Speaker: Ilias Diakonikolas, Professor, The University of Wisconsin–Madison
Abstract:
Robustness is a basic requirement for trustworthy machine learning, yet achieving it efficiently in high dimensions has long been a fundamental challenge. For decades, the prevailing view was that learning algorithms with strong robustness guarantees necessarily come with prohibitive computational cost, creating a sharp tension between statistical guarantees and algorithmic tractability. This talk describes a research program aimed at overcoming this barrier through an algorithmic theory of robust learning.
I will describe two interconnected threads within this research program. The first develops a unified framework for efficient robust high-dimensional estimation, including the first polynomial-time algorithms for several fundamental unsupervised learning tasks under adversarial corruption. The second studies supervised learning under noisy labels, with an emphasis on learning predictors with low-dimensional latent representations. I will conclude by discussing future directions, including robustness beyond worst-case corruption and the efficient learning of richer nonlinear representations.
Bio:
lias Diakonikolas is the Lubar Professor in the Department of Computer Sciences at UW Madison. He obtained a Diploma in electrical and computer engineering from the National Technical University of Athens and a Ph.D. in computer science from Columbia University where he was advised by Mihalis Yannakakis. Before moving to UW, he was an Andrew and Erna Viterbi Early Career Chair at USC and a faculty member at the University of Edinburgh. Prior to that, he was the Simons postdoctoral fellow in theoretical computer science at the University of California, Berkeley. His research is on the algorithmic foundations of massive data sets, in particular on designing efficient algorithms for fundamental problems in machine learning. He is a recipient of the ACM Grace Murray Hopper award, a Sloan Fellowship, an NSF CAREER Award, a Romnes Faculty Fellowship, a Google Faculty Research Award, a Marie Curie Fellowship, best paper awards at NeurIPS and COLT, the IBM Research Pat Goldberg Best Paper Award, and an honorable mention in the George Nicholson competition from the INFORMS society. Ilias wrote with Daniel Kane the textbook "Algorithmic High-dimensional Robust Statistics" published by Cambridge University Press.
]]>Speaker: Ilias Diakonikolas, Professor, The University of Wisconsin–Madison
]]>Date: Wednesday, April 29, 2026, at 12:00 p.m.
Location: Coda, Room 114 (Google Maps link)
Lunch provided!
Title: Safety Alignment of Generative Foundation Models
Abstract: Modern LLMs are safety-aligned through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF) to mitigate harmful, undesirable, or disallowed outputs. Despite ongoing progress, LLMs still exhibit critical safety gaps: models can be jailbroken into revealing harmful content, often overrefuse benign queries, and fail to maintain safety under adversarial scenarios. My dissertation research advances the safety alignment of generative foundation models by developing principled tools, architectures, and training methods that strengthen their robustness and reliability at scale. Specifically, this thesis focuses on three complementary thrusts: a) Understanding and shaping the safety landscape of LLMs, b) Internalizing safety in agentic reasoning intelligence, and c) Grounding safety and robustness in multimodal perception.
Bio: Anthony is a CS Ph.D. candidate at Georgia Tech working with Polo Chau. His thesis research has elevated foundational AI efforts at Nvidia, Meta, IBM, Intel, and ADP via internships and collaborations, and has resulted in several first-author publications and awards at NeurIPS, ACL, ICCV, EMNLP, CVPR, and BMVC. His research has contributed to the AI foundation of multiple funded industry research grants totaling over $1.4M. Learn more about him at shengyun-peng.github.io.
About HotCSE
HotCSE is an academic seminar series to bring Ph.D. students in Computational Science and Engineering together to discuss interesting topics. The topics consist of high-performance computing, machine learning, data analysis, simulation, computational sustainability, medical informatics, etc.
The talks have always been enjoyable and have ranged from quite informal to formal conference style talks. Either chalks or slides can be used to help people understand your talk. It is also a great forum to practice conference talks and bounce around new ideas.
Currently the talks are sponsored by the School of Computational Science and Engineering. The goal of CSE is slightly broader than that of these talks - we want to bring more people outside CSE to discuss their related work here.
]]>Date: Wednesday, April 29, 2026, at 12:00 p.m.
Location: Coda, Room 114 (Google Maps link)
Title: Safety Alignment of Generative Foundation Models
]]>cse-gsa@cc.gatech.edu
]]>
IDEaS-affiliated students and staff are also welcome.
If you do not have access to Coda, near the beginning of the event we will have a staff member or student waiting by the reception desk near the elevators to escort people up.
For questions please contact Ashley.edwards@gatech.edu
]]>Coffee and snacks will be served.
Digital technologies are reshaping our work and our lives at unprecedented speed. This presentation examines three forces driving this Fourth Industrial Revolution: exponentiality, convergence, and ubiquity, and their implications for higher education and adult learning. Dr. Schatz explores critical questions: How do we leverage AI-enabled personalization to support careers when 40% of worker skills become obsolete every five years? How do we design learning ecosystems that scale adaptive support across institutional boundaries? How do we use data to inform lifelong learning while respecting individuals’ data sovereignty? Drawing on cognitive science and learning engineering research, this presentation offers actionable strategies for implementing AI-augmented adult learning systems that move from pilot projects to institutional practice.
Biosketch
Sae (pronounced like “say”) works at the intersection of cognition, technology, and data. She specializes in bridging the gap between scientific principles and human-centered practice, and her unique approach to “strategic storytelling” (translating complex topics into memorable messages) has garnered professional awards and seen her work translated into multiple languages.
In 2023, Sae launched the Knowledge Forge LLC, a boutique consultancy offering keynotes, professional development workshops, and strategic services. Her clients include government agencies, academic institutions, and businesses. Recently, for example, she delivered keynotes at the UK Special Forces Club (Knightsbridge), Prometric board meeting, and Innovations in Testing annual conference. She’s published works in TD Magazine, Defense Dossier, and the Journal of Military Learning, and she helped to produce the Learning Engineering Toolkit (2022), authored Engines of Engagement: A Curious Book About Generative AI (2023), and contributed to the U.S. National Academies’ report on Adult Learning in the Military Context (2024).
From 2015 to 2022, Sae served as the director of the Advanced Distributed Learning (ADL) Initiative, a U.S. Department of Defense program for research, development, and policy stewardship. She also co-chaired the NATO Training Group (NTG) Individual Training and Educational Developments task group. Under her leadership, the U.S. ADL Initiative sparked the international community’s pursuit of the lifelong “digital learning ecosystem,” in part with her popular book Modernizing Learning: Building the Future Learning Ecosystem. Her efforts were also formally recognized as “a pathfinder for enterprise data services” by then–DoD Chief Data Officer David L. Spirk.
Before joining the civil service, Sae worked as an applied human-systems scientist in both business and academia. From 2011 to 2014, she was the chief scientist at MESH Solutions (a defense contractor), where she led the U.S. Marine Corps’ Making Good Instructors Great project and the U.S. Joint Staff’s award-winning Blended Learning–Training effort. Prior to that, she held an assistant professorship with the University of Central Florida’s Institute for Simulation and Training. Sae is a prolific writer and professional presenter as well as a graphic designer who often uses those skills to enhance books, presentations, and infographics.
She holds a doctorate in Modeling and Simulation (M&S), with an emphasis on human systems.
]]>Title: Recent Advances in the Design and Simulation of Approximate Multi-Species Collisional Models in Computational Kinetic Theory
Abstract: Kinetic descriptions of particle systems are characterized by a balance of phase-space advection and particles collisions. Often the operators that model collisions are the most expensive part of a kinetic simulation, and simplified models are desired. In this talk, I will present some of these models and discuss recent extensions to the multispecies setting.
Bio: Cory Hauck is an applied mathematician and group leader of the Multiscale Methods and Dynamics Group. His research interests cover various aspects of numerical analysis, computational physics, scientific computing, and mathematical tools for scientific data. His primary research area lies is the development of numerical methods for kinetic equations and related models. These models are characteristic by multiscale phenomena, and their simulation requires advanced mathematical tools in modeling and computation.
Dr. Hauck received his Ph.D. in Applied Mathematics from the University of Maryland in 2006. Before moving to Oak Ridge, he did a postdoc in the Computational Physics and Methods Group and at the Center for Nonlinear Studies at Los Alamos. He serves on the editorial boards of SIAM Multiscale Modeling & Simulation, Journal of Scientific Computing, and others. He has received Householder Fellowship from ORNL and Early Career Award from the Department of Energy (ASCR).
]]>Title: Recent Advances in the Design and Simulation of Approximate Multi-Species Collisional Models in Computational Kinetic Theory
]]>Location: Klaus Atrium
Who: All students are welcome to participate.
Register on the site or use the link provided.
]]>
Title: Breaking the Scaling Wall in Distributed Deep Learning
Abstract: Significant advances in computer architecture (development of extremely powerful server-class GPUs) and parallel computing (scalable libraries for dense and sparse linear algebra) have contributed to the on-going AI revolution. In particular, distributed training of deep neural networks (DNNs) relies on scalable matrix multiplication algorithms and efficient communication on high-speed interconnects. Pre-training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters and graph neural networks (GNNs) on extremely large graphs requires hundreds to tens of thousands of GPUs. However, such training often suffers from significant scaling bottlenecks such as high communication overheads and load imbalance.
In this talk, I will present several systems research directions that directly impact AI model training. First, I will describe my group's work in using a three-dimensional parallel algorithm for matrix multiplication in large-scale LLM training. Second, I will demonstrate the application of the same algorithm to full-graph and mini-batch GNN training when working with extremely large graphs. Finally, I will also discuss the need for scalable collective communication routines for large-scale DNN training.
Bio: Abhinav Bhatele is an associate professor in the department of computer science, and director of the Parallel Software and Systems Group at the University of Maryland, College Park. His research interests are broadly in systems and AI, with a focus on parallel computing and distributed AI. He has published research in parallel programming models and runtimes, network design and simulation, applications of machine learning to parallel systems, parallel deep learning, and on analyzing/visualizing, modeling and optimizing the performance of parallel software and systems. Abhinav has received best paper awards at Euro-Par 2009, IPDPS 2013, IPDPS 2016, and PDP 2024, and a best poster award at SC 2023. He was selected as a recipient of the IEEE TCSC Award for Excellence in Scalable Computing (Early Career) in 2014, the LLNL Early and Mid-Career Recognition award in 2018, the NSF CAREER award in 2021, the IEEE TCSC Award for Excellence in Scalable Computing (Middle Career) in 2023, and the UIUC CS Early Career Academic Achievement Alumni Award in 2024.
Abhinav received a B.Tech. degree in Computer Science and Engineering from I.I.T. Kanpur, India in May 2005, and M.S. and Ph.D. degrees in Computer Science from the University of Illinois at Urbana-Champaign in 2007 and 2010 respectively. He was a post-doc and later computer scientist in the Center for Applied Scientific Computing at Lawrence Livermore National Laboratory from 2011-2019. Abhinav was an associate editor of the IEEE Transactions on Parallel and Distributed Systems (TPDS) from 2022-2024. He was one of the General Chairs of IEEE Cluster 2022, and Research Papers Chair of ISC 2023.
]]>Title: Breaking the Scaling Wall in Distributed Deep Learning
]]>
What Participants Will Learn:
Schedule:
Date: Wednesday, April 1, 2026, at 12:00 p.m.
Location: Coda, Room 230 (Google Maps link)
Lunch provided!
Title: Fast Active-Set Thresholding Method for Nonnegative Least Squares
Abstract: Nonnegative Least Squares (NNLS) is a fundamental constrained optimization problem encountered in many applications such as image deblurring, signal processing, nonnegative matrix factorization, magnetic microscopy, and hyperspectral imaging. Active-set based methods are a common class of algorithms for solving NNLS which identify the optimal variable set of the NNLS solution. They do so by iteratively solving a series of unconstrained least squares problems, identifying which variables violate the nonnegativity constraints, and then swapping variables in/out of consideration until the optimal set of variables is found. Several variations improving upon this method exist in the literature. In this work, we propose an active-set swap heuristic which further improves upon existing active-set based methods for NNLS. Our optimizations are based upon adding multiple variables to the passive set within a threshold of the smallest gradient value and removing variables within a similar threshold of the closest boundary constraint. We leverage these optimizations to yield a Fast Active-Set Thresholding NNLS (FAST-NNLS) algorithm which significantly outperforms the existing state-of-the-art NNLS algorithms for a wide range of problems. Rigorous convergence guarantees are proven for the proposed method. We demonstrate the effectiveness of our proposed method on multiple synthetic datasets and two real-world text analysis applications. In doing so, we present the most comprehensive NNLS solver comparison in the literature to date.
Bio: Ben Cobb is a CSE Ph.D. candidate conducting research at the intersection of high-performance computing and numerical linear algebra under the co-advisement of Richard Vuduc and Haesun Park. His doctoral research pertains to various forms of tensor decompositions for data analysis and compression.
About HotCSE
HotCSE is an academic seminar series to bring Ph.D. students in Computational Science and Engineering together to discuss interesting topics. The topics consist of high-performance computing, machine learning, data analysis, simulation, computational sustainability, medical informatics, etc.
The talks have always been enjoyable and have ranged from quite informal to formal conference style talks. Either chalks or slides can be used to help people understand your talk. It is also a great forum to practice conference talks and bounce around new ideas.
Currently the talks are sponsored by the School of Computational Science and Engineering. The goal of CSE is slightly broader than that of these talks - we want to bring more people outside CSE to discuss their related work here.
]]>Date: Wednesday, April 1, 2026, at 12:00 p.m.
Location: Coda, Room 230 (Google Maps link)
Title: Fast Active-Set Thresholding Method for Nonnegative Least Squares
]]>cse-gsa@cc.gatech.edu
]]>IDEaS-affiliated students and staff are also welcome.
If you do not have access to Coda, near the beginning of the event we will have a staff member or student waiting by the reception desk near the elevators to escort people up.