Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest. We introduce an unbiased estimator of the log marginal likelihood and its gradients for latent variable models based on randomized truncation of infinite series. If parameterized by an encoder-decoder architecture, the parameters of the encoder can be optimized to minimize its variance of this estimator. We show that models trained using our estimator give better test-set likelihoods than a standard importance-sampling based approach for the same average computational cost. This estimator also allows use of latent variable models for tasks where unbiased estimators, rather than marginal likelihood lower bounds, are preferred, such as minimizing reverse KL divergences and estimating score functions.

These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to devastating financial, reputational and even life-threatening consequences. Therefore, it is crucially important to correct model mistakes quickly as they appear. In this work, we investigate the problem of neural network editing $-$ how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. Namely, we propose Editable Training, a model-agnostic training technique that encourages fast editing of the trained model. We empirically demonstrate the effectiveness of this method on large-scale image classification and machine translation tasks.

Few-shot learning has attracted intensive research attention in recent years. Many methods have been proposed to generalize a model learned from provided base classes to novel classes, but no previous work studies how to select base classes, or even whether different base classes will result in different generalization performance of the learned model. In this paper, we utilize a simple yet effective measure, the Similarity Ratio, as an indicator for the generalization performance of a few-shot model. We then formulate the base class selection problem as a submodular optimization problem over Similarity Ratio. We further provide theoretical analysis on the optimization lower bound of different optimization methods, which could be used to identify the most appropriate algorithm for different experimental settings. The extensive experiments on ImageNet, Caltech256 and CUB-200-2011 demonstrate that our proposed method is effective in selecting a better base dataset.

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of available features. In this paper, we propose gOMP, a highly-scalable generalisation of the Orthogonal Matching Pursuit feature selection algorithm to several directions: (a) different types of outcomes, such as continuous, binary, nominal, and time-to-event, (b) different types of predictive models (e.g., linear least squares, logistic regression), (c) different types of predictive features (continuous, categorical), and (d) different, statistical-based stopping criteria. We compare the proposed algorithm against LASSO, a prototypical, widely used algorithm for high-dimensional data. On dozens of simulated datasets, as well as, real gene expression datasets, gOMP is on par, or outperforms LASSO for case-control binary classification, quantified outcomes (regression), and (censored) survival times (time-to-event) analysis. gOMP has also several theoretical advantages that are discussed. While gOMP is based on quite simple and basic statistical ideas, easy to implement and to generalize, we also show in an extensive evaluation that it is also quite effective in bioinformatics analysis settings.

We study the differential privacy of sequential statistical inference and learning algorithms that are characterized by random termination time. Using the two examples: sequential probability ratio test and sequential empirical risk minimization, we show that the number of steps such algorithms execute before termination can jeopardize the differential privacy of the input data in a similar fashion as their outputs, and it is impossible to use the usual Laplace mechanism to achieve standard differentially private in these examples. To remedy this, we propose a notion of weak differential privacy and demonstrate its equivalence to the standard case for large i.i.d. samples. We show that using the Laplace mechanism, weak differential privacy can be achieved for both the sequential probability ratio test and the sequential empirical risk minimization with proper performance guarantees. Finally, we provide preliminary experimental results on the Breast Cancer Wisconsin (Diagnostic) and Landsat Satellite Data Sets from the UCI repository.

Probabilistic Computation Tree Logic (PCTL) is frequently used to formally specify control objectives such as probabilistic reachability and safety. In this work, we focus on model checking PCTL specifications statistically on Markov Decision Processes (MDPs) by sampling, e.g., checking whether there exists a feasible policy such that the probability of reaching certain goal states is greater than a threshold. We use reinforcement learning to search for such a feasible policy for PCTL specifications, and then develop a statistical model checking (SMC) method with provable guarantees on its error. Specifically, we first use upper-confidence-bound (UCB) based Q-learning to design an SMC algorithm for bounded-time PCTL specifications, and then extend this algorithm to unbounded-time specifications by identifying a proper truncation time by checking the PCTL specification and its negation at the same time. Finally, we evaluate the proposed method on case studies.

Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen classes, well-known problems in deep networks such as memorizing training statistics have been less explored for few-shot learning. To tackle this issue, we propose self-augmentation that consolidates regional dropout and self-distillation. Specifically, we exploit a data augmentation technique called regional dropout, in which a patch of an image is substituted into other values. Then, we employ a backbone network that has auxiliary branches with its own classifier to enforce knowledge sharing. Lastly, we present a fine-tuning method to further exploit a few training examples for unseen classes. Experimental results show that the proposed method outperforms the state-of-the-art methods for prevalent few-shot benchmarks and improves the generalization ability.

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge. Thus it has triggered enormous research activities in machine learning and pattern recognition. One of the most important challenge of deep learning is to figure out relations between a feature and the depth of deep neural networks (deep nets for short) to reflect the necessity of depth. Our purpose is to quantify this feature-depth correspondence in feature extraction and generalization. We present the adaptivity of features to depths and vice-verse via showing a depth-parameter trade-off in extracting both single feature and composite features. Based on these results, we prove that implementing the classical empirical risk minimization on deep nets can achieve the optimal generalization performance for numerous learning tasks. Our theoretical results are verified by a series of numerical experiments including toy simulations and a real application of earthquake seismic intensity prediction.

Spatio-temporal forecasting is an open research field whose interest is growing exponentially. In this work we focus on creating a complex deep neural framework for spatio-temporal traffic forecasting with comparatively very good performance and that shows to be adaptable over several spatio-temporal conditions while remaining easy to understand and interpret. Our proposal is based on an interpretable attention-based neural network in which several modules are combined in order to capture key spatio-temporal time series components. Through extensive experimentation, we show how the results of our approach are stable and better than those of other state-of-the-art alternatives.

Reliably transmitting messages despite information loss due to a noisy channel is a core problem of information theory. One of the most important aspects of real world communication, e.g. via wifi, is that it may happen at varying levels of information transfer. The bandwidth-limited channel models this phenomenon. In this study we consider learning coding with the bandwidth-limited channel (BWLC). Recently, neural communication models such as variational autoencoders have been studied for the task of source compression. We build upon this work by studying neural communication systems with the BWLC. Specifically,we find three modelling choices that are relevant under expected information loss. First, instead of separating the sub-tasks of compression (source coding) and error correction (channel coding), we propose to model both jointly. Framing the problem as a variational learning problem, we conclude that joint systems outperform their separate counterparts when coding is performed by flexible learnable function approximators such as neural networks. To facilitate learning, we introduce a differentiable and computationally efficient version of the bandwidth-limited channel. Second, we propose a design to model missing information with a prior, and incorporate this into the channel model. Finally, sampling from the joint model is improved by introducing auxiliary latent variables in the decoder. Experimental results justify the validity of our design decisions through improved distortion and FID scores.