About this course: What is machine learning, and what kinds of problems can it solve? Google thinks about machine learning slightly differently -- of being about logic, rather than just data. We talk about why such a framing is useful when thinking about building a pipeline of machine learning models. We end with a recognition of the biases that machine learning can amplify and how to recognize this.
A standard introduction to online learning might place Online Gradient Descent at its center and then proceed to develop generalizations and extensions like Online Mirror Descent and second-order methods. Here we explore the alternative approach of putting exponential weights (EW) first. We show that many standard methods and their regret bounds then follow as a special case by plugging in suitable surrogate losses and playing the EW posterior mean. For instance, we easily recover Online Gradient Descent by using EW with a Gaussian prior on linearized losses, and, more generally, all instances of Online Mirror Descent based on regular Bregman divergences also correspond to EW with a prior that depends on the mirror map. Furthermore, appropriate quadratic surrogate losses naturally give rise to Online Gradient Descent for strongly convex losses and to Online Newton Step. We further interpret several recent adaptive methods (iProd, Squint, and a variation of Coin Betting for experts) as a series of closely related reductions to exp-concave surrogate losses that are then handled by Exponential Weights. Finally, a benefit of our EW interpretation is that it opens up the possibility of sampling from the EW posterior distribution instead of playing the mean. As already observed by Bubeck and Eldan, this recovers the best-known rate in Online Bandit Linear Optimization.
Alex Irpan, a software engineer at Google, wrote an excellent article on the current difficulties of getting deep reinforcement learning to work. For example, even after weeks of optimizing hyperparameters and explotation-exploration rates, these models are still highly sensitive to initial conditions. A 30% failure rate is seen as "working."
We introduce several new black-box reductions that significantly improve the design of adaptive and parameter-free online learning algorithms by simplifying analysis, improving regret guarantees, and sometimes even improving runtime. We reduce parameter-free online learning to online exp-concave optimization, we reduce optimization in a Banach space to one-dimensional optimization, and we reduce optimization over a constrained domain to unconstrained optimization. All of our reductions run as fast as online gradient descent. We use our new techniques to improve upon the previously best regret bounds for parameter-free learning, and do so for arbitrary norms.
The field of learning analytics needs to adopt a more rigorous approach for predictive model evaluation that matches the complex practice of model-building. In this work, we present a procedure to statistically test hypotheses about model performance which goes beyond the state-of-the-practice in the community to analyze both algorithms and feature extraction methods from raw data. We apply this method to a series of algorithms and feature sets derived from a large sample of Massive Open Online Courses (MOOCs). While a complete comparison of all potential modeling approaches is beyond the scope of this paper, we show that this approach reveals a large gap in dropout prediction performance between forum-, assignment-, and clickstream-based feature extraction methods, where the latter is significantly better than the former two, which are in turn indistinguishable from one another. This work has methodological implications for evaluating predictive or AI-based models of student success, and practical implications for the design and targeting of at-risk student models and interventions.
Advanced Data Mining Projects with R takes you one step ahead in understanding the most complex data mining algorithms and implementing them in the popular R language. Follow up to our course Data Mining Projects in R, this course will teach you how to build your own recommendation engine. You will also implement dimensionality reduction and use it to build a real-world project. Going ahead, you will be introduced to the concept of neural networks and learn how to apply them for predictions, classifications, and forecasting. Finally, you will implement ggplot2, plotly and aspects of geomapping to create your own data visualization projects.By the end of this course, you will be well-versed with all the advanced data mining techniques and how to implement them using R, in any real-world scenario.
Column n The Educational Advances in Artificial Intelligence column discusses and shares innovative educational approaches that teach or leverage AI and its many subfields at all levels of education (K-12, undergraduate, and graduate levels). In this column I describe my experience adapting the content and infrastructure from massive, open, online courses (MOOCs) to enhance my courses in the Department of Electrical Engineering and Computer Science at Vanderbilt University. I begin with my informal, early use of MOOC content and then move to two deliberatively designed strategies for adapting MOOCs to campus (that is, wrappers and small private online classes [SPOCs]). I describe student reactions and touch on selected policy and institutional considerations. In the never-ending search for increasing student bang-for-the-buck, I was motivated to increase the bang, rather than reduce the buck, the latter being well above my pay grade.