YoVDO

Algorithms and Hardness for Attention and Kernel Density Estimation

Offered By: Google TechTalks via YouTube

Tags

Algorithms Courses Machine Learning Courses Computational Complexity Courses Computational Physics Courses Transformer Models Courses Polynomial Method Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the computational challenges and algorithmic solutions for Attention in Large Language Models and Kernel Density Estimation in this Google TechTalk presented by Josh Alman. Dive into the quadratic-time algorithms for both problems and discover recent advancements in achieving almost linear-time performance through techniques like the Fast Multipole Method and the polynomial method. Examine fine-grained hardness results that demonstrate the optimality of these approaches in specific parameter regimes, while identifying potential areas for improvement. Learn about the speaker's collaborative research efforts and gain insights into the intersection of algorithm design, complexity theory, and algebraic tools for enhancing algorithmic efficiency.

Syllabus

Algorithms and Hardness for Attention and Kernel Density Estimation


Taught by

Google TechTalks

Related Courses

The Polynomial Method and the Restriction Problem - Larry Guth
Institute for Advanced Study via YouTube
Additive Number Theory - Extremal Problems and the Combinatorics of Sumsets by M. Nathanson
International Centre for Theoretical Sciences via YouTube
Basic Lower Bounds and Kneser's Theorem by David Grynkiewicz
International Centre for Theoretical Sciences via YouTube
The Restriction Problem and the Polynomial Method - Lecture I
Hausdorff Center for Mathematics via YouTube
Marina Iliopoulou- Three Polynomial Methods for Point Counting, Lecture II
Hausdorff Center for Mathematics via YouTube