News & Events

Department Events & Announcements

Events

• Feb

  27

  CS Seminar: Algorithms and Systems for Efficient Machine Learning (Tri Dao)

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Monday / CS Seminar
  February 27th / 12:00 PM
  Mudd 3514

  Title: Algorithms and Systems for Efficient Machine Learning
  Speaker: Tri Dao

  Abstract:
  Machine learning (ML) models training will continue to grow to consume more cycles, their inference will proliferate on more kinds of devices, and their capabilities will be used on more domains. Some goals central to this future are to make ML models efficient so they remain practical to train and deploy, and to unlock new application domains with new capabilities. We describe some recent developments in hardware-aware algorithms to improve the efficiency-quality tradeoff of ML models and equip them with long context. In the first half, we focus on structured sparsity, a natural approach to mitigate the extensive compute and memory cost of large ML models. We describe a line of work on learnable fast transforms which, thanks to their expressiveness and efficiency, yields some of the first sparse training methods to speed up large models in wall-clock time (2x) without compromising their quality. In the second half, we focus on efficient Transformer training and inference for long sequences. We describe FlashAttention, a fast and memory-efficient algorithm to compute attention with no approximation. By careful accounting of reads/writes between different levels of memory hierarchy, FlashAttention is 2-4x faster and uses 10-20x less memory compared to the best existing attention implementations, allowing us to train higher-quality Transformers with 8x longer context. FlashAttention is now widely used in some of the largest research labs and companies, in just 6 months after its release. We conclude with some exciting directions in ML and systems, such as software-hardware co-design, structured sparsity for scientific AI, and long context for new AI workflows and modalities.

  Biography:
  Tri Dao is a PhD student in Computer Science at Stanford, co-advised by Christopher Ré and Stefano Ermon. He works at the interface of machine learning and systems, and his research interests include sequence models with long-range memory and structured matrices for compact deep learning models. His work has received the ICML 2022 Outstanding paper runner-up award.

  more less

  TIME Monday, February 27, 2023 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Jan

  29

  Bagel Thursday

  Department of Computer Science (CS)

  9:00 AM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  

  Join us for our monthly free bagels and coffee while mingling with fellow faculty and students.

  There will also be another informal discussion from 9:30AM hosted by CSPAC and CSSI on the topic "AI in Research". Invited guests Aaron Shaw, Jessica Hullman, and Samir Khuller will discuss this topic with a focus on integrating AI in the research process (brainstorming, literature review, experimental setup, writing, etc.).

  more less

  TIME Thursday, January 29, 2026 at 9:00 AM - 11:00 AM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Feb

  2

  CS Seminar: Toward Faster Algebraic Computation: An Isomorphism Perspective (Xiaorui Sun)

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Monday / CS Seminar
  February 2 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  Xiaorui Sun, UIC

  Talk Title
  Toward Faster Algebraic Computation: An Isomorphism Perspective

  Abstract

  "Over the past few decades, linear-algebraic techniques played a central role in the design of faster algorithms, with notable successes in many graph algorithms such as maximum flow and shortest paths. However, for many problems that are not yet known to admit polynomial-time algorithms—such as integer factoring and various isomorphism problems—linear methods alone are often insufficient. In these settings, more general nonlinear algebraic structures, including groups, rings, and modules, naturally arise. Achieving further algorithmic progress requires a deeper understanding of these algebraic objects.

  In this talk, I will discuss how algebraic representations have become essential to recent advances in isomorphism problems. I will highlight connections among several central isomorphism problems and survey the techniques that have led to more efficient algorithms. I will conclude by discussing open challenges and outlining promising directions for future research."

  Biography
  Xiaorui Sun is an Associate Professor of Computer Science at the University of Illinois Chicago. His research interests lie in theoretical computer science, with an emphasis on the intersection of algorithms and algebraic computation. After earning his PhD from Columbia University, he worked at Simons Institute for the Theory of Computing and Microsoft Research. He is a recipient of the NSF CAREER Award, and his work have been featured in Communications of the ACM and Quanta Magazine.

  Research Interests: theoretical computer science, algorithms, and algebraic computation

  ---
  Zoom Link
  Panopto Link

  more less

  TIME Monday, February 2, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Feb

  26

  Bagel Thursday

  Department of Computer Science (CS)

  9:00 AM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  CS Community! Join us for our monthly free bagels and coffee while mingling with fellow faculty and students.

  more less

  TIME Thursday, February 26, 2026 at 9:00 AM - 11:00 AM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)

• Apr

  13

  CS Seminar

  Department of Computer Science (CS)

  12:00 PM 3514, Mudd Hall ( formerly Seeley G. Mudd Library)

  EVENT DETAILS

  Monday / CS Seminar
  April 13 / 12:00 PM
  Hybrid / Mudd 3514

  Speaker
  TBA

  Talk Title
  TBA

  Abstract
  TBA

  Biography
  TBA

  ---
  Zoom: TBA
  Panopto: TBA

  more less

  TIME Monday, April 13, 2026 at 12:00 PM - 1:00 PM

  LOCATION 3514, Mudd Hall ( formerly Seeley G. Mudd Library)    map it

  ADD TO CALENDAR

  CONTACT Wynante R Charles    wynante.charles@northwestern.edu EMAIL

  CALENDAR Department of Computer Science (CS)