Optimization-based meta-learning aims to learn an initialization so that a new unseen task can be learned within a few gradient updates. Model Agnostic Meta-Learning (MAML) is a benchmark algorithm comprising two optimization loops. The inner loop is dedicated to learning a new task and the outer loop leads to meta-initialization. However, ANIL (almost no inner loop) algorithm shows that feature reuse is an alternative to rapid learning in MAML. Thus, the meta-initialization phase makes MAML primed for feature reuse and obviates the need for rapid learning. Contrary to ANIL, we hypothesize that there may be a need to learn new features during meta-testing. A new unseen task from non-similar distribution would necessitate rapid learning in addition reuse and recombination of existing features. In this paper, we invoke the width-depth duality of neural networks, wherein, we increase the width of the network by adding extra computational units (ACU). The ACUs enable the learning of new atomic features in the meta-testing task, and the associated increased width facilitates information propagation in the forwarding pass. The newly learnt features combine with existing features in the last layer for meta-learning. Experimental results show that our proposed MAC method outperformed existing ANIL algorithm for non-similar task distribution by approximately 13% (5-shot task setting)

Transporter Net is a recently proposed framework for pick and place that is able to learn good manipulation policies from a very few expert demonstrations. A key reason why Transporter Net is so sample efficient is that the model incorporates rotational equivariance into the pick module, i.e. the model immediately generalizes learned pick knowledge to objects presented in different orientations. This paper proposes a novel version of Transporter Net that is equivariant to both pick and place orientation. As a result, our model immediately generalizes place knowledge to different place orientations in addition to generalizing pick knowledge as before. Ultimately, our new model is more sample efficient and achieves better pick and place success rates than the baseline Transporter Net model.

We consider the well-studied problem of decomposing a vector time series signal into components with different characteristics, such as smooth, periodic, nonnegative, or sparse. We describe a simple and general framework in which the components are defined by loss functions (which include constraints), and the signal decomposition is carried out by minimizing the sum of losses of the components (subject to the constraints). When each loss function is the negative log-likelihood of a density for the signal component, this framework coincides with maximum a posteriori probability (MAP) estimation; but it also includes many other interesting cases. Summarizing and clarifying prior results, we give two distributed optimization methods for computing the decomposition, which find the optimal decomposition when the component class loss functions are convex, and are good heuristics when they are not. Both methods require only the masked proximal operator of each of the component loss functions, a generalization of the well-known proximal operator that handles missing entries in its argument. Both methods are distributed, i.e., handle each component separately. We derive tractable methods for evaluating the masked proximal operators of some loss functions that, to our knowledge, have not appeared in the literature.

We tackle the challenge of feature embedding for the purposes of improving the click-through rate prediction process. We select three models: logistic regression, factorization machines and deep factorization machines, as our baselines and propose five different feature embedding modules: embedding scaling, FM embedding, embedding encoding, NN embedding and the embedding reweighting module. The embedding modules act as a way to improve baseline model feature embeddings and are trained alongside the rest of the model parameters in an end-to-end manner. Each module is individually added to a baseline model to obtain a new augmented model. We test the predictive performance of our augmented models on a publicly accessible dataset used for benchmarking click-through rate prediction models. Our results show that several proposed embedding modules provide an important increase in predictive performance without a drastic increase in training time.

Weight norm $\|w\|$ and margin $\gamma$ participate in learning theory via the normalized margin $\gamma/\|w\|$. Since standard neural net optimizers do not control normalized margin, it is hard to test whether this quantity causally relates to generalization. This paper designs a series of experimental studies that explicitly control normalized margin and thereby tackle two central questions. First: does normalized margin always have a causal effect on generalization? The paper finds that no -- networks can be produced where normalized margin has seemingly no relationship with generalization, counter to the theory of Bartlett et al. (2017). Second: does normalized margin ever have a causal effect on generalization? The paper finds that yes -- in a standard training setup, test performance closely tracks normalized margin. The paper suggests a Gaussian process model as a promising explanation for this behavior.

Clinical records frequently include assessments of the characteristics of patients, which may include the completion of various questionnaires. These questionnaires provide a variety of perspectives on a patient's current state of well-being. Not only is it critical to capture the heterogeneity given by these perspectives, but there is also a growing demand for developing cost-effective technologies for clinical phenotyping. Filling out many questionnaires may be a strain for the patients and therefore costly. In this work, we propose COBALT -- a cost-based layer selector model for detecting phenotypes using a community detection approach. Our goal is to minimize the number of features used to build these phenotypes while preserving its quality. We test our model using questionnaire data from chronic tinnitus patients and represent the data in a multi-layer network structure. The model is then evaluated by predicting post-treatment data using baseline features (age, gender, and pre-treatment data) as well as the identified phenotypes as a feature. For some post-treatment variables, predictors using phenotypes from COBALT as features outperformed those using phenotypes detected by traditional clustering methods. Moreover, using phenotype data to predict post-treatment data proved beneficial in comparison with predictors that were solely trained with baseline features.

In order to operate in human environments, a robot's semantic perception has to overcome open-world challenges such as novel objects and domain gaps. Autonomous deployment to such environments therefore requires robots to update their knowledge and learn without supervision. We investigate how a robot can autonomously discover novel semantic classes and improve accuracy on known classes when exploring an unknown environment. To this end, we develop a general framework for mapping and clustering that we then use to generate a self-supervised learning signal to update a semantic segmentation model. In particular, we show how clustering parameters can be optimized during deployment and that fusion of multiple observation modalities improves novel object discovery compared to prior work. Models, data, and implementations can be found at github.com/hermannsblum/scim.

Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or raw data, practitioners are faced with significant issues of data quality and diversity which can be prohibitively labor intensive to address. Existing methods for dealing with these challenges tend to make strong assumptions about the particular issues at play, and often require a priori knowledge or metadata such as domain labels. Our work is orthogonal to these methods: we instead focus on providing a unified and efficient framework for Metadata Archaeology -- uncovering and inferring metadata of examples in a dataset. We curate different subsets of data that might exist in a dataset (e.g. mislabeled, atypical, or out-of-distribution examples) using simple transformations, and leverage differences in learning dynamics between these probe suites to infer metadata of interest. Our method is on par with far more sophisticated mitigation methods across different tasks: identifying and correcting mislabeled examples, classifying minority-group samples, prioritizing points relevant for training and enabling scalable human auditing of relevant examples.

Sports, due to their global reach and impact-rich prediction tasks, are an exciting domain to deploy machine learning models. However, data from conventional sports is often unsuitable for research use due to its size, veracity, and accessibility. To address these issues, we turn to esports, a growing domain that encompasses video games played in a capacity similar to conventional sports. Since esports data is acquired through server logs rather than peripheral sensors, esports provides a unique opportunity to obtain a massive collection of clean and detailed spatiotemporal data, similar to those collected in conventional sports. To parse esports data, we develop awpy, an open-source esports game log parsing library that can extract player trajectories and actions from game logs. Using awpy, we parse 8.6m actions, 7.9m game frames, and 417k trajectories from 1,558 game logs from professional Counter-Strike tournaments to create the Esports Trajectory and Actions (ESTA) dataset. ESTA is one of the largest and most granular publicly available sports data sets to date. We use ESTA to develop benchmarks for win prediction using player-specific information.

Sarcasm can be defined as saying or writing the opposite of what one truly wants to express, usually to insult, irritate, or amuse someone. Because of the obscure nature of sarcasm in textual data, detecting it is difficult and of great interest to the sentiment analysis research community. Though the research in sarcasm detection spans more than a decade, some significant advancements have been made recently, including employing unsupervised pre-trained transformers in multimodal environments and integrating context to identify sarcasm. In this study, we aim to provide a brief overview of recent advancements and trends in computational sarcasm research for the English language. We describe relevant datasets, methodologies, trends, issues, challenges, and tasks relating to sarcasm that are beyond detection. Our study provides well-summarized tables of sarcasm datasets, sarcastic features and their extraction methods, and performance analysis of various approaches which can help researchers in related domains understand current state-of-the-art practices in sarcasm detection.