In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate predictions using a scalar reward function, which may be easily assembled from human knowledge or non-differentiable pipelines. But searching through the entire output space to find the best output with respect to this reward function is typically intractable. In this paper, we instead use efficient truncated randomized search in this reward function to train structured prediction energy networks (SPENs), which provide efficient test-time inference using gradient-based search on a smooth, learned representation of the score landscape, and have previously yielded state-of-the-art results in structured prediction. In particular, this truncated randomized search in the reward function yields previously unknown local improvements, providing effective supervision to SPENs, avoiding their traditional need for labeled training data.

Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done on a test sample once the entire training data is observed, and the individual setting where the features and labels, both in the training and test, are specific individual quantities. The information theoretic approach naturally uses the self-information loss or log-loss. Our results provide universal learning schemes that compete with a "genie" (or reference) that knows the true test label. In particular, it is demonstrated that the main proposed scheme, termed Predictive Normalized Maximum Likelihood (pNML), is a robust learning solution that outperforms the current leading approach based on Empirical Risk Minimization (ERM). Furthermore, the pNML construction provides a pointwise indication for the learnability of the specific test challenge with the given training examples

The ability to build a model on a source task and subsequently adapt such model on a new target task is a pervasive need in many astronomical applications. The problem is generally known as transfer learning in machine learning, where domain adaptation is a popular scenario. An example is to build a predictive model on spectroscopic data to identify Supernovae IA, while subsequently trying to adapt such model on photometric data. In this paper we propose a new general approach to domain adaptation that does not rely on the proximity of source and target distributions. Instead we simply assume a strong similarity in model complexity across domains, and use active learning to mitigate the dependency on source examples. Our work leads to a new formulation for the likelihood as a function of empirical error using a theoretical learning bound; the result is a novel mapping from generalization error to a likelihood estimation. Results using two real astronomical problems, Supernova Ia classification and identification of Mars landforms, show two main advantages with our approach: increased accuracy performance and substantial savings in computational cost.

Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances. Trajectories imitating to solve the task at hand can help to increase sample-efficiency of deep RL methods. In this paper, we present a simple approach to use such trajectories, applied to the challenging Ball-in-Maze Games, recently introduced in the literature. We show that in spite of not using human-generated trajectories and just using the simulator as a model to generate a limited number of trajectories, we can get a speed-up of about 2-3x in the learning process. We also discuss some challenges we observed while using trajectory-based learning for very sparse reward functions.

For many natural language processing (NLP) tasks the amount of annotated data is limited. This urges a need to apply semi-supervised learning techniques, such as transfer learning or meta-learning. In this work we tackle Named Entity Recognition (NER) task using Prototypical Network - a metric learning technique. It learns intermediate representations of words which cluster well into named entity classes. This property of the model allows classifying words with extremely limited number of training examples, and can potentially be used as a zero-shot learning method. By coupling this technique with transfer learning we achieve well-performing classifiers trained on only 20 instances of a target class.

Many conversational agents in the market today follow a standard bot development framework which requires training intent classifiers to recognize user input. The need to create a proper set of training examples is often the bottleneck in the development process. In many occasions agent developers have access to historical chat logs that can provide a good quantity as well as coverage of training examples. However, the cost of labeling them with tens to hundreds of intents often prohibits taking full advantage of these chat logs. In this paper, we present a framework called \textit{search, label, and propagate} (SLP) for bootstrapping intents from existing chat logs using weak supervision. The framework reduces hours to days of labeling effort down to minutes of work by using a search engine to find examples, then relies on a data programming approach to automatically expand the labels. We report on a user study that shows positive user feedback for this new approach to build conversational agents, and demonstrates the effectiveness of using data programming for auto-labeling. While the system is developed for training conversational agents, the framework has broader application in significantly reducing labeling effort for training text classifiers.

SMART is an open source web application designed to help data scientists and research teams efficiently build labeled training data sets for supervised machine learning tasks. SMART provides users with an intuitive interface for creating labeled data sets, supports active learning to help reduce the required amount of labeled data, and incorporates inter-rater reliability statistics to provide insight into label quality. SMART is designed to be platform agnostic and easily deployable to meet the needs of as many different research teams as possible. The project website contains links to the code repository and extensive user documentation.

Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in the training domain that will generalize to the target domain by incorporating prior knowledge of aspects of the data generating process that are expected to differ as expressed in a causal selection diagram. Specifically, we remove variables generated by unstable mechanisms from the joint factorization to yield the Graph Surgery Estimator---an interventional distribution that is invariant to the differences across domains. We prove that the surgery estimator finds stable relationships in strictly more scenarios than previous approaches which only consider conditional relationships, and demonstrate this in simulated experiments. We also evaluate on real world data for which the true causal diagram is unknown, performing competitively against entirely data-driven approaches.

A robot needs contextual awareness, effective speech production and complementing non-verbal gestures for successful communication in society. In this paper, we present our end-to-end system that tries to enhance the effectiveness of non-verbal gestures. For achieving this, we identified prominently used gestures in performances by TED speakers and mapped them to their corresponding speech context and modulated speech based upon the attention of the listener. The proposed method utilized Convolutional Pose Machine [4] to detect the human gesture. Dominant gestures of TED speakers were used for learning the gesture-to-speech mapping. The speeches by them were used for training the model. We also evaluated the engagement of the robot with people by conducting a social survey. The effectiveness of the performance was monitored by the robot and it self-improvised its speech pattern on the basis of the attention level of the audience, which was calculated using visual feedback from the camera. The effectiveness of interaction as well as the decisions made during improvisation was further evaluated based on the head-pose detection and interaction survey.

In recent years, state-of-the-art methods for supervised learning have exploited increasingly gradient boosting techniques, with mainstream efficient implementations such as xgboost or lightgbm. One of the key points in generating proficient methods is Feature Selection (FS). It consists in selecting the right valuable effective features. When facing hundreds of these features, it becomes critical to select best features. While filter and wrappers methods have come to some maturity, embedded methods are truly necessary to find the best features set as they are hybrid methods combining features filtering and wrapping. In this work, we tackle the problem of finding through machine learning best a priori trades from an algorithmic strategy. We derive this new method using coordinate ascent optimization and using block variables. We compare our method to Recursive Feature Elimination (RFE) and Binary Coordinate Ascent (BCA). We show on a real life example the capacity of this method to select good trades a priori. Not only this method outperforms the initial trading strategy as it avoids taking loosing trades, it also surpasses other method, having the smallest feature set and the highest score at the same time. The interest of this method goes beyond this simple trade classification problem as it is a very general method to determine the optimal feature set using some information about features relationship as well as using coordinate ascent optimization.