## Quasi-Newton methods: L-BFGS

BFGS In this previous post, we described how Quasi-Newton methods can be used to minimize a twice-differentiable function whose domain is all of . BFGS is a popular quasi-Newton method. At each iteration, we take the following steps: Solve for in . Update with . Update according to the equation where and . Limited memory […]

Quasi-Newton methods: L-BFGS

## Affine hull vs. convex hull

The affine hull and convex hull are closely related concepts. Let be a set in . The affine hull of is the set of all affine combinations of elements of : The convex hull of is the set of all convex combinations of the elements of : Putting the definitions side by side, we see […]

Affine hull vs. convex hull

## What are the KKT conditions?

Consider an optimization problem in standard form: with the variable . Assume that the ‘s and ‘s are differentiable. (At this point, we are not assuming anything about their convexity.) As before, define the Lagrangian as the function Let and be the primal and dual optimal points respectively (i.e. points where the primal and dual […]

What are the KKT conditions?

## Lagrange dual, weak duality and strong duality

Consider an optimization problem in standard form: with the variable . Let be the domain for , i.e. the intersection of the domains of the ‘s and the ‘s. Let denote the optimal value of the problem. The Lagrange dual function is the function defined as the minimum value of the Lagrangian over : The […]

Lagrange dual, weak duality and strong duality

## SUPUESTOS DEL MODELO CLÁSICO DE REGRESIÓN LINEAL Y DE LOS MODELOS LINEALES GENERALIZADOS

### REFERENCIAS

Banerjee, A. (29 de Octubre de 2019). Intuition behind model fitting: Overfitting v/s Underfitting. Obtenido de Towards Data Science: https://towardsdatascience.com/intuition-behind-model-fitting-overfitting-v-s-underfitting-d308c21655c7

Bhuptani, R. (13 de Julio de 2020). Quora. Obtenido de What is the difference between linear regression and least squares?: https://www.quora.com/What-is-the-difference-between-linear-regression-and-least-squares

Cross Validated. (23 de Marzo de 2018). Will log transformation always mitigate heteroskedasticity? Obtenido de StackExchange: https://stats.stackexchange.com/questions/336315/will-log-transformation-always-mitigate-heteroskedasticity

Greene, W. (2012). Econometric Analysis (Séptima ed.). Harlow, Essex, England: Pearson Education Limited.

Guanga, A. (11 de Octubre de 2018). Machine Learning: Bias VS. Variance. Obtenido de Becoming Human: Artificial Intelligence Magazine: https://becominghuman.ai/machine-learning-bias-vs-variance-641f924e6c57

Gujarati, D., & Porter, D. (8 de Julio de 2010). Econometría (Quinta ed.). México, D.F.: McGrawHill Educación. Obtenido de Homocedasticidad.

McCullagh, P., & Nelder, J. A. (1989). Generalized Linear Models (Segunda ed.). London: Chapman and Hall.

MIT Computer Science & Artificial Intelligence Lab. (6 de Mayo de 2021). Solving over- and under-determined sets of equations. Obtenido de Articles: http://people.csail.mit.edu/bkph/articles/Pseudo_Inverse.pdf

Penn State University, Eberly College of Science. (2018). 10.4 – Multicollinearity. Obtenido de Lesson 10: Regression Pitfalls: https://online.stat.psu.edu/stat462/node/177/

Penn State University, Eberly College of Science. (24 de Mayo de 2021). Introduction to Generalized Linear Models. Obtenido de Analysis of Discrete Data: https://online.stat.psu.edu/stat504/lesson/6/6.1

Perezgonzalez, J. D. (3 de Marzo de 2015). Fisher, Neyman-Pearson or NHST? A tutorial for teaching data testing. frontiers in PSYCHOLOGY, VI(223), 1-11.

ResearchGate. (10 de Noviembre de 2014). How it can be possible to fit the four-parameter Fedlund model by only 3 PSD points? Obtenido de https://www.researchgate.net/post/How_it_can_be_possible_to_fit_the_four-parameter_Fedlund_model_by_only_3_PSD_points

ResearchGate. (28 de Septiembre de 2019). s there a rule for how many parameters I can fit to a model, depending on the number of data points I use for the fitting? Obtenido de https://www.researchgate.net/post/Is-there-a-rule-for-how-many-parameters-I-can-fit-to-a-model-depending-on-the-number-of-data-points-I-use-for-the-fitting

Salmerón Gómez, R., Blanco Izquierdo, V., & García García, C. (2016). Micronumerosidad aproximada y regresión lineal múltiple. Anales de ASEPUMA(24), 1-17. Obtenido de https://dialnet.unirioja.es/descarga/articulo/6004585.pdf

Simon Fraser University. (30 de Septiembre de 2011). THE CLASSICAL MODEL. Obtenido de http://www.sfu.ca/~dsignori/buec333/lecture%2010.pdf

StackExchange Cross Validated. (2 de Febrero de 2017). “Least Squares” and “Linear Regression”, are they synonyms? Obtenido de What is the difference between least squares and linear regression? Is it the same thing?: https://stats.stackexchange.com/questions/259525/least-squares-and-linear-regression-are-they-synonyms

Wikipedia. (18 de Marzo de 2021). Overdetermined system. Obtenido de Partial Differential Equations: https://en.wikipedia.org/wiki/Overdetermined_system

Zhao, J. (9 de Noviembre de 2017). More features than data points in linear regression? Obtenido de Medium: https://medium.com/@jennifer.zzz/more-features-than-data-points-in-linear-regression-5bcabba6883e

## SOBRE LOS ESTIMADORES DE BAYES, EL ANÁLISIS DE GRUPOS Y LAS MIXTURAS GAUSSIANAS

Un Análisis Teórico General del Paquete densityMclust del programa estadístico R