Lecture

Understanding Generalization: Implicit Bias & Optimization

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In course

EE-556: Mathematics of data: from theory to computation

This course provides an overview of key advances in continuous optimization and statistical analysis for machine learning. We review recent learning formulations and models as well as their guarantees

Description

This lecture delves into the trade-off between complexity and risk in machine learning models, showcasing how test error decreases with increasing model complexity. It explores the benefits of overparametrization, the implicit bias of optimization algorithms, and the concept of implicit regularization. The discussion extends to the stability of optimization algorithms, the double descent phenomenon, and the probability of interpolation in high-dimensional datasets.

Instructor

Volkan Cevher

Volkan Cevher received the B.Sc. (valedictorian) in electrical engineering from Bilkent University in Ankara, Turkey, in 1999 and the Ph.D. in electrical and computer engineering from the Georgia Institute of Technology in Atlanta, GA in 2005. He was a Research Scientist with the University of Maryland, College Park from 2006-2007 and also with Rice University in Houston, TX, from 2008-2009. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University. His research interests include machine learning, signal processing theory, optimization theory and methods, and information theory. Dr. Cevher is an ELLIS fellow and was the recipient of the Google Faculty Research award in 2018, the IEEE Signal Processing Society Best Paper Award in 2016, a Best Paper Award at CAMSAP in 2015, a Best Paper Award at SPARS in 2009, and an ERC CG in 2016 as well as an ERC StG in 2011.

Official source

Related concepts (32)

Implicit stereotype

An implicit bias or implicit stereotype is the pre-reflective attribution of particular qualities by an individual to a member of some social out group. Implicit stereotypes are thought to be shaped by experience and based on learned associations between particular qualities and social categories, including race and/or gender. Individuals' perceptions and behaviors can be influenced by the implicit stereotypes they hold, even if they are sometimes unaware they hold such stereotypes.

Implicit-association test

The implicit-association test (IAT) is an assessment intended to detect subconscious associations between mental representations of objects (concepts) in memory. Its best-known application is the assessment of implicit stereotypes held by test subjects, such as associations between particular racial categories and stereotypes about those groups. The test has been applied to a variety of belief associations, such as those involving racial groups, gender, sexuality, age, and religion but also the self-esteem, political views, and predictions of the test taker.

Implicit attitude

Implicit attitudes are evaluations that occur without conscious awareness towards an attitude object or the self. These evaluations are generally either favorable or unfavorable and come about from various influences in the individual experience. The commonly used definition of implicit attitude within cognitive and social psychology comes from Anthony Greenwald and Mahzarin Banaji's template for definitions of terms related to implicit cognition: "Implicit attitudes are introspectively unidentified (or inaccurately identified) traces of past experience that mediate favorable or unfavorable feeling, thought, or action toward social objects".

Algorithm

In mathematics and computer science, an algorithm (ˈælɡərɪðəm) is a finite sequence of rigorous instructions, typically used to solve a class of specific problems or to perform a computation. Algorithms are used as specifications for performing calculations and data processing. More advanced algorithms can use conditionals to divert the code execution through various routes (referred to as automated decision-making) and deduce valid inferences (referred to as automated reasoning), achieving automation eventually.

Regularization (mathematics)

In mathematics, statistics, finance, computer science, particularly in machine learning and inverse problems, regularization is a process that changes the result answer to be "simpler". It is often used to obtain results for ill-posed problems or to prevent overfitting. Although regularization procedures can be divided in many ways, the following delineation is particularly helpful: Explicit regularization is regularization whenever one explicitly adds a term to the optimization problem.

Related lectures (64)

Generalization in Deep Learning

Delves into the trade-off between model complexity and risk, generalization bounds, and the dangers of overfitting complex function classes.

Generalization in Deep Learning

Explores generalization in deep learning, covering model complexity, implicit bias, and the double descent phenomenon.

Adaptive Optimization Methods: Theory and Applications

Explores adaptive optimization methods that adapt locally and converge without knowing the smoothness constant.

Implicit Bias in Machine Learning

Explores implicit bias, gradient descent, stability in optimization algorithms, and generalization bounds in machine learning.

Solving Parity Games in Practice