Recently, I have been working with several projects related to NLP at work. Some of them had something to do with training the company's in-house word embedding. At work, the tasks were mostly done with the help of a Python library: gensim. However, I decided to implement a Word2vec model from scratch just with the help of Python and NumPy because reinventing the wheel is usually an awesome way to learn something deeply. Word embedding is nothing fancy but methods to represent words in a numerical way.

Electronic power inverters are capable of quickly delivering reactive power to maintain customer voltages within operating tolerances and to reduce system losses in distribution grids. This paper proposes a systematic and data-driven approach to determine reactive power inverter output as a function of local measurements in a manner that obtains near optimal results. First, we use a network model and historic load and generation data and do optimal power flow to compute globally optimal reactive power injections for all controllable inverters in the network. Subsequently, we use regression to find a function for each inverter that maps its local historical data to an approximation of its optimal reactive power injection. The resulting functions then serve as decentralized controllers in the participating inverters to predict the optimal injection based on a new local measurements. The method achieves near-optimal results when performing voltage- and capacity-constrained loss minimization and voltage flattening, and allows for an efficient volt-VAR optimization (VVO) scheme in which legacy control equipment collaborates with existing inverters to facilitate safe operation of distribution networks with higher levels of distributed generation.

In the age of data driven solution, the customer demographic attributes, such as gender and age, play a core role that may enable companies to enhance the offers of their services and target the right customer in the right time and place. In the marketing campaign, the companies want to target the real user of the GSM (global system for mobile communications), not the line owner. Where sometimes they may not be the same. This work proposes a method that predicts users' gender and age based on their behavior, services and contract information. We used call detail records (CDRs), customer relationship management (CRM) and billing information as a data source to analyze telecom customer behavior, and applied different types of machine learning algorithms to provide marketing campaigns with more accurate information about customer demographic attributes. This model is built using reliable data set of 18,000 users provided by SyriaTel Telecom Company, for training and testing. The model applied by using big data technology and achieved 85.6% accuracy in terms of user gender prediction and 65.5% of user age prediction. The main contribution of this work is the improvement in the accuracy in terms of user gender prediction and user age prediction based on mobile phone data and end-to-end solution that approaches customer data from multiple aspects in the telecom domain.

Predicting the direction of assets have been an active area of study and a difficult task. Machine learning models have been used to build robust models to model the above task. Ensemble methods is one of them showing results better than a single supervised method. In this paper, we have used generative and discriminative classifiers to create the stack, particularly 3 generative and 9 discriminative classifiers and optimized over one-layer Neural Network to model the direction of price cryptocurrencies. Features used are technical indicators used are not limited to trend, momentum, volume, volatility indicators, and sentiment analysis has also been used to gain useful insight combined with the above features. For Cross-validation, Purged Walk forward cross-validation has been used. In terms of accuracy, we have done a comparative analysis of the performance of Ensemble method with Stacking and Ensemble method with blending. We have also developed a methodology for combined features importance for the stacked model. Important indicators are also identified based on feature importance.

Febrile neutropenia (FN) has been associated with high mortality, especially among adults with cancer. Understanding the patient and provider level heterogeneity in FN hospital admissions has potential to inform personalized interventions focused on increasing survival of individuals with FN. We leverage machine learning techniques to disentangling the complex interactions among multi domain risk factors in a population with FN. Data from the Healthcare Cost and Utilization Project (HCUP) National Inpatient Sample and Nationwide Inpatient Sample (NIS) were used to build machine learning based models of mortality for adult cancer patients who were diagnosed with FN during a hospital admission. In particular, the importance of risk factors from different domains (including demographic, clinical, and hospital associated information) was studied. A set of more interpretable (decision tree, logistic regression) as well as more black box (random forest, gradient boosting, neural networks) models were analyzed and compared via multiple cross validation. Our results demonstrate that a linear prediction score of FN mortality among adults with cancer, based on admission information is effective in classifying high risk patients; clinical diagnoses is the domain with the highest predictive power. A number of the risk variables (e.g. sepsis, kidney failure, etc.) identified in this study are clinically actionable and may inform future studies looking at the patients prior medical history are warranted.

We study the performance of the certainty equivalent controller on the Linear Quadratic Regulator (LQR) with unknown transition dynamics. We show that the sub-optimality gap between the cost incurred by playing the certainty equivalent controller on the true system and the cost incurred by using the optimal LQR controller enjoys a fast statistical rate, scaling as the square of the parameter error. Our result improves upon recent work by Dean et al. (2017), who present an algorithm achieving a sub-optimality gap linear in the parameter error. A key part of our analysis relies on perturbation bounds for discrete Riccati equations. We provide two new perturbation bounds, one that expands on an existing result from Konstantinov et al. (1993), and another based on a new elementary proof strategy. Our results show that certainty equivalent control with $\varepsilon$-greedy exploration achieves $\tilde{\mathcal{O}}(\sqrt{T})$ regret in the adaptive LQR setting, yielding the first guarantee of a computationally tractable algorithm that achieves nearly optimal regret for adaptive LQR.

A popular approach for predicting the future of dynamical systems involves mapping them into a lower-dimensional "latent space" where prediction is easier. We show that the information-theoretically optimal approach uses different mappings for present and future, in contrast to state-of-the-art machine-learning approaches where both mappings are the same. We illustrate this dichotomy by predicting the time-evolution of coupled harmonic oscillators with dissipation and thermal noise, showing how the optimal 2-mapping method significantly outperforms principal component analysis and all other approaches that use a single latent representation, and discuss the intuitive reason why two representations are better than one. We conjecture that a single latent representation is optimal only for time-reversible processes, not for e.g. text, speech, music or out-of-equilibrium physical systems.

The increasing occurrence of ordinal data, mainly sociodemographic, led to a renewed research interest in ordinal regression, i.e. the prediction of ordered classes. Besides model accuracy, the interpretation of these models itself is of high relevance, and existing approaches therefore enforce e.g. model sparsity. For high dimensional or highly correlated data, however, this might be misleading due to strong variable dependencies. In this contribution, we aim for an identification of feature relevance bounds which - besides identifying all relevant features - explicitly differentiates between strongly and weakly relevant features.

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a function $f$, a point $x$, and the gradient $\nabla_x f$ of $f$, we aim to find the step-size $h$ which is (locally) optimal, i.e. satisfies: $$ h=arg\,min_{t \geq 0} f(x-t \nabla_x f). $$ Making use of quadratic approximation, we show that the algorithm satisfies the above assumption. We experimentally show that our method is insensitive to the choice of initial learning rate while achieving results comparable to other methods.

Pre-conditioning is a well-known concept that can significantly improve the convergence of optimization algorithms. For noise-free problems, where good pre-conditioners are not known a priori, iterative linear algebra methods offer one way to efficiently construct them. For the stochastic optimization problems that dominate contemporary machine learning, however, this approach is not readily available. We propose an iterative algorithm inspired by classic iterative linear solvers that uses a probabilistic model to actively infer a pre-conditioner in situations where Hessian-projections can only be constructed with strong Gaussian noise. The algorithm is empirically demonstrated to efficiently construct effective pre-conditioners for stochastic gradient descent and its variants. Experiments on problems of comparably low dimensionality show improved convergence. In very high-dimensional problems, such as those encountered in deep learning, the pre-conditioner effectively becomes an automatic learning-rate adaptation scheme, which we also empirically show to work well.