Engineering
Workshops & Infosessions
Hoa Nguyen, Director of Engineering at Insight, will discuss the growing demand for data scientists and data engineers at companies across the U.S. She'll also provide some tips and strategies for making the transition into the industry. Come learn about a variety of data careers. We will discuss what academic skills transfer to each career type and provide tips on how to bridge the gap between your current skills and your next dream job. All backgrounds are welcome!
RSVP HERELocation: James H. Zumberge Hall Of Science (ZHS) - 159
Audiences: Everyone Is Invited
Contact: Ryan Rozan
-
CS Colloquium: Aditya Grover (Stanford University) - Mitigating Bias in Generative Modeling
Tue, Oct 29, 2019 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Aditya Grover, Stanford University
Talk Title: Mitigating Bias in Generative Modeling
Series: Computer Science Colloquium
Abstract: In the last few years, there has been remarkable progress in deep generative modeling. However, the learned models are noticeably inaccurate w.r.t. to the underlying data distribution, as evident from downstream metrics that compare statistics of interest across the true and generated data samples. This bias in downstream evaluation can be attributed to imperfections in learning ("model bias") or be propagated due to the bias in the training dataset itself ("dataset bias"). In this talk, I will present an importance weighting approach for mitigating both these kinds of biases of generative models. Our approach assumes only 'black-box' sample access to a generative model and is broadly applicable to both likelihood-based and likelihood-free generative models. Empirically, we find that our technique consistently improves standard goodness-of-fit metrics for evaluating the sample quality of state-of-the-art deep generative models, suggesting reduced bias. We demonstrate its utility on representative applications in a) data augmentation and b) model-based policy evaluation using off-policy data. Finally, I will present some recent work extending these ideas to fair data generation in the presence of biased training datasets.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Aditya Grover is a 5th-year Ph.D. candidate in Computer Science at Stanford University advised by Stefano Ermon. His research focuses on probabilistic machine learning, including topics in generative modeling, approximate inference, and deep learning as well as applications in sustainability. His research has been cited widely in academia, deployed into production at major technology companies, and recognized with a best paper award (StarAI), a Lieberman Fellowship, a Data Science Institute Scholarship, and a Microsoft Research Ph.D. Fellowship. He is also a Teaching Fellow at Stanford since 2018, where he co-designed and teaches a new class on Deep Generative Models. Previously, Aditya obtained his bachelors in Computer Science and Engineering from IIT Delhi in 2015, where he received a best undergraduate thesis award.
Host: If you would like to meet the speaker, please email the host Bistra Dilkina at dilkina@usc.edu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Tech Talk: WiSE Presents: Walmart Tech Talk with Senior VP of Customer Technology, Fiona Tan
Tue, Oct 29, 2019 @ 04:00 PM - 05:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Fiona Tan, Walmart
Talk Title: WiSE Presents: Walmart Tech Talk with Senior VP of Customer Technology, Fiona Tan
Series: Computer Science Colloquium
Abstract: Come hear more about the exciting opportunities available in tech at Walmart.
Fiona will also talk about her tech journey, as well as why she loves working for Walmart.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Fiona Tan joined Walmart in 2014 and is currently the Senior Vice President of Customer Technology. She is responsible for innovation and engineering execution on all customer-facing technology across Walmart's physical and digital footprint. Her team leverages data and machine learning to drive marketing and advertising campaigns, oversees all personalization capabilities, and delivers the desktop and mobile customer experience for Walmart's eCommerce as well as the technology across point-of-sale systems, pharmacy, specialty departments, and associate productivity apps in Walmart stores. Their goal is to deliver a seamless shopping experience for our customers -“ while empowering our millions of associates with technology.
Previously, Fiona was Walmart's Vice President of Engineering, responsible for product roadmap and engineering capabilities for Walmart's international eCommerce businesses as well as the Sam's Club business in the U.S. In addition, her team drove technology strategy and operational excellence across Walmart Labs.
Prior to Walmart, Fiona served in a number of leadership roles at Ariba and TIBCO Software. At Ariba, she led a global engineering organization responsible for the strategy, lifecycle, and delivery of the Ariba Commerce Network. At TIBCO Software, she was responsible for a major product line as well as the management of their offshore development centers.
Fiona has a master's degree in Computer Science from Stanford and a bachelor's degree in Computer Science and Engineering from Massachusetts Institute of Technology (MIT).
Host: WiSE
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Computer Science General Faculty Meeting
Wed, Oct 30, 2019 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Invited Faculty Only
Contact: Assistant to CS chair
-
Theory Lunch
Thu, Oct 31, 2019 @ 12:15 PM - 02:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Federico Echenique, Professor of Economics at CalTech
Talk Title: The Edgeworth Conjecture with Small Coalitions and Approximate Equilibria in Large Economies
Abstract: A talk about the paper Federico Echenique worked on with Siddharth Barman entitled "The Edgeworth Conjecture with Small Coalitions and Approximate Equilibria in Large Economies." The paper shows that deciding if an allocation is approximately Walrasian can be done in polynomial time, even if finding the market equilibrium in intractable.
It will be a fun time, so make sure not to miss out!
Host: Shaddin Dughmi
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: Cherie Carter
-
CS Colloquium: Masahiro Ono (NASA JPL) - Robots in Space: How AI and Machine Learning are Revolutionizing Space Exploration
Thu, Oct 31, 2019 @ 02:00 PM - 03:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Masahiro Ono, NASA JPL
Talk Title: Robots in Space: How AI and Machine Learning are Revolutionizing Space Exploration
Series: Computer Science Colloquium
Abstract: On the third planet of the Solar System, there is an ongoing revolution caused by a group of technologies collectively called as "AI," including, but not limited to, machine learning, optimal decision making, situation awareness, and autonomous navigation. The same revolution is taking off elsewhere in the Solar System, triggered by an advent of HPSC (high-performance spacecraft computing). This talk introduces ongoing research efforts to adapt and enhance latest AI technologies for future exploration missions to Mars, Europa, and Enceladus, such as resource-aware autonomous rover driving, on-board science interpretation, and autonomous descent into Enceladus's vents, which are believed to be connected to the subsurface ocean that may harbor extraterrestrial life.
If you would like to take a peek of the talk, take a look at the following YouTube movies:
https://www.youtube.com/watch?v=-AYvgTlDKQM&t=5s
https://www.youtube.com/watch?v=LJXQ0-a9IJE
https://www.youtube.com/watch?v=7bdS_xpYz7A
This lecture satisfies requirements for CSCI 591: Research Colloquium. *Note: Rescheduled to 10/31/19, 2:00-3:20PM*
Biography: Dr. Masahiro (Hiro) Ono is a Research Technologist at NASA Jet Propulsion Laboratory, California Institute of Technology. His broad interest is centered around the application of robotic autonomy to space exploration, with an emphasis on machine learning applications to perception, data interpretation, and decision making. Before joining JPL in 2013, he was an assistant professor at Keio University in Japan. He graduated from MIT with PhD in Aeronautics and Astronautics in 2012. Since 2017 he is the PI of a JPL-funded Strategic Research and Development task on the machine learning-based analytics for automated rover systems (MAARS). From 2015 he has led the development of machine learning- based Martian terrain classifier, which is used by MSL and Mars 2020 Rover missions. He was also the PI of a JPL-Caltech joint project on imitation learning-based planning from 2016 to 2018. He was awarded two NIAC Phase I studies: Comet Hitchhiker (2014) and Journey to the Center of Icy Moon (2016). Since 2019, he has been the Autonomy Lead of the EELS (Exobiology Extant Life Surveyor) project.
Host: Stefanos Nikolaidis
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
MASCLE Machine Learning Seminar: Joan Bruna (NYU) - On (Provably) Learning with Large Neural Networks
Thu, Oct 31, 2019 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Joan Bruna, New York University
Talk Title: On (Provably) Learning with Large Neural Networks
Series: Machine Learning Seminar Series hosted by USC Machine Learning Center
Abstract: Virtually all modern deep learning systems are trained with some form of local descent algorithm over a high-dimensional parameter space. Despite its apparent simplicity, the mathematical picture of the resulting setup contains several mysteries that combine statistics, approximation theory and optimization, all intertwined in a curse of dimensionality.
In order to make progress, authors have focused in the so-called 'overparametrised' regime, which studies asymptotic properties of the algorithm as the number of neurons grows. In particular, neural networks with a large number of parameters admit a mean-field description, which has recently served as a theoretical explanation for its favorable training properties. In this regime, gradient descent obeys a deterministic partial differential equation (PDE) that converges to a globally optimal solution for networks with a single hidden layer under appropriate assumptions.
In this talk, we will review recent progress on this problem, and argue that such framework might provide crucial robustness against the curse of dimensionality. First, we will describe a non-local mass transport dynamics that leads to a modified PDE with the same minimizer, that can be implemented as a stochastic neuronal birth-death process, and such that it provably accelerates the rate of convergence in the mean-field limit. Next, such dynamics fit naturally within the framework of total-variation regularization, which following [Bach'17] have fundamental advantages in the high-dimensional regime. We will discuss a unified framework that controls both optimization, approximation and generalisation errors using large deviation principles, and discuss current open problems in this research direction.
Joint work with G. Rotskoff (NYU), Z. Chen (NYU), S. Jelassi (NYU) and E. Vanden-Eijnden (NYU).
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Joan Bruna is an Assistant Professor at Courant Institute, New York University (NYU), in the Department of Computer Science, Department of Mathematics (affiliated) and the Center for Data Science, since Fall 2016. He belongs to the CILVR group and to the Math and Data groups. From 2015 to 2016, he was Assistant Professor of Statistics at UC Berkeley and part of BAIR (Berkeley AI Research). Before that, he worked at FAIR (Facebook AI Research) in New York. Prior to that, he was a postdoctoral researcher at Courant Institute, NYU. He completed his PhD in 2013 at Ecole Polytechnique, France. Before his PhD he was a Research Engineer at a semi-conductor company, developing real-time video processing algorithms. Even before that, he did a MsC at Ecole Normale Superieure de Cachan in Applied Mathematics (MVA) and a BA and MS at UPC (Universitat Politecnica de Catalunya, Barcelona) in both Mathematics and Telecommunication Engineering. For his research contributions, he has been awarded a Sloan Research Fellowship (2018), a NSF CAREER Award (2019) and a best paper award at ICMLA (2018).
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
