A high-bias, low-variance introduction to machine learning for physicists
Abstract Machine Learning (ML) is one of the most exciting and dynamic areas of modern
research and application. The purpose of this review is to provide an introduction to the core …
research and application. The purpose of this review is to provide an introduction to the core …
Statistical mechanics of deep learning
The recent striking success of deep neural networks in machine learning raises profound
questions about the theoretical principles underlying their success. For example, what can …
questions about the theoretical principles underlying their success. For example, what can …
[HTML][HTML] High-dimensional dynamics of generalization error in neural networks
We perform an analysis of the average generalization dynamics of large neural networks
trained using gradient descent. We study the practically-relevant “high-dimensional” regime …
trained using gradient descent. We study the practically-relevant “high-dimensional” regime …
Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks
A theoretical understanding of generalization remains an open problem for many machine
learning models, including deep networks where overparameterization leads to better …
learning models, including deep networks where overparameterization leads to better …
Bayes-optimal learning of deep random networks of extensive-width
We consider the problem of learning a target function corresponding to a deep, extensive-
width, non-linear neural network with random Gaussian weights. We consider the asymptotic …
width, non-linear neural network with random Gaussian weights. We consider the asymptotic …
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
Deep neural networks achieve stellar generalisation even when they have enough
parameters to easily fit all their training data. We study this phenomenon by analysing the …
parameters to easily fit all their training data. We study this phenomenon by analysing the …
[图书][B] Random fields for spatial data modeling
DT Hristopulos - 2020 - Springer
The series aims to: present current and emerging innovations in GIScience; describe new
and robust GIScience methods for use in transdisciplinary problem solving and decision …
and robust GIScience methods for use in transdisciplinary problem solving and decision …
Organizing memories for generalization in complementary learning systems
Memorization and generalization are complementary cognitive processes that jointly
promote adaptive behavior. For example, animals should memorize safe routes to specific …
promote adaptive behavior. For example, animals should memorize safe routes to specific …
Geometry of neural network loss surfaces via random matrix theory
J Pennington, Y Bahri - International conference on machine …, 2017 - proceedings.mlr.press
Understanding the geometry of neural network loss surfaces is important for the
development of improved optimization algorithms and for building a theoretical …
development of improved optimization algorithms and for building a theoretical …
A precise high-dimensional asymptotic theory for boosting and minimum--norm interpolated classifiers
A precise high-dimensional asymptotic theory for boosting and minimum-l1-norm
interpolated classifiers Page 1 The Annals of Statistics 2022, Vol. 50, No. 3, 1669–1695 …
interpolated classifiers Page 1 The Annals of Statistics 2022, Vol. 50, No. 3, 1669–1695 …