By using the framework of Determinantal Point Processes (DPPs), some theoretical results concerning the interplay between diversity and regularization can be obtained. In this paper we show that sampling subsets with kDPPs results in implicit regularization in the context of ridgeless Kernel Regression. Furthermore, we leverage the common setup of state-of-the-art DPP algorithms to sample multiple small subsets and use them in an ensemble of ridgeless regressions. Our first empirical results indicate that ensemble of ridgeless regressors can be interesting to use for datasets including redundant information.

In this paper, we establish the ordinary differential equation (ODE) that underlies the training dynamics of Model-Agnostic Meta-Learning (MAML). Our continuous-time limit view of the process eliminates the influence of the manually chosen step size of gradient descent and includes the existing gradient descent training algorithm as a special case that results from a specific discretization. We show that the MAML ODE enjoys a linear convergence rate to an approximate stationary point of the MAML loss function for strongly convex task losses, even when the corresponding MAML loss is non-convex. Moreover, through the analysis of the MAML ODE, we propose a new BI-MAML training algorithm that significantly reduces the computational burden associated with existing MAML training methods. To complement our theoretical findings, we perform empirical experiments to showcase the superiority of our proposed methods with respect to the existing work.

Network embedding is an influential graph mining technique for representing nodes in a graph as distributed vectors. However, the majority of network embedding methods focus on learning a single vector representation for each node, which has been recently criticized for not being capable of modeling multiple aspects of a node. To capture the multiple aspects of each node, existing studies mainly rely on offline graph clustering performed prior to the actual embedding, which results in the cluster membership of each node (i.e., node aspect distribution) fixed throughout training of the embedding model. We argue that this not only makes each node always have the same aspect distribution regardless of its dynamic context, but also hinders the end-to-end training of the model that eventually leads to the final embedding quality largely dependent on the clustering. In this paper, we propose a novel end-to-end framework for multi-aspect network embedding, called asp2vec, in which the aspects of each node are dynamically assigned based on its local context. More precisely, among multiple aspects, we dynamically assign a single aspect to each node based on its current context, and our aspect selection module is end-to-end differentiable via the Gumbel-Softmax trick. We also introduce the aspect regularization framework to capture the interactions among the multiple aspects in terms of relatedness and diversity. We further demonstrate that our proposed framework can be readily extended to heterogeneous networks. Extensive experiments towards various downstream tasks on various types of homogeneous networks and a heterogeneous network demonstrate the superiority of asp2vec.

Federated Learning (FL) has become a popular paradigm for learning from distributed data. To effectively utilize data at different devices without moving them to the cloud, algorithms such as the Federated Averaging (FedAvg) have adopted a "computation then aggregation" (CTA) model, in which multiple local updates are performed using local data, before sending the local models to the cloud for aggregation. However, these schemes typically require strong assumptions, such as the local data are identically independent distributed (i.i.d), or the size of the local gradients are bounded. In this paper, we first explicitly characterize the behavior of the FedAvg algorithm, and show that without strong and unrealistic assumptions on the problem structure, the algorithm can behave erratically for non-convex problems (e.g., diverge to infinity). Aiming at designing FL algorithms that are provably fast and require as few assumptions as possible, we propose a new algorithm design strategy from the primal-dual optimization perspective. Our strategy yields a family of algorithms that take the same CTA model as existing algorithms, but they can deal with the non-convex objective, achieve the best possible optimization and communication complexity while being able to deal with both the full batch and mini-batch local computation models. Most importantly, the proposed algorithms are {\it communication efficient}, in the sense that the communication pattern can be adaptive to the level of heterogeneity among the local data. To the best of our knowledge, this is the first algorithmic framework for FL that achieves all the above properties.

Failure of mission-critical equipment interrupts production and results in monetary loss. The risk of unplanned equipment downtime can be minimized through Predictive Maintenance of revenue generating assets to ensure optimal performance and safe operation of equipment. However, the increased sensorization of the equipment generates a data deluge, and existing machine-learning based predictive model alone becomes inadequate for timely equipment condition predictions. In this paper, a model-free Deep Reinforcement Learning algorithm is proposed for predictive equipment maintenance from an equipment-based sensor network context. Within each equipment, a sensor device aggregates raw sensor data, and the equipment health status is analyzed for anomalous events. Unlike traditional black-box regression models, the proposed algorithm self-learns an optimal maintenance policy and provides actionable recommendation for each equipment. Our experimental results demonstrate the potential for broader range of equipment maintenance applications as an automatic learning framework.

Time-Series involves temporal datasets that change over a period of time and time-based attributes are of paramount importance in these datasets. The trading prices of stocks change constantly over time, and reflect various unmeasured factors such as market confidence, external influences, and other driving forces that may be hard to identify or measure. There are hypothesis like the Efficient Market Hypothesis, which says that it is almost impossible to beat the market consistently and there are others which disagree with it. Forecasting the future value of a given stock is a crucial task as investing in stock market involves higher risk.. Here, given the historical daily close price for Dow-Jones Index, we would like to prepare and compare forecasting models. The black swan theory, which predicts that anomalous events, such as a stock market crash, are much more likely to occur than would be predicted by the normal distribution.

Python is and will be the leading language for data science and machine learning. The Python Data Science Handbook is the perfect book for boosting our Python skills. This is a perfect reference to keep close by for those frequent data manipulation tasks using Pandas. This book covers IPython, Numpy for computations, Data manipulation with Pandas, Data visualizations with Matplotlib, Machine learning with Scikit-Learn. It provides easy to understand explanations of concepts and coding examples with R. The book covers K-fold cross-validation, Regularization, Feature selection, Polynomial regression, Decision Trees, Support vector machines, Unsupervised learning i.e.

Hello guys, you may know that Machine Learning and Artificial Intelligence have become more and more important in this increasingly digital world. They are now providing a competitive edge to businesses like NetFlix's Movie recommendations. If you have just started in this field and looking for what to learn then I am going to share 5 essential Machine learning algorithms you can learn as a beginner. These essential algorithms form the basis of most common Machine learning projects and having a good knowledge of them will not only help you to understand the project and model quickly but also to change them as per your need. Machine learning by a simple word is the science or the field of making the computer learn like a human by feeding it with the data and without being programmed and it separate into two categories the first one is classification problems which the machine needs to classify between two objects or more like between human and animal and the second is regression problems which the machine need to produce an output based on a previous data.

The first principles approach to problem-solving is the act of breaking a problem down to the fundamental parts and building up from there. This method is well known to physicists dating back as far as the days of Aristotle. The first principles method is a very efficient method for problem-solving. Elon Musk (CEO of Tesla and SpaceX) is well known for applying the first principles method for solving technological and engineering problems. In this article, we discuss how the first principles method can be used to simplify data science tasks.

GANs, originally discovered in the context of unsupervised learning, have had far reaching implications to science, engineering, and society. However, training GANs remains challenging (in part) due to the lack of convergent algorithms for nonconvex-nonconcave min-max optimization. In this post, we present a new first-order algorithm for min-max optimization which is particularly suited to GANs. This algorithm is guaranteed to converge to an equilibrium, is competitive in terms of time and memory with gradient descent-ascent and, most importantly, GANs trained using it seem to be stable. Starting with the work of Goodfellow et al., Generative Adversarial Nets (GANs) have become a critical component in various ML systems; for prior posts on GANs, see here for a post on GAN architecture, and here and here for posts which discuss some of the many difficulties arising when training GANs.