Stock market volatility forecasting is a task relevant to assessing market risk. We investigate the interaction between news and prices for the one-day-ahead volatility prediction using state-of-the-art deep learning approaches. The proposed models are trained either end-to-end or using sentence encoders transfered from other tasks. We evaluate a broad range of stock market sectors, namely Consumer Staples, Energy, Utilities, Heathcare, and Financials. Our experimental results show that adding news improves the volatility forecasting as compared to the mainstream models that rely only on price data. In particular, our model outperforms the widely-recognized GARCH(1,1) model for all sectors in terms of coefficient of determination $R^2$, $MSE$ and $MAE$, achieving the best performance when training from both news and price data.

Privacy-preserving distributed machine learning has become more important than ever due to the high demand of large-scale data processing. This paper focuses on a class of machine learning problems that can be formulated as regularized empirical risk minimization, and develops a privacy-preserving learning approach to such problems. We use Alternating Direction Method of Multipliers (ADMM) to decentralize the learning algorithm, and apply Gaussian mechanisms to provide differential privacy guarantee. However, simply combining ADMM and local randomization mechanisms would result in a nonconvergent algorithm with poor performance even under moderate privacy guarantees. Besides, this intuitive approach requires a strong assumption that the objective functions of the learning problems should be differentiable and strongly convex. To address these concerns, we propose an improved ADMM-based Differentially Private distributed learning algorithm, DP-ADMM, where an approximate augmented Lagrangian function and Gaussian mechanisms with time-varying variance are utilized. We also apply the moments accountant method to bound the total privacy loss. Our theoretical analysis shows that DP-ADMM can be applied to a general class of convex learning problems, provides differential privacy guarantee, and achieves a convergence rate of $O(1/\sqrt{t})$, where $t$ is the number of iterations. Our evaluations demonstrate that our approach can achieve good convergence and accuracy with moderate privacy guarantee.

Functional data analysis is a statistical framework where data are assumed to follow some functional form. This method of analysis is commonly applied to time series data, where time, measured continuously or in discrete intervals, serves as the location for a function's value. Gaussian processes are a generalization of the multivariate normal distribution to function space and, in this paper, they are used to shed light on coastal rainfall patterns in British Columbia (BC). Specifically, this work addressed the question over how one should carry out an exploratory cluster analysis for the BC, or any similar, coastal rainfall data. An approach is developed for clustering multiple processes observed on a comparable interval, based on how similar their underlying covariance kernel is. This approach provides significant insights into the BC data, and these insights can be described in terms of El Nino and La Nina; however, the result is not simply one cluster representing El Nino years and another for La Nina years. From one perspective, the results show that clustering annual rainfall can potentially be used to identify extreme weather patterns.

Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings. IC3Net controls continuous communication with a gating mechanism and uses individualized rewards foreach agent to gain better performance and scalability while fixing credit assignment issues. Using variety of tasks including StarCraft BroodWars explore and combat scenarios, we show that our network yields improved performance and convergence rates than the baselines as the scale increases. Our results convey that IC3Net agents learn when to communicate based on the scenario and profitability.

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between solving two sub-problems: (i) learn a phoneme classifier for a given set of phoneme segmentation boundaries, and (ii) refining the phoneme boundaries based on a given classifier. To solve the first sub-problem, we introduce a novel unsupervised cost function named Segmental Empirical Output Distribution Matching, which generalizes the work in (Liu et al., 2017) to segmental structures. For the second sub-problem, we develop an approximate MAP approach to refining the boundaries obtained from Wang et al. (2017). Experimental results on TIMIT dataset demonstrate the success of this fully unsupervised phoneme recognition system, which achieves a phone error rate (PER) of 41.6%. Although it is still far away from the state-of-the-art supervised systems, we show that with oracle boundaries and matching language model, the PER could be improved to 32.5%.This performance approaches the supervised system of the same model architecture, demonstrating the great potential of the proposed method.

Last July, photographer Reuben Wu and a crew of around 30 people hiked from the Peruvian city of Huaraz, nestled in the Cordillera Blanca region of the Andes, to the 16,000-foot-high Pastoruri glacier. The hike took around four hours and the crew arrived after sunset, finding the melting glacier lit only by a full moon. These Stitched Photos of Greenland's Icebergs Are Sew Great Wu has shot conceptual landscape photography in some of the world's most remote locations--East Java, Patagonia, Chile's Atacama Desert, Norway's Svalbard Archipelago--but this shoot, part of a mini-documentary about Wu's photography done as part of a Coors Light ad campaign, gave him the opportunity to highlight global warming by photographing a fast-receding glacier, one of the last in South America. "There were parts of the glacier where you could see evidence of pretty extreme breakdown and melting of the snow," Wu says. "Parts of the glacier no longer had the epic, jagged chunks of ice."

Depression is ranked as the largest contributor to global disability and is also a major reason for suicide. Still, many individuals suffering from forms of depression are not treated for various reasons. Previous studies have shown that depression also has an effect on language usage and that many depressed individuals use social media platforms or the internet in general to get information or discuss their problems. This paper addresses the early detection of depression using machine learning models based on messages on a social platform. In particular, a convolutional neural network based on different word embeddings is evaluated and compared to a classification based on user-level linguistic metadata. An ensemble of both approaches is shown to achieve state-of-the-art results in a current early detection task. Furthermore, the currently popular ERDE score as metric for early detection systems is examined in detail and its drawbacks in the context of shared tasks are illustrated. A slightly modified metric is proposed and compared to the original score. Finally, a new word embedding was trained on a large corpus of the same domain as the described task and is evaluated as well.

In a recent article, Santiago Siri, the founder of Democracy Earth Foundation, talks about internet giants and how they have been taking Orwellian measures to control the whole network through artificial intelligence (AI). He also discusses how crypto could play an important role for individuals to defend against this. According to him, AI seems to be a threat to humanity. Something that Elon Musk and Sam Altman usually warn. Additionally, social algorithms have been growing all over the internet and are able to explain today's political reality.

Stagnation in the proportion of women in the workplace and women's declining representation in politics, coupled with greater inequality in access to health and education, offset improvements in wage equality and the number of women in professional positions, leaving the global gender gap only slightly reduced in 2018. This is according to the Forum's Global Gender Gap Report 2018, published today. According to the report, the world has closed 68% of its gender gap, as measured across four key pillars: economic opportunity; political empowerment; educational attainment; and health and survival. While only a marginal improvement on 2017, the move is nonetheless welcome as 2017 was the first year since the report was first published in 2006 that the gap between men and women widened. At the current rate of change, the data suggest that it will take 108 years to close the overall gender gap and 202 years to bring about parity in the workplace.

Every day at around 4 p.m., the creeeek criikkk of stretched packing tape echoes through Huaqiangbei, Shenzhen's sprawling neighborhood of hardware stores. Shopkeepers package up the day's sales--selfie sticks, fidget spinners, electric scooters, drones--and by 5, crowds of people are on the move at the rapid pace locals call Shenzhen sudu, or "Shenzhen speed," carting boxes out on motorcycles, trucks, and--if it's a light order--zippy balance boards. From Huaqiangbei the boxes are brought to the depots of global logistics companies and loaded onto airplanes and cargo ships. In the latter case they join 24 million metric tons of container cargo going out every month from Shekou harbor--literally "snake's mouth," the world's third-busiest shipping port after Shanghai and Singapore. A few days or weeks later, the boxes arrive in destinations as nearby as Manila and Phnom Penh and as far afield as Dubai, Buenos Aires, Lagos, and Berlin. They appear in the world's largest cities and smallest villages: selfie sticks held up in front of Indian temples, a (rebranded) Xiaomi electric scooter cruising down San Francisco's Market Street, and a DJI drone flying over pretty much anywhere.