We now turn to understanding the impact that COVID-19 had on the personal productivity and well-being of information workers as their work practices were impacted by remote work. This chapter overviews people's productivity, satisfaction, and work patterns, and shows that the challenges and benefits of remote work are closely linked. Looking forward, the infrastructure surrounding work will need to evolve to help people adapt to the challenges of remote and hybrid work.

In real-world applications of large-scale time series, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such heterogeneity, training a forecasting model with commonly used stochastic optimizers (e.g. SGD) potentially suffers large gradient variance, and thus requires long time training. To alleviate this issue, we propose a sampling strategy named Subgroup Sampling, which mitigates the large variance via sampling over pre-grouped time series. We further introduce SCott, a variance reduced SGD-style optimizer that co-designs subgroup sampling with the control variate method. In theory, we provide the convergence guarantee of SCott on smooth non-convex objectives. Empirically, we evaluate SCott and other baseline optimizers on both synthetic and real-world time series forecasting problems, and show SCott converges faster with respect to both iterations and wall clock time. Additionally, we show two SCott variants that can speed up Adam and Adagrad without compromising generalization of forecasting models.

The game is as wide as the Pacific Ocean at the beginning of a rookie's R6 tenure. There's always a new operator to learn, a new gadget interaction to test, a new strategy to try, and the horizon is constantly expanding. Put bluntly, players must do a lot of homework and suffer tens, if not hundreds of hours worth of hard-learned lessons before they feel they can contribute competently. On one hand, the game's complexity is its biggest appeal, on the other, it's a significant barrier to expanding its player base. While that number is massive, numbering 70 as of this year, could this ongoing expanse and evolution eventually case that player base to stagnate?

Abstract: Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evaluation measures in order to make quantifiable and generalizable progress in this area.

This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM). In SDM, the occurrence pattern of a species on a landscape is predicted by environmental features based on observations at a set of locations. At first, SDM may appear to be a binary classification problem, and one might be inclined to employ classic tools (e.g., logistic regression, support vector machines, neural networks) to tackle it. However, wildlife surveys introduce structured noise (especially under-counting) in the species observations. If unaccounted for, these observation errors systematically bias SDMs. To address the unique challenges of SDM, this paper proposes a framework called StatEcoNet. Specifically, this work employs a graphical generative model in statistical ecology to serve as the skeleton of the proposed computational framework and carefully integrates neural networks under the framework. The advantages of StatEcoNet over related approaches are demonstrated on simulated datasets as well as bird species data. Since SDMs are critical tools for ecological science and natural resource management, StatEcoNet may offer boosted computational and analytical powers to a wide range of applications that have significant social impacts, e.g., the study and conservation of threatened species.

Combining drone imagery with weather data and planting schemes to forecast how much fresh vegetables a harvest is going to yield; that's what predictive modelling intern Berend Klaver from TU Delft is sweating on at VanBoven, while his bosses are entertaining the American west coast. VanBoven is one of the ten winners of the Academic Startup Competition 2020, currently on tour in Silicon Valley for a 4-week incubator programme. "The market of fresh vegetables is one of constant shortages and surpluses. VanBoven predicts the harvest of fresh produce to perfectly align supply and demand. The result is decreased food waste, a resilient value chain and fair prices," says the startup on its website.

Seniors and first responders try to snag one of 800 doses available at a vaccination site in Fort Myers, Fla. Octavio Jones/Getty Images hide caption Seniors and first responders try to snag one of 800 doses available at a vaccination site in Fort Myers, Fla. With millions of older Americans eligible for coronavirus vaccines and limited supplies, many continue to describe a frantic and frustrating search to secure a shot, beset by uncertainty and difficulty. The efforts to vaccinate people who are 65 and older have strained under the enormous demand that has overwhelmed cumbersome, inconsistent scheduling systems. The struggle represents a shift from the first wave of vaccinations -- health care workers in health care settings -- which went comparatively smoothly. Now, in most places, elderly people are pitted against each other competing on an unstable technological playing field for limited shots.

One of the earliest images in Natalia Almada's virtuoso documentary Users is of an infant, tightly wrapped and strapped to a Snoo smart crib, robotically being rocked to sleep to the sound of manufactured white noise. By recreating many of the sensations of being in the womb, the Snoo has become a popular gadget for new parents who need help tucking their little ones in. In many ways, it's the pinnacle of a smart gadget: Developed by Dr. Harvey Karp, with product design by the renowned Yves Behar, the Snoo solves a problem that parents have faced for millennia. But what do we lose if a robot can automatically soothe a crying baby, effectively replacing a nurturing parent. That's the question at the heart of Users, which premiered at the Sundance Film Festival this week.

In many cases, it is difficult to generate highly accurate models for time series data using a known parametric model structure. In response, an increasing body of research focuses on using neural networks to model time series approximately. A common assumption in training neural networks on time series is that the errors at different time steps are uncorrelated. However, due to the temporality of the data, errors are actually autocorrelated in many cases, which makes such maximum likelihood estimation inaccurate. In this paper, we propose to learn the autocorrelation coefficient jointly with the model parameters in order to adjust for autocorrelated errors. For time series regression, large-scale experiments indicate that our method outperforms the Prais-Winsten method, especially when the autocorrelation is strong. Furthermore, we broaden our method to time series forecasting and apply it with various state-of-the-art models. Results across a wide range of real-world datasets show that our method enhances performance in almost all cases.

We consider the problem of forecasting multiple values of the future of a vector time series, using some past values. This problem, and related ones such as one-step-ahead prediction, have a very long history, and there are a number of well-known methods for it, including vector auto-regressive models, state-space methods, multi-task regression, and others. Our focus is on low rank forecasters, which break forecasting up into two steps: estimating a vector that can be interpreted as a latent state, given the past, and then estimating the future values of the time series, given the latent state estimate. We introduce the concept of forecast consistency, which means that the estimates of the same value made at different times are consistent. We formulate the forecasting problem in general form, and focus on linear forecasters, for which we propose a formulation that can be solved via convex optimization. We describe a number of extensions and variations, including nonlinear forecasters, data weighting, the inclusion of auxiliary data, and additional objective terms. We illustrate our methods with several examples.