We study the impact of the constraint set and gradient geometry on the convergence of online and stochastic methods for convex optimization, providing a characterization of the geometries for which stochastic gradient and adaptive gradient methods are (minimax) optimal. In particular, we show that when the constraint set is quadratically convex, diagonally pre-conditioned stochastic gradient methods are minimax optimal. We further provide a converse that shows that when the constraints are not quadratically convex---for example, any $\ell_p$-ball for $p < 2$---the methods are far from optimal. Based on this, we can provide concrete recommendations for when one should use adaptive, mirror or stochastic gradient methods.

Decentralized stochastic gradient method emerges as a promising solution for solving large-scale machine learning problems. This paper studies the decentralized Markov chain gradient descent (DMGD) algorithm - a variant of the decentralized stochastic gradient methods where the random samples are taken along the trajectory of a Markov chain. This setting is well-motivated when obtaining independent samples is costly or impossible, which excludes the use of the traditional stochastic gradient algorithms. Specifically, we consider the first- and zeroth-order versions of decentralized Markov chain gradient descent over a connected network, where each node only communicates with its neighbors about intermediate results. The nonergodic convergence and the ergodic convergence rate of the proposed algorithms have been rigorously established, and their critical dependences on the network topology and the mixing time of Markov chain have been highlighted. The numerical tests further validate the sample efficiency of our algorithm.

Palo Alto Research Center, Mail Stop: 3333 Coyote Hill Road, Palo Alto, CA 94034 USA Abstract Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter that produces acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with a high fidelity multi-modal transportation simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA. 1. Introduction Transportation is one of the largest consumers of energy in the ...

Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics. 1 Introduction Assessing the knowledge acquired by students is one of the most important aspects of the learning process as it provides feedback to help students correct their misunderstanding of knowledge and improves their overall learning performance. Traditionally, the assessing paradigm is often conducted by instructors or teachers. However, this access paradigm is not suitable in many cases especially when teaching resources are not readily available.

Neural dialogue models have been widely adopted in various chatbot applications because of their good performance in simulating and generalizing human conversations. However, there exists a dark side of these models -- due to the vulnerability of neural networks, a neural dialogue model can be manipulated by users to say what they want, which brings in concerns about the security of practical chatbot services. In this work, we investigate whether we can craft inputs that lead a well-trained black-box neural dialogue model to generate targeted outputs. We formulate this as a reinforcement learning (RL) problem and train a Reverse Dialogue Generator which efficiently finds such inputs for targeted outputs. Experiments conducted on a representative neural dialogue model show that our proposed model is able to discover such desired inputs in a considerable portion of cases. Overall, our work reveals this weakness of neural dialogue models and may prompt further researches of developing corresponding solutions to avoid it.

It's not surprising that in this day and age, artificial intelligence jobs are some of the most sought-after positions on the market. The chance to work with exciting technology that's becoming increasingly important, collaborate with top-level engineers and be an employee on the most avant-garde companies around makes a career in artificial intelligence an excellent choice for an ambitious young graduate. Not to mention the fact that tech companies are paying big money for the right kind of candidate. The AI sector currently offers all kinds of exciting opportunities. Let's take a look at some of the hottest AI jobs out there.

The Directorate General of Training (DGT), under the skill development and entrepreneurship ministry, has signed an agreement with IT major IBM to carry out a nationwide Train-the-Trainer programme in basic artificial intelligence, an official statement said on Wednesday. As part of the programme, ITI trainers will be trained on basic artificial intelligence (AI) skills towards using the technology in their day-to-day training activities, the ministry said in a statement. This programme, it said, aims at enabling the trainers with basic approach, workflow and application of artificial intelligence that they can apply in their training modules. "IBM aims at training 10,000 faculty members from ITIs across the country and the programme will be executed over a period of one year with 14 trainers across 7 locations with over 200 workshops," it added. Mahendra Nath Pandey, Minister for Skill Development and Entrepreneurship said, many more training programmes will be initiated for the trainers.

The Internet of things (IoT) is the inter-networking of physical devices (also termed as connected devices or smart devices), vehicles, buildings and other objects (which could be smart wearable, diagnostic device, kitchen appliances etc.) embedded with electronics, software, sensors, actuators, and network connectivity that enables these "smart objects" to collect and exchange data. In other words, Internet of things is a global infrastructure for the information society. IoT allows advanced services by interconnecting (physical and virtual) things based on existing and evolving interoperable information and communication technologies. For example, the smart refrigerator in your kitchen (at home) can send you an alert (or notification) on your smartphone (while you are leaving office) when you're out of milk or gas. Your wearable or smartwatch can warn you if there is something wrong with your pulse or heart-rate. Additionally, all this information gets recorded. Later, the software after looking at the data can provide you information like: you are likely to run of milk on Wednesday, run out of gas in two weeks, or likely to get a heart attack in three months (so, time for a check-up and take precautions).

At KDnuggets, we try to keep our finger on the pulse of main events and developments in industry, academia, and technology. We also do our best to look forward to key trends on the horizon. In previous years, we have brought collections of predictions and analysis from experts. What were the main developments in Machine Learning and Artificial Intelligence in 2018, and what key trends do you expect in 2019? Below are the responses from Anima Anandkumar, Andriy Burkov, Pedro Domingos, Ajit Jaokar, Nikita Johnson, Zachary Chase Lipton, Matthew Mayo, Brandon Rohrer, Elena Sharova, Rachel Thomas, and Daniel Tunkelang. Key themes singled out by these experts include deep learning advancements, transfer learning, the limitations of machine learning, the changing landscape of natural language processing, and much more. Be sure to check out collected opinions we shared last week when we asked a group of experts the related question, "What were the main developments in Data Science and Analytics in 2018 and what key trends do you expect in 2019?" Anima Anandkumar (@AnimaAnandkumar) is Director of ML research at NVIDIA and Bren Professor at Caltech.

The School of Science has announced that the recipients of the school's 2019 Teaching Prizes for Graduate and Undergraduate Education are Mehrdad Jazayeri and Hazel Sive. Nominated by peers and students, the faculty members chosen to receive these prizes are selected to acknowledge their exemplary efforts in teaching graduate and undergraduate students. Mehrdad Jazayeri, an associate professor in the Department of Brain and Cognitive Sciences and investigator at the McGovern Institute for Brain Research, is awarded the prize for graduate education for 9.014 (Quantitative Methods and Computational Models in Neuroscience). Earlier this year, he was recognized for excellence in graduate teaching by the Department of Brain and Cognitive Sciences and won a Graduate Student Council teaching award in 2016. In their nomination letters, peers and students alike remarked that he displays not only great knowledge, but extraordinary skill in teaching, most notably by ensuring everyone learns the material.