Events

Upcoming Events

There are no upcoming events matching your criteria.

Past Events

CSE DSI Machine Learning Seminar with Aldo Scutari (IE, Purdue)

Aldo Scutari, Purdue University, will give a talk entitled Statistical Inference over Networks: Decentralized Optimization Meets High-Dimensional Statistics.

CSE DSI Machine Learning Seminar with Qing Qu (University of Michigan)

Qing Qu, assistant professor at the University of Michigan, will give a presentation entitled On the Emergence of Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Networks.

IMA Data Science seminar - Data Driven Modeling of Unknown Systems with Deep Neural Networks

Dongbin Xiu (The Ohio State University) will give a talk entitled Data Driven Modeling of Unknown Systems.

CSE DSI Machine Learning Seminar with Volkan Cevher (EPFL)

Volkan Cevher (EPFL) will give a talk entitled Key Challenges in Foundation Models (... and some solutions!).

CRAY Colloquium: Well-being, AI, and You: Developing AI-based Technology to Enhance our Well-being

Alon Halevy (Meta) will give a talk entitled Well-being, AI, and You: Developing AI-based Technology to Enhance our Well-being.

IMA Data Science Seminar - Trading off accuracy for reduced computation in scientific computing

Data Science Seminar

Alex Gittens (Rensselaer Polytechnic Institute)

Abstract

Classical linear algebraic algorithms guarantee high accuracy in exchange for high computational cost. These costs can be infeasible in modern applications, so over the last two decades, randomized algorithms have been developed that allow a user-specified trade-off between accuracy and computational efficiency when dealing with massive data sets. The intuition is that when dealing with an excess of structured data (e.g., a large matrix which has low numerical rank), one can toss away a large portion of this data, thereby reducing the computational load, without introducing much additional error into the computation. In this talk we look at the design and performance analysis of several numerical linear algebra and machine learning algorithms--- including linear solvers, approximate kernel machines, and tensor low-rank decomposition--- based upon this principle.

CSE DSI Machine Learning Seminar with Benjamin Grimmer (John Hopkins)

Benjamin Grimmer will give a talk entitled Accelerated Gradient Descent via Long Steps.

CSE DSI Machine Learning Seminar with Ahmet Alacaoglu (UW-Madison)

Ahmet Alacaoglu, UW-Madison, will give a talk entitled Stochastic Variance Reduction Beyond Minimization Problems.

 

CSE DSI Machine Learning Seminar with Hanshen Xiao (CSAIL, MIT)

Hanshen Xiao, CSAIL, MIT, will give a talk entitled PAC Privacy: Automatic Privacy Measurement and Control of Data Processing.

CSE DSI Machine Learning Seminar with Qianwen Wang

Qianwen Wang (CS&E, UMN) will give a talk entitled Interpreting and Steering AI Explanations with Interactive Visualizations.