Select a calendar:
Filter December Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for December
-
D.R.E.A.M. Pitch Industry Mentorship Panel
Fri, Dec 03, 2021 @ 10:00 AM - 11:20 AM
USC Viterbi School of Engineering
University Calendar
This panel features dream pitches from students with additive feedback from industry mentors from a variety of tech and destination companies. Please contact Elisabeth Arnold Weiss at arnolde@usc.edu if you would like to attend this event.
D.R.E.A.M. (Direct Response to Engineers Aspirations from Mentors) is an initiative that leverages insights from industry mentors who directly respond to students dream pitches, an original leadership communication assignment in WRIT 340 where students create a vision for their future selves, align their efforts around purpose, and build a consistent character and identity in the context of growth, reinvention, and constant change. To achieve that vision, they design a detailed career roadmap which encourages adaptability and determination, frees up cognitive resources to embrace new opportunities, and instills mental flexibility, long-range thinking, and a sense of agency about the future.
Location: Virtual (Zoom)
Audiences: Everyone Is Invited
Contact: Elisabeth Arnold Weiss
-
PhD Thesis Proposal - Arka Sadhu
Fri, Dec 03, 2021 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
Ph.D. Thesis Proposal - Arka Sadhu
Friday, Dec 3rd, 2021: 12pm-2pm
Title: Grounding Language in Images and Videos
Thesis Committee members: Prof. Ram Nevatia, Prof. Xiang Ren, Prof. Yan Liu, Prof. Stefanos Nikolaidis, Prof. Toby Mintz.
Abstract: Language grounding in images and videos -- the task of associating linguistic symbols to perceptual experiences and actions -- is fundamental to developing multi-modal models which can understand and jointly reason over images, videos and text.
It has garnered wide interest from multiple disciplines such as computer vision, natural language processing, and robotics. An essential element in this space involves formulating tasks that investigate a particular phenomenon inherent in image or video understanding in isolation, thereby encouraging the community to develop more robust models. In this thesis proposal, I will articulate four vision-language tasks developed during the course of my Ph.D., namely, grounding unseen words, spatio-temporal localization of entities in a video, video question-answering, and visual semantic role labeling in videos. For each of these tasks, I will further discuss the development of corresponding datasets, evaluation protocols, and model frameworks.
Zoom Link: https://usc.zoom.us/j/92383912262?pwd=N25ETlRMVFRiWTlKdGxtN09UVHhlQT09WebCast Link: https://usc.zoom.us/j/92383912262?pwd=N25ETlRMVFRiWTlKdGxtN09UVHhlQT09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal - Chen-Yu Wei
Fri, Dec 03, 2021 @ 01:00 PM - 02:30 PM
Thomas Lord Department of Computer Science
University Calendar
Time: 1:00-2:30pm, December 3rd
Committee: Haipeng Luo (host), Rahul Jain, David Kempe, Vatsal Sharan, Jiapeng Zhang
Title: Robust and Adaptive Online Reinforcement Learning
Abstract: Online reinforcement learning (RL) studies how an agent learns to behave in an unknown environment from scratch. In this thesis, I focus on the theoretical foundations of this learning paradigm, with emphasis on designing algorithms that are robust to the non-stationarity of the environment, where the non-stationarity may come from natural drift, adversarial manipulation, or the existence of other agents. While being robust, most of our algorithms are also "adaptive" at the same time in the sense that they do not sacrifice nice performance guarantees if the environment happens to be stationary. More broadly speaking, the performance of our algorithms automatically scale with some intrinsic properties that reflect the difficulty of the problem.
For future work, I plan to characterize the fundamental limit of RL in large state space, a central topic in theoretical RL. We hope to answer the following questions: "what are the minimal assumptions to be made so that RL algorithms can find near-optimal policies with polynomial number of samples", and the similar question under the restriction of "polynomial computational time".WebCast Link: https://usc.zoom.us/j/96695544670?pwd=VnZJUzRLam9scVpHbFRTYUVmQlk4Zz09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal - Hikaru Ibayashi
Wed, Dec 08, 2021 @ 02:00 PM - 03:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Hikaru Ibayashi
Wed, Dec 8, 2021 @ 02:00 PM - 03:30 PM
Committee members: Chair: Prof. Aiichiro Nakano, Prof. Satish Kumar Thittamaranahalli, Prof. Emilio Ferrara, Prof. Yan Liu, Prof. Paulo Branicio (Department of Chemical Engineering and Materials Science)
Title:
Sharpness analysis of neural-networks for high-performance physics simulation
Abstract:
In recent years, deep neural networks have witnessed tremendous success in a wide range of fields. Especially, in physics simulations, neural networks have achieved drastically efficient computation by approximating first-principles simulations. However, such practical successes have opened theoretical problems. One open question is why a simple optimization algorithm such as stochastic gradient descent (SGD) can find solutions that generalize well over non-convex loss surfaces. In this proposal, we leverage the second-order information of loss surface, i.e., sharpness, to lay a theoretical foundation of the generalizability of neural networks. First, we use a novel quasi-potential theory to prove that SGD avoids non-generalizing sharp minima. Secondly, we develop a scale-invariant sharpness measure named "minimum sharpness" to theoretically explain why sharp minima are not generalizing. Finally, as a practical application of the thus-developed theoretical framework, we propose a novel sharpness-regularization scheme for robust neural-network-based molecular dynamics simulations. This research will demonstrate the effectiveness of sharpness analysis to deepen the understanding of neural networks and their successful application in physics simulations.
Zoom link: https://usc.zoom.us/j/7751892842WebCast Link: https://usc.zoom.us/j/7751892842
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal -Yury Zemlyanskiy
Thu, Dec 09, 2021 @ 11:00 AM - 01:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Yury Zemlyanskiy
Title: Parametric and semi-parametric methods for knowledge acquisition from text
Time: 11:00 AM-1:00 PM PST, Dec 9 (Thursday)
Committee: Fei Sha, Leana Golubchik, Xiang Ren, Robin Jia, Jonathan May, and Meisam Razaviyayn (external).
Zoom link: https://usc.zoom.us/j/95672050503
Abstract:
Knowledge acquisition is a crucial characteristic of an intelligent system that allows the processing of large amounts of information. Nonetheless, modern neural networks (e.g., BERT) used in natural language processing typically do not have a dedicated memory component. The knowledge about the world that the models acquire is stored implicitly in the model's parameters. This proves unreliable and makes the models ill-suited for knowledge-intensive tasks that require reasoning over vast amounts of textual data.
My thesis explores alternative parametric and semi-parametric methods to extract and represent knowledge from text. Specifically, the proposed methods seek to establish several desirable properties for the neural network memory component. First, the memory should benefit the model and allow it to reason over large amounts of textual information. Second, the memory should be amendable and adapt to a new context (a different book or collection of articles) on the fly. Finally, certain applications will benefit from the transparent structure of the memory, allowing queries on information about particular objects or entities.
The proposed thesis consists of three sections: the first section focuses on parametric memory for a pre-defined set of entities. The second section explores a semi-parametric approach to capturing entity-centric facts in a long document or entire corpus. Finally, the last section discusses future work on memory specialized for structure prediction tasks.WebCast Link: https://usc.zoom.us/j/95672050503
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal - Sarah Cooney
Thu, Dec 09, 2021 @ 03:00 PM - 04:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Sarah Cooney
Thur, Dec 9, 2021 @ 03:00 PM - 04:30 PM
Committee members: Chair: Prof. Barath Raghavan, Prof. Romesh Govindan, Prof. Heather Culbertson, Prof. Bistra Dilkina, Prof. Hajar Yazdiha (Sociology)
Title:
Toward Sustainable and Resilient Communities
with HCI: Physical Structures and Socio-Cultural Factors
Abstract:
Recently, large-scale global challenges such as shifting weather patterns due to climate change and the Covid-19 pandemic have caused us to be more reliant than ever on the resources and resilience of our local communities. My research looks at how computing can be applied to the challenges of creating sustainable and resilient communities equipped to handle such challenges at the local level. My work covers two complementary threads. The first looks at how technology can be used to influence grassroots redesign of urban spaces to promote sustainability, community resilience, and individual wellbeing. Within this area I have worked on three specific projects which I will discuss in more detail. The second thread looks at sustainability and sustainable HCI from a socio-cultural perspective. Specifically, I have been looking at the way that religion and spirituality can influence the intersections of sustainability and technology use, and I will discuss my ongoing study in this area as well.
Zoom link: https://usc.zoom.us/j/96182449560
WebCast Link: https://usc.zoom.us/j/96182449560
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
PhD Thesis Proposal - Séb Arnold
Fri, Dec 10, 2021 @ 03:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Séb Arnold
Friday, Dec 10, 2021 @ 03:00 PM - 05:00 PM
Committee members: Chair: Prof. Maja Mataric, Prof. Fei Sha, Prof. Yan Liu, Prof. Stefanos Nikolaidis, Prof. Jesse Thomason, Prof. Salman Avestimehr (ECE)
Title:
Quickly solving new tasks, with meta-learning and without.
Abstract:
This thesis proposal seeks to answer how learning systems can reuse and adapt their knowledge to quickly solve new test tasks. We first show how to improve the test task performance of meta-learning algorithms (eg, MAML) by carefully choosing which tasks to train on -- even when these test tasks are unknown a priori. We then zero in on these algorithms and uncover modeling pitfalls that completely prevent fast adaptation; fortunately, there exist simple remedies. Leveraging those insights, we conclude with the challenge of quickly solving new tasks using off-the-shelf models, which were trained without meta-learning.
Zoom link: https://usc.zoom.us/j/94965325337
WebCast Link: https://usc.zoom.us/j/94965325337
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
