stochQN0.1.2-1 package

Stochastic Limited Memory Quasi-Newton Optimizers

adaQN

adaQN guided optimizer

adaQN_free

adaQN Free-Mode Optimizer

coef.stoch_logistic

Retrieve fitted coefficients from stochastic logistic regression objec...

get_curr_x

Get current values of the optimization variables

get_iteration_number

Get current iteration number from the optimizer object

oLBFGS

oLBFGS guided optimizer

oLBFGS_free

oLBFGS Free-Mode Optimizer

partial_fit

Partial fit stochastic model to new data

partial_fit_logistic

Update stochastic logistic regression model with new batch of data

predict.stoch_logistic

Prediction function for stochastic logistic regression

predict.stochQN_guided

Predict function for stochastic optimizer object

print.adaQN

Print summary info about adaQN guided-mode object

print.adaQN_free

Print summary info about adaQN free-mode object

print.oLBFGS

Print summary info about oLBFGS guided-mode object

print.oLBFGS_free

Print summary info about oLBFGS free-mode object

print.SQN

Print summary info about SQN guided-mode object

print.SQN_free

Print summary info about SQN free-mode object

print.stoch_logistic

Print general info about stochastic logistic regression object

run_adaQN_free

Run adaQN optimizer in free-mode

run_oLBFGS_free

Run oLBFGS optimizer in free-mode

run_SQN_free

Run SQN optimizer in free-mode

SQN

SQN guided optimizer

SQN_free

SQN Free-Mode Optimizer

stochastic.logistic.regression

Stochastic Logistic Regression

summary.stoch_logistic

Print general info about stochastic logistic regression object

update_fun

Update objective function value (adaQN)

update_gradient

Update gradient (oLBFGS, SQN, adaQN)

update_hess_vec

Update Hessian-vector product (SQN)

Implementations of stochastic, limited-memory quasi-Newton optimizers, similar in spirit to the LBFGS (Limited-memory Broyden-Fletcher-Goldfarb-Shanno) algorithm, for smooth stochastic optimization. Implements the following methods: oLBFGS (online LBFGS) (Schraudolph, N.N., Yu, J. and Guenter, S., 2007 <http://proceedings.mlr.press/v2/schraudolph07a.html>), SQN (stochastic quasi-Newton) (Byrd, R.H., Hansen, S.L., Nocedal, J. and Singer, Y., 2016 <arXiv:1401.7020>), adaQN (adaptive quasi-Newton) (Keskar, N.S., Berahas, A.S., 2016, <arXiv:1511.01169>). Provides functions for easily creating R objects with partial_fit/predict methods from some given objective/gradient/predict functions. Includes an example stochastic logistic regression using these optimizers. Provides header files and registered C routines for using it directly from C/C++.

  • Maintainer: David Cortes
  • License: BSD_2_clause + file LICENSE
  • Last published: 2021-09-26