### Spectral Transformers

We'll discuss a new technique for sequence modeling for prediction tasks with long range dependencies and fast inference/generation. At the heart of the method is a new formulation for state space model

Filter by year:

Date:

6

November

2024

Hour:
11:15 - 12:15

Ziskind Building, Room 1

Machine Learning and Statistics Seminar

Elad Hazan

Princeton

We'll discuss a new technique for sequence modeling for prediction tasks with long range dependencies and fast inference/generation. At the heart of the method is a new formulation for state space model

Date:

10

November

2024

Hour:
11:00 - 12:00

Ziskind Building, Room 155

Special Guest Seminar

Yuri Zarkhin

Pennsylvania State University

**Let p be an odd prime and f(x) a polynomial of degree at least 5 with complex coefficients and without repeated roots. Suppose that all the coefficients of f(x) lie in a subfield K suc**

Date:

11

November

2024

Hour:
11:15 - 12:15

Ziskind Building, Room 155

Foundations of Computer Science Seminar

Avi Wigderson

IAS

I will discuss some well-known and less-known papers of Turing, exemplify the scope of deep, prescient ideas he put forth, and mention follow-up work on these by the Theoretical CS community.

No sp

Date:

13

November

2024

Hour:
11:15 - 12:15

Ziskind Building, Room 1

Machine Learning and Statistics Seminar

Michael Feldman

WIS

Sparse principal component analysis (PCA) is a powerful method for low-rank and sparse signal recovery, applicable to covariance estimation, dimension reduction, and feature selection. In this work, w

Seminars

Date:

18

November

2024

Hour:
11:15 - 12:15

Ziskind Building, Room 155

Foundations of Computer Science Seminar

Michael Chapman

NYU

A common theme in mathematics is that limits of finite objects are well behaved. This allows one to prove many theorems about **finitely approximable** objects, while leaving the general case op