Search

Automl is the key technology for machine learning problem. Current state of art hyperparameter optimization methods are based on traditional black-box optimization methods like SMBO (SMAC, TPE). The objective function of black-box optimization is non-smooth, or time-consuming to evaluate, or in some way noisy. Recent years, many researchers offered the work about the properties of hyperparameters. However, traditional hyperparameter optimization methods do not take those information into consideration. In this paper, we use gradient information and machine learning model analysis information to accelerate traditional hyperparameter optimization methods SMBO. In our L2 norm experiments, our method yielded state-of-the-art performance, and in many cases outperformed the previous best configuration approach.

In AI research and industry, machine learning is the most widely used tool. One of the most important machine learning algorithms is Gradient Boosting Decision Tree, i.e. GBDT whose training process needs considerable computational resources and time. To shorten GBDT training time, many works tried to apply GBDT on Parameter Server. However, those GBDT algorithms are synchronous parallel algorithms which fail to make full use of Parameter Server. In this paper, we examine the possibility of using asynchronous parallel methods to train GBDT model and name this algorithm as asynch-SGBDT (asynchronous parallel stochastic gradient boosting decision tree). Our theoretical and experimental results indicate that the scalability of asynch-SGBDT is influenced by the sample diversity of datasets, sampling rate, step length and the setting of GBDT tree. Experimental results also show asynch-SGBDT training process reaches a linear speedup in asynchronous parallel manner when datasets and GBDT trees meet high scalability requirements.

In recent decades, the amount of waste produced by humans has increased greatly. Society demands increasingly high standards of production and quality, leading to the production of greater volumes of waste and consequent increases in the associated risks of contamination. There is international concern regarding the management of all types of wastes and the consequent environmental degradation and public health risks. Land application of wastes, such as animal excrement or vegetable residues, has been carried out since long time ago. However, many environmental problems have now appeared primary because the final goal of the addition of wastes to soils is often the elimination of wastes rather than the enhancement of soil fertility or improvement of soil physical properties. The objective of this thesis was to evaluate the suitability of anthropogeomorphic wastes as soil amendment or fertilizer. For this, different studies have been carried out and described in six chapters: four of them describe the study of Technosols and the other two describe the geochemical accelerated weathering study of biochar and biomass fly ash.