Главная
Study mode:
on
1
Intro
2
Overfitting in Deep Networks
3
Statistical Wisdom and Overhitting
4
Progress on Overfitting Prediction Rules
5
Outline
6
Definitions
7
From regularization to overfitting
8
Interpolating Linear Regression
9
Benign Overfitting: A Characterization
10
Notions of Effective Rank
11
Benign Overfitting: Proof Ideas
12
What kinds of eigenvalues?
13
Extensions
14
Implications for deep learning
15
Implications for adversarial examples
16
Benign averfitting: Future directions
17
Benign Overfitting in Linear Regression
Description:
Explore the phenomenon of benign overfitting in machine learning through this 42-minute lecture by Peter Bartlett from UC Berkeley, presented at the Alan Turing Institute. Delve into the intersection of statistics and computer science, examining how modern machine learning algorithms can overfit training data yet still generalize well. Investigate topics such as overfitting in deep networks, statistical wisdom, regularization, interpolating linear regression, and characterizations of benign overfitting. Learn about notions of effective rank, proof ideas, and the implications for deep learning and adversarial examples. Gain insights into the future directions of benign overfitting research and its application in linear regression, providing a comprehensive overview of this important concept in the era of Big Data and high-dimensional statistical models.

Benign Overfitting - Peter Bartlett, UC Berkeley

Alan Turing Institute
Add to list
00:00
-00:22