Many modern high-performing machine learning models such as GPT-3 primarily rely on scaling up models, e.g., transformer networks. Simultaneously, a parallel line of work aims to improve the model performance by augmenting an input instance with other (labeled) instances during inference. Examples of such augmentations include task-specific prompts and similar examples retrieved from the training data by a nonparametric component. Remarkably, retrieval-based methods have enjoyed success on a wide range of problems, ranging from standard natural language processing and vision tasks to protein folding, as demonstrated by many recent efforts, including WebGPT and AlphaFold. Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored. In this paper, we present a formal treatment of retrieval-based models to characterize their generalization ability. In particular, we focus on two classes of retrieval-based classification approaches: First, we analyze a local learning framework that employs an explicit local empirical risk minimization based on retrieved examples for each input instance. Interestingly, we show that breaking down the underlying learning task into local sub-tasks enables the model to employ a low complexity parametric component to ensure good overall accuracy. The second class of retrieval-based approaches we explore learns a global model using kernel methods to directly map an input instance and retrieved examples to a prediction, without explicitly solving a local learning task.

With the boom of e-commerce, Multimodal Review Helpfulness Prediction (MRHP), which aims to sort product reviews according to the predicted helpfulness scores has become a research hotspot. Previous work on this task focuses on attention-based modality fusion, information integration, and relation modeling, which primarily exposes the following drawbacks: 1) the model may fail to capture the really essential information due to its indiscriminate attention formulation; 2) lack appropriate modeling methods that take full advantage of correlation among provided data. In this paper, we propose SANCL: Selective Attention and Natural Contrastive Learning for MRHP. SANCL adopts a probe-based strategy to enforce high attention weights on the regions of greater significance. It also constructs a contrastive learning framework based on natural matching properties in the dataset. Experimental results on two benchmark datasets with three categories show that SANCL achieves state-of-the-art baseline performance with lower memory consumption.

Aggregating a dataset, then injecting some noise, is a simple and common way to release differentially private data.However, aggregated data -- even without noise -- is not an appropriate input for machine learning classifiers.In this work, we show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. The resulting model is a Markov Random Field (MRF), and we detail how to apply, modify and scale a MRF training algorithm to our setting. Finally we present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.

Despite the impressive successes of modern reinforcement learning (RL) (Sutton & Barto, 2018) methods in designing efficient specialized control policies for a wide variety of difficult tasks, many studies have highlighted the limited ability of RL agents to generalize to variations of such tasks that would appear easy to a human being (Farebrother et al., 2018; Packer et al., 2018; Zhang et al., 2018; Song et al., 2020; Cobbe et al., 2019). This work is motivated by the idea that networks trained for specific tasks build state representations that can easily be fooled by the ambiguity between observation variables. For instance, in some platform video games, it is possible to design an optimal policy for a given level based solely on background features and progression indicators, rather than on the position of platforms and enemies (Song et al., 2020). While very efficient on this specific level, such a policy might not perform well on another. Conversely, we formulate and evaluate the hypothesis that a network trained to imitate several such specialized policies on a limited set of task variations induces a state representation that lifts the ambiguity and filters out confounding observation variables. Specifically, we investigate whether the process of network distillation (Hinton et al., 2015; Rusu et al., 2016a), inspired by knowledge consolidation in cognitive systems (Wilson & McNaughton, 1994; Ashworth et al., 2014; McClelland et al., 1995), induces valuable state representations. The interplay between distillation and state representation appears to have received little attention so far. We endeavor to fill this gap and investigate how neural distillation can act as a state representation bottleneck in RL. Our contributions are as follows: We propose a generic experimental protocol to evaluate the effects of imitation (via distillation) on state representation.

Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to the overall global structure of the object. We propose Relational Proxies, a novel approach that leverages the relational information between the global and local views of an object for encoding its semantic label. Starting with a rigorous formalization of the notion of distinguishability between fine-grained categories, we prove the necessary and sufficient conditions that a model must satisfy in order to learn the underlying decision boundaries in the fine-grained setting. We design Relational Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets and achieve state-of-the-art results on all of them, surpassing the performance of all existing works with a margin exceeding 4% in some cases. We also experimentally validate our theory on fine-grained distinguishability and obtain consistent results across multiple benchmarks.

We develop an approach to policy selection in active inference that allows us to efficiently search large policy spaces by mapping each policy to its embedding in a vector space. We sample the expected free energy of representative points in the space, then perform a more thorough policy search around the most promising point in this initial sample. We consider various approaches to creating the policy embedding space, and propose using k-means clustering to select representative points. We apply our technique to a goal-oriented graph-traversal problem, for which naive policy selection is intractable for even moderately large graphs.

Electrocardiogram (ECG), a technique for medical monitoring of cardiac activity, is an important method for identifying cardiovascular disease. However, analyzing the increasing quantity of ECG data consumes a lot of medical resources. This paper explores an effective algorithm for automatic classifications of multi-classes of heartbeat types based on ECG. Most neural network based methods target the individual heartbeats, ignoring the secrets embedded in the temporal sequence. And the ECG signal has temporal variation and unique individual characteristics, which means that the same type of ECG signal varies among patients under different physical conditions. A two-stream architecture is used in this paper and presents an enhanced version of ECG recognition based on this. The architecture achieves classification of holistic ECG signal and individual heartbeat and incorporates identified and temporal stream networks. Identified networks are used to extract features of individual heartbeats, while temporal networks aim to extract temporal correlations between heartbeats. Results on the MIT-BIH Arrhythmia Database demonstrate that the proposed algorithm performs an accuracy of 99.38\%. In addition, the proposed algorithm reaches an 88.07\% positive accuracy on massive data in real life, showing that the proposed algorithm can efficiently categorize different classes of heartbeat with high diagnostic performance.

Optimizing machine learning algorithms that are used to solve the objective function has been of great interest. Several approaches to optimize common algorithms, such as gradient descent and stochastic gradient descent, were explored. One of these approaches is reducing the gradient variance through adaptive sampling to solve large-scale optimization's empirical risk minimization (ERM) problems. In this paper, we will explore how starting with a small sample and then geometrically increasing it and using the solution of the previous sample ERM to compute the new ERM. This will solve ERM problems with first-order optimization algorithms of sublinear convergence but with lower computational complexity. This paper starts with theoretical proof of the approach, followed by two experiments comparing the gradient descent with the adaptive sampling of the gradient descent and ADAM with adaptive sampling ADAM on different datasets.

Large-scale social networks are thought to contribute to polarization by amplifying people's biases. However, the complexity of these technologies makes it difficult to identify the mechanisms responsible and to evaluate mitigation strategies. Here we show under controlled laboratory conditions that information transmission through social networks amplifies motivational biases on a simple perceptual decision-making task. Participants in a large behavioral experiment showed increased rates of biased decision-making when part of a social network relative to asocial participants, across 40 independently evolving populations. Drawing on techniques from machine learning and Bayesian statistics, we identify a simple adjustment to content-selection algorithms that is predicted to mitigate bias amplification. This algorithm generates a sample of perspectives from within an individual's network that is more representative of the population as a whole. In a second large experiment, this strategy reduced bias amplification while maintaining the benefits of information sharing. For example, social networks often lead to "echo-chambers" of like-minded individuals In this paper, we use an experimental paradigm to study how information sharing affects bias in judgment and decision-making. This new experimental paradigm allowed us to evaluate a mathematical theory of bias amplification and test a mitigation strategy based on this theory. Participants received a monetary reward for every correct answer. However, certain participants were offered an additional monetary reward for every green or blue dot in each stimulus ("motivated color" was randomized across participants, Our experimental paradigm consisted of arranging participants into an ordered set of groups, called "waves". At each wave t participants in social conditions observed judgments made by the participants in wave t 1. Participants in asocial conditions did not observe any social information. Each colored circle at the top of the image represents a participant. Stimuli consisted of 100 randomly positioned and sized blue and green dots displayed for one second. After viewing a stimulus, participants indicated whether they thought the stimulus had more green or more blue dots. Participants received feedback after each judgment on practice trials, and at the end of the experiment on test trials. All participants received a bonus on every trial if their judgment was correct. Participants in motivated conditions (shown here) received an additional bonus on every trial for every dot of their motivated color (green in both plots) regardless of whether their judgment was correct.

New time-domain surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will observe millions of transient alerts each night, making standard approaches of visually identifying new and interesting transients infeasible. We present two novel methods of automatically detecting anomalous transient light curves in real-time. Both methods are based on the simple idea that if the light curves from a known population of transients can be accurately modelled, any deviations from model predictions are likely anomalies. The first modelling approach is a probabilistic neural network built using Temporal Convolutional Networks (TCNs) and the second is an interpretable Bayesian parametric model of a transient. We demonstrate our methods' ability to provide anomaly scores as a function of time on light curves from the Zwicky Transient Facility. We show that the flexibility of neural networks, the attribute that makes them such a powerful tool for many regression tasks, is what makes them less suitable for anomaly detection when compared with our parametric model. The parametric model is able to identify anomalies with respect to common supernova classes with high precision and recall scores, achieving area under the precision-recall curves (AUCPR) above 0.79 for most rare classes such as kilonovae, tidal disruption events, intermediate luminosity transients, and pair-instability supernovae. Our ability to identify anomalies improves over the lifetime of the light curves. Our framework, used in conjunction with transient classifiers, will enable fast and prioritised followup of unusual transients from new large-scale surveys.