We consider stochastic second order methods for minimizing strongly-convex functions under an interpolation condition satisfied by over-parameterized models. Under this condition, we show that the regularized sub-sampled Newton method (R-SSN) achieves global linear convergence with an adaptive step size and a constant batch size. By growing the batch size for both the sub-sampled gradient and Hessian, we show that R-SSN can converge at a quadratic rate in a local neighbourhood of the solution. We also show that R-SSN attains local linear convergence for the family of self-concordant functions. Furthermore, we analyse stochastic BFGS algorithms in the interpolation setting and prove their global linear convergence. We empirically evaluate stochastic L-BFGS and a "Hessian-free" implementation of R-SSN for binary classification on synthetic, linearly-separable datasets and consider real medium-size datasets under a kernel mapping. Our experimental results show the fast convergence of these methods both in terms of the number of iterations and wall-clock time.

Hierarchical Reinforcement Learning (HRL) is a promising approach to solving long-horizon problems with sparse and delayed rewards. Many existing HRL algorithms either use pre-trained low-level skills that are unadaptable, or require domain-specific information to define low-level rewards. In this paper, we aim to adapt low-level skills to downstream tasks while maintaining the generality of reward design. We propose an HRL framework which sets auxiliary rewards for low-level skill training based on the advantage function of the high-level policy. This auxiliary reward enables efficient, simultaneous learning of the high-level policy and low-level skills without using task-specific knowledge. In addition, we also theoretically prove that optimizing low-level skills with this auxiliary reward will increase the task return for the joint policy. Experimental results show that our algorithm dramatically outperforms other state-of-the-art HRL methods in Mujoco domains. We also find both low-level and high-level policies trained by our algorithm transferable.

Recent studies on catastrophic forgetting during sequential learning typically focus on fixing the accuracy of the predictions for a previously learned task. In this paper we argue that the outputs of neural networks are subject to rapid changes when learning a new data distribution, and networks that appear to "forget" everything still contain useful representation towards previous tasks. Instead of enforcing the output accuracy to stay the same, we propose to reduce the effect of catastrophic forgetting on the representation level, as the output layer can be quickly recovered later with a small number of examples. Towards this goal, we propose an experimental setup that measures the amount of representational forgetting, and develop a novel meta-learning algorithm to overcome this issue. The proposed meta-learner produces weight updates of a sequential learning network, mimicking a multi-task teacher network's representation. We show that our meta-learner can improve its learned representations on new tasks, while maintaining a good representation for old tasks.

We consider the problem of manifold learning. Extending existing approaches of learning from randomly sampled data points, we consider contexts where data may be chosen by a teacher. We analyze learning from teachers who can provide structured data such as points, comparisons (pairs of points), demonstrations (sequences). We prove results showing that the former two do not yield notable decreases in the amount of data required to infer a manifold. Teaching by demonstration can yield remarkable decreases in the amount of data required, if we allow the goal to be teaching up to topology. We further analyze teaching learners in the context of persistence homology. Teaching topology can greatly reduce the number of datapoints required to infer correct geometry, and allows learning from teachers who themselves do not have full knowledge of the true manifold. We conclude with implications for learning in humans and machines.

This paper considers a variant of the classical online learning problem with expert predictions. Our model's differences and challenges are due to lacking any direct feedback on the loss each expert incurs at each time step $t$. We propose an approach that uses peer assessment and identify conditions where it succeeds. Our techniques revolve around a carefully designed peer score function $s()$ that scores experts' predictions based on the peer consensus. We show a sufficient condition, that we call \emph{peer calibration}, under which standard online learning algorithms using loss feedback computed by the carefully crafted $s()$ have bounded regret with respect to the unrevealed ground truth values. We then demonstrate how suitable $s()$ functions can be derived for different assumptions and models.

Our research aims to develop interactive, social agents that can coach people to learn new tasks, skills, and habits. In this paper, we focus on coaching sedentary, overweight individuals (i.e., trainees) to exercise regularly. We employ adaptive goal setting in which the intelligent health coach generates, tracks, and revises personalized exercise goals for a trainee. The goals become incrementally more difficult as the trainee progresses through the training program. Our approach is model-based - the coach maintains a parameterized model of the trainee's aerobic capability that drives its expectation of the trainee's performance. The model is continually revised based on trainee-coach interactions. The coach is embodied in a smartphone application, NutriWalking, which serves as a medium for coach-trainee interaction. We adopt a task-centric evaluation approach for studying the utility of the proposed algorithm in promoting regular aerobic exercise. We show that our approach can adapt the trainee program not only to several trainees with different capabilities, but also to how a trainee's capability improves as they begin to exercise more. Experts rate the goals selected by the coach better than other plausible goals, demonstrating that our approach is consistent with clinical recommendations. Further, in a 6-week observational study with sedentary participants, we show that the proposed approach helps increase exercise volume performed each week.

We seek causes through science, religion, and in everyday life. We get excited when a big rock causes a big splash, and we get scared when it tumbles without a cause. But our causal cognition is usually biased. The 'why' is influenced by the 'who'. It is influenced by the 'self', and by 'others'. We share rituals, we watch action movies, and we influence each other to believe in the same causes. Human mind is packed with subjectivity because shared cognitive biases bring us together. But they also make us vulnerable. An artificial mind is deemed to be more objective than the human mind. After many years of science-fiction fantasies about even-minded androids, they are now sold as personal or expert assistants, as brand advocates, as policy or candidate supporters, as network influencers. Artificial agents have been stunningly successful in disseminating artificial causal beliefs among humans. As malicious artificial agents continue to manipulate human cognitive biases, and deceive human communities into ostensive but expansive causal illusions, the hope for defending us has been vested into developing benevolent artificial agents, tasked with preventing and mitigating cognitive distortions inflicted upon us by their malicious cousins. Can the distortions of human causal cognition be corrected on a more solid foundation of artificial causal cognition? In the present paper, we study a simple model of causal cognition, viewed as a quest for causal models. We show that, under very mild and hard to avoid assumptions, there are always self-confirming causal models, which perpetrate self-deception, and seem to preclude a royal road to objectivity.

Posted By C. M. Rubin on Oct 9, 2019 "We added "Artificial Intelligence" to "Robotics & STEM" this year because it is an important and timely topic for young people to learn about." Prior to joining the Girls of Steel Robotics Program at Carnegie Mellon University's (CMU) Field Robotics Center, Theresa Richards was a science teacher in Pittsburgh where she created an award-winning lesson integrating robotics into a Human Anatomy and Physiology course. The problem her organization is trying to solve is the demand for more people in STEM, and in particular, women. A December 2018 report in Pittsburgh shows there are 80,000 STEM jobs currently available. "We believe that building robots builds confidence in STEM," says Richards.

Editor's Note: SHRM has partnered with TrainingIndustry.com to bring you relevant articles on key HR topics and strategies. The National Center for Women in Technology (NCWIT) predicts that while there will be 3.5 million "computing-related" jobs in the U.S. by 2026, 83% of them could go unfilled due to a lack of college graduates with related degrees. To meet this demand, organizations must reskill their workforces and look to candidates who have learned in-demand technical skills through alternate forms of education. In recent years, coding bootcamps have succeeded in training a diverse group of workers for careers as web, full-stack and software developers, among other roles, as well as reskilling people already in those professions. However, several major coding bootcamps have also closed in recent years, including Dev Bootcamp and The Iron Yard in 2017.

Rachelle Dene Poth is an educator, attorney, consultant, and author who is concentrated on making a difference throughout the education space. Poth, who recently received the Making IT Happen Award from ISTE and the Presidential Gold Award for volunteer service, will be a featured speaker at the 2020 Future of Education Technology Conference (FETC 2020), this coming January in Miami. Poth has taken her diverse array of professional experiences into the classroom to motivate 8th grade students to engage in their learning, even when it takes them a little time to discover the relevance. In terms of motivation, she explains, "I ask 8th graders to be receptive to ideas. It's not just'I want you just to do this because I say you have to do this.' It's, 'I want you to do this as a start to see what other interests stir in you.'"