Arguably, the most crucial objective of Learning Theory is to understand the basic notion of generalization: How can a learning agent infer from a finite amount of data to the whole population? Today's learning algorithms are poor...
Arguably, the most crucial objective of Learning Theory is to understand the basic notion of generalization: How can a learning agent infer from a finite amount of data to the whole population? Today's learning algorithms are poorly understood from that perspective. In particular, best practices, such as using highly overparameterized models to fit relatively few data, seem to be in almost contradiction to common wisdom, and classical models of learning seem to be incapable of explaining the impressive success of such algorithms. The objective of this proposal is to understand generalization in overparameterized models and understand the role of algorithms in learning. Toward this task, I will consider two mathematical models of learning that shed light on this fundamental problem.The first model is the well-studied, yet only seemingly well-understood, model of Stochastic Convex optimization. My investigations, so far, provided a new picture that is much more complex than was previously known or assumed, regarding fundamental notions such as regularization, inductive bias as well as stability. These works show that even in this, simplistic setup of learning, understanding such fundamental principles may be a highly ambitious task. On the other hand, given the simplicity of the model, it seems that such an understanding is a prerequisite to any future model that will explain modern Machine Learning algorithms.The second model considers a modern task of synthetic data generation. Synthetic data generation serves as an ideal model to further study the tension between concepts such as generalization and memorization. Here we with a challenge to model the question of generalization, and answer fundamental questions such as: when is synthetic data original and when is it a copy of the empirical data?ver más
Seleccionando "Aceptar todas las cookies" acepta el uso de cookies para ayudarnos a brindarle una mejor experiencia de usuario y para analizar el uso del sitio web. Al hacer clic en "Ajustar tus preferencias" puede elegir qué cookies permitir. Solo las cookies esenciales son necesarias para el correcto funcionamiento de nuestro sitio web y no se pueden rechazar.
Cookie settings
Nuestro sitio web almacena cuatro tipos de cookies. En cualquier momento puede elegir qué cookies acepta y cuáles rechaza. Puede obtener más información sobre qué son las cookies y qué tipos de cookies almacenamos en nuestra Política de cookies.
Son necesarias por razones técnicas. Sin ellas, este sitio web podría no funcionar correctamente.
Son necesarias para una funcionalidad específica en el sitio web. Sin ellos, algunas características pueden estar deshabilitadas.
Nos permite analizar el uso del sitio web y mejorar la experiencia del visitante.
Nos permite personalizar su experiencia y enviarle contenido y ofertas relevantes, en este sitio web y en otros sitios web.