We consider semidefinite programs (SDPs) of size $n$ with equality constraints. In order to overcome scalability issues, Burer and Monteiro proposed a factorized approach based on optimizing over a matrix $Y$ of size $n\times k$ such that $X=YY^*$ is the SDP variable. The advantages of such formulation are twofold: the dimension of the optimization variable is reduced, and positive semidefiniteness is naturally enforced. However, optimization in $Y$ is non-convex. In prior work, it has been shown that, when the constraints on the factorized variable regularly define a smooth manifold, provided $k$ is large enough, for almost all cost matrices, all second-order stationary points (SOSPs) are optimal. Importantly, in practice, one can only compute points which approximately satisfy necessary optimality conditions, leading to the question: are such points also approximately optimal? To this end, and under similar assumptions, we use smoothed analysis to show that approximate SOSPs for a randomly perturbed objective function are approximate global optima, with $k$ scaling like the square root of the number of constraints (up to log factors). We particularize our results to an SDP relaxation of phase retrieval.

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in the posterior regularization framework. SSDKL combines the hierarchical representation learning of neural networks with the probabilistic modeling capabilities of Gaussian processes. By leveraging unlabeled data, we show improvements on a diverse set of real-world regression tasks over supervised deep kernel learning and semi-supervised methods such as VAT and mean teacher adapted for regression.

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity. However, this framework has limitations in terms of the classes of tasks it can efficiently learn. In this paper we introduce a novel deictic object-oriented framework that has provably efficient learning bounds and can solve a broader range of tasks. Additionally, we show that this framework is capable of zero-shot transfer of transition dynamics across tasks and demonstrate this empirically for the Taxi and Sokoban domains.

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in the posterior regularization framework. SSDKL combines the hierarchical representation learning of neural networks with the probabilistic modeling capabilities of Gaussian processes. By leveraging unlabeled data, we show improvements on a diverse set of real-world regression tasks over supervised deep kernel learning and semi-supervised methods such as VAT and mean teacher adapted for regression.

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity. However, this framework has limitations in terms of the classes of tasks it can efficiently learn. In this paper we introduce a novel deictic object-oriented framework that has provably efficient learning bounds and can solve a broader range of tasks. Additionally, we show that this framework is capable of zero-shot transfer of transition dynamics across tasks and demonstrate this empirically for the Taxi and Sokoban domains.

Artificial intelligence (AI) can generate eerily realistic faces, but what about tribal artwork? That's the question Victor Dibia, a human-computer interaction researcher and Carnegie Mellon graduate, sought to answer with an AI system trained on a dataset of African masks. As Dibia explains in a blog post, the work was inspired by a trip to the 2018 Deep Learning Indaba, an annual machine learning conference held at Stellenbosch University, South Africa, in September. Attendees were provided access to second-generation Tensor Processing Units (TPUs) -- Google-designed chips purpose-built for fast training or inference of AI models -- which Dibia used for training. He tapped Google's TensorFlow machine learning framework to get a generative adversarial network (GAN) -- a two-part neural network consisting of generators that produce samples and discriminators that attempt to distinguish between the generated samples and real-world samples -- up and running on the TPUs.

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other paths connecting a pair of entities. Given the enormous size of KBs and the exponential number of paths, previous path-based models have considered only the problem of predicting a missing relation given two entities or evaluating the truth of a proposed triple. Additionally, these methods have traditionally used random paths between fixed entity pairs or more recently learned to pick paths between them. We propose a new algorithm MINERVA, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity. Since random walks are impractical in a setting with combinatorially many destinations from a start node, we present a neural reinforcement learning approach which learns how to navigate the graph conditioned on the input query to find predictive paths. Empirically, this approach obtains state-of-the-art results on several datasets, significantly outperforming prior methods.

In this tutorial, you will learn how to apply deep learning to perform medical image analysis. Specifically, you will discover how to use the Keras deep learning library to automatically analyze medical images for malaria testing. Such a deep learning medical imaging system can help reduce the 400,000 deaths per year caused by malaria. Today's tutorial was inspired by two sources. They've helped me as I've been studying deep learning. I live in an area of Africa that is prone to disease, especially malaria. I'd like to be able to apply computer vision to help reduce malaria outbreaks. Do you have any tutorials on medical imaging? I would really appreciate it if you wrote one.

Digital transformation is the adoption of advanced technologies and the rise of innovations as companies and individuals reorganise to be mobile- and digital-first, multimodal, and intelligence-driven. It is a catalyst for engendering agility, and has become crucial for organisations to stay competitive, achieve successes, and even survive. A key enabler of this is artificial intelligence,which has been dubbed a'great transformer'. Artificial intelligence (AI) refers to systems that change their behaviours without being explicitly programmed to do so – simply put, they learn. These systems use things like aggregated data, usage analysis, pattern recognition, and predictive analytics to deliver intuitive insights or make choices, improving efficiency and even shifting business models across all sectors.

The Chart of the Week is a weekly Visual Capitalist feature on Fridays. Are you ready to hand your job over to R2D2? A recent study by the Mckinsey Global Institute forecasts up to 800 million workers worldwide could lose their jobs to automation by 2030. Industrial machine operators, administrators, and service workers will be the first to take a hit. Meanwhile, poorer countries with lower investment in tech are less likely to feel the pinch. Today's chart uses data from the Future of Jobs Report 2018 by the World Economic Forum to take a peek at the changes technology will bring over the next four years.