منابع مشابه
Online Variance-reducing Optimization
We emphasize the importance of variance reduction in stochastic methods and propose a probabilistic interpretation as a way to store information about past gradients. The resulting algorithm is very similar to the momentum method, with the difference that the weight over past gradients depends on the distance moved in parameter space rather than the number of steps.
متن کاملOnline Minimization Knapsack Problem
In this paper, we address the online minimization knapsack problem, i. e., the items are given one by one over time and the goal is to minimize the total cost of items that covers a knapsack. We study the removable model, where it is allowed to remove old items from the knapsack in order to accept a new item. We obtain the following results. (i) We propose an 8-competitive deterministic algorit...
متن کاملOnline submodular minimization
We consider an online decision problem over a discrete space in which the loss function is submodular. We give algorithms which are computationally efficient and are Hannan-consistent in both the full information and bandit settings.
متن کاملVariance-minimization scheme for optimizing Jastrow factors
We describe a scheme for optimizing many-electron trial wave functions by minimizing the unreweighted variance of the energy using stochastic integration and correlated-sampling techniques. The scheme is restricted to parameters that are linear in the exponent of a Jastrow correlation factor, which are the most important parameters in the wave functions we use. The scheme is highly efficient an...
متن کاملA Probability Sampling Approach for Variance Minimization
A number of techniques for probability sampling without replacement (SWOR) have been suggested, although it is not clear which method is consistently superior in terms of statistical efficiency. Rao and Bayless (1969) empirically studied the stability of estimators of the population total for a variety of methods of unequal probability SWOR when selecting two units per stratum. One of their maj...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Machine Learning
سال: 2011
ISSN: 0885-6125,1573-0565
DOI: 10.1007/s10994-011-5269-0