Yang et al. [7] used Fisher widely advocated for image classification problems. To further Information criterion in their class-specific reconstruction errors sharpen their discriminative capabilities, most state-ofthe-art to compose their approach. DL methods have additional constraints included in Besides SDL, Analysis Dictionary Learning (ADL) [8, 9] the learning stages. These various constraints, however, lead has recently been of interest on account of its fast encoding to additional computational complexity. We hence propose an and stability attributes. ADL provides a linear transformation efficient Discriminative Convolutional Analysis Dictionary of a signal to a nearly sparse representation. Inspired by Learning (DCADL) method, as a lower cost Discriminative the SDL methodology in image classification, ADL has also DL framework, to both characterize the image structures and been adapted to the supervised learning problems by promoting refine the interclass structure representations. The proposed discriminative sparse representations [10, 11]. In [10], DCADL jointly learns a convolutional analysis dictionary and Guo et al. incorporated both a topological structure and a representation a universal classifier, while greatly reducing the time complexity similarity constraint to encourage a suitable classselective in both training and testing phases, and achieving a representation for a 1-Nearest Neighbor classifier.

Over the past 10 years, commercial AI has enjoyed what we at Amazon call the flywheel effect: customer interactions with AI systems generate data; with more data, machine learning algorithms perform better, which leads to better customer experiences; better customer experiences drive more usage and engagement, which in turn generate more data. Those data are used to train machine learning systems in three chief ways. The first is supervised learning, in which the training data are hand-labeled (with, say, words' parts of speech or the names of objects in an image) and the system learns to apply labels to unlabeled data. A variation of this is weakly supervised learning, which uses easily acquired but imprecise labels to enable machine learning at scale. If a website visitor performs a search, for instance, the links she clicks indicate which search results should have been at the top of the list; that kind of implicit information can be used to automatically label data. Training with entirely unlabeled data is called unsupervised learning.

We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs. We propose an efficient algorithm based on trace norm regularization which, differently from previous methods, does not require explicit knowledge of the coding/decoding functions of the surrogate framework. As a result, our algorithm can be applied to the broad class of problems in which the surrogate space is large or even infinite dimensional. We study excess risk bounds for trace norm regularized structured prediction, implying the consistency and learning rates for our estimator. We also identify relevant regimes in which our approach can enjoy better generalization performance than previous methods. Numerical experiments on ranking problems indicate that enforcing low-rank relations among surrogate outputs may indeed provide a significant advantage in practice.

Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches.

Deep structured-prediction energy-based models combine the expressive power of learned representations and the ability of embedding knowledge about the task at hand into the system. A common way to learn parameters of such models consists in a multistage procedure where different combinations of components are trained at different stages. The joint end-to-end training of the whole system is then done as the last fine-tuning stage. This multistage approach is time-consuming and cumbersome as it requires multiple runs until convergence and multiple rounds of hyperparameter tuning. From this point of view, it is beneficial to start the joint training procedure from the beginning. However, such approaches often unexpectedly fail and deliver results worse than the multistage ones. In this paper, we hypothesize that one reason for joint training of deep energy-based models to fail is the incorrect relative normalization of different components in the energy function. We propose online and offline scaling algorithms that fix the joint training and demonstrate their efficacy on three different tasks.

Current methods for covariate-shift adaptation use unlabelled data to compute importance weights or domain-invariant features, while the final model is trained on labelled data only. Here, we consider a particular case of covariate shift which allows us also to learn from unlabelled data, that is, combining adaptation with semi-supervised learning. Using ideas from causality, we argue that this requires learning with both causes, $X_C$, and effects, $X_E$, of a target variable, $Y$, and show how this setting leads to what we call a semi-generative model, $P(Y,X_E|X_C,\theta)$. Our approach is robust to domain shifts in the distribution of causal features and leverages unlabelled data by learning a direct map from causes to effects. Experiments on synthetic data demonstrate significant improvements in classification over purely-supervised and importance-weighting baselines.

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this compositional structure is reflected in the the inputs' learned representations. While the assessment of compositionality in languages has received significant attention in linguistics and adjacent fields, the machine learning literature lacks general-purpose tools for producing graded measurements of compositional structure in more general (e.g. vector-valued) representation spaces. We describe a procedure for evaluating compositionality by measuring how well the true representation-producing model can be approximated by a model that explicitly composes a collection of inferred representational primitives. We use the procedure to provide formal and empirical characterizations of compositional structure in a variety of settings, exploring the relationship between compositionality and learning dynamics, human judgments, representational similarity, and generalization.

In many application settings, the data are plagued with missing features. These hinder data analysis. An abundant literature addresses missing values in an inferential framework, where the aim is to estimate parameters and their variance from incomplete tables. Here, we consider supervised-learning settings where the objective is to best predict a target when missing values appear in both training and test sets. We analyze which missing-values strategies lead to good prediction. We show the consistency of two approaches to estimating the prediction function. The most striking one shows that the widely-used mean imputation prior to learning method is consistent when missing values are not informative. This is in contrast with inferential settings as mean imputation is known to have serious drawbacks in terms of deformation of the joint and marginal distribution of the data. That such a simple approach can be consistent has important consequences in practice. This result holds asymptotically when the learning algorithm is consistent in itself. We contribute additional analysis on decision trees as they can naturally tackle empirical risk minimization with missing values. This is due to their ability to handle the half-discrete nature of variables with missing values. After comparing theoretically and empirically different missing-values strategies in trees, we recommend using the missing incorporated in attributes method as it can handle both non-informative and informative missing values.

Abstract--Early detection of incipient faults is of vital importance toreducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To overcome this challenge, this paper proposes using Monte Carlo dropout (MCdropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MCdropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types. I. INTRODUCTION Building faults whose impact are less perceivable and/or hinder regular operations are called soft faults [21], [32]. These soft faults, especially in their incipient phase, are hard to detect as their signatures are not generally obvious (due to their magnitudes) and are lurking under measurement/system noise or feedback control actions [10], [27]. Nevertheless, they will impact energy consumption, system performance, and maintenance costs adversely in the long-run if left undetected and unattended [14].

Inspired by the success of AlphaGo Zero (AGZ) which utilizes Monte Carlo Tree Search (MCTS) with Supervised Learning via Neural Network to learn the optimal policy and value function, in this work, we focus on establishing formally that such an approach indeed finds optimal policy asymptotically, as well as establishing non-asymptotic guarantees in the process. We shall focus on infinite-horizon discounted Markov Decision Process to establish the results. To start with, it requires establishing the MCTS's claimed property in the literature that for any given query state, MCTS provides approximate value function for the state with enough simulation steps of MDP. We provide non-asymptotic analysis establishing this property by analyzing a non-stationary multi-arm bandit setup. Our proof suggests that MCTS needs to be utilized with polynomial rather than logarithmic "upper confidence bound" for establishing its desired performance -- interestingly enough, AGZ chooses such polynomial bound. Using this as a building block, combined with nearest neighbor supervised learning, we argue that MCTS acts as a "policy improvement" operator; it has a natural "bootstrapping" property to iteratively improve value function approximation for all states, due to combining with supervised learning, despite evaluating at only finitely many states. In effect, we establish that to learn $\varepsilon$ approximation of value function in $\ell_\infty$ norm, MCTS combined with nearest-neighbors requires samples scaling as $\widetilde{O}\big(\varepsilon^{-(d+4)}\big)$, where $d$ is the dimension of the state space. This is nearly optimal due to a minimax lower bound of $\widetilde{\Omega}\big(\varepsilon^{-(d+2)}\big).$