K-Medoids(KM) is a standard clustering method, used extensively on semi-metric data. Error analyses of KM have traditionally used an in-sample notion of error, which can be far from the true error and suffer from generalization error. We formalize the true K-Medoid error based on the underlying data distribution, by decomposing it into fundamental statistical problems of: minimum estimation (ME) and minimum mean estimation (MME). We provide a convergence result for MME and bound the true KM error for iid data. Inspired by this bound, we propose a computationally efficient, distributed KM algorithm namely MCPAM. MCPAM has expected runtime $\mathcal{O}(km)$ and provides massive computational savings for a small tradeoff in accuracy. We verify the quality and scaling properties of MCPAM on various datasets. And achieve the hitherto unachieved feat of calculating the KM of 1 billion points on semi-metric spaces.

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security domain and the privacy domain have typically been considered separately. It is thus unclear whether the defense methods in one domain will have any unexpected impact on the other domain. In this paper, we take a step towards resolving this limitation by combining the two domains. In particular, we measure the success of membership inference attacks against six state-of-the-art adversarial defense methods that mitigate adversarial examples (i.e., evasion attacks). Membership inference attacks aim to infer an individual's participation in the target model's training set and are known to be correlated with target model's overfitting and sensitivity with regard to training data. Meanwhile, adversarial defense methods aim to enhance the robustness of target models by ensuring that model predictions are unchanged for a small area around each training sample. Thus, adversarial defenses typically have a more fine-grained reliance on the training set and make the target model more vulnerable to membership inference attacks. To perform the membership inference attacks, we leverage the conventional inference method based on prediction confidence and propose two new inference methods that exploit structural properties of adversarially robust defenses. Our experimental evaluation demonstrates that compared with the natural training (undefended) approach, adversarial defense methods can indeed increase the target model's risk against membership inference attacks. When applying adversarial defenses to train the robust models, the membership inference advantage increases by up to $4.5$ times compared to the naturally undefended models.

The problem of forecasting stock price movements, due to market's uncertainty from incoming news, nonlinear financial instruments and behavioral and emotional biases is a challenging task facing academics and practitioners in the field; perhaps by far more complex than predicting the course of a comet by a physicist. In the past, many models have been proposed to face this problem including Support vector regression (SVR) as the extended routine designed from Support Vector Machines (SVM). Originally introduced by Vapnik for classification problems, SVM was redesigned to solve regression problems in the SVR framework. Nevertheless, SVM can solve small-sample, nonlinear and high dimension problems by using the structural risk minimization principle instead of the empirical risk principle, which could theoretically guarantee to achieve the global optimum [9]. Although SVR experimental results have shown great performance compared to other nonlinear methods [39, 40], its performance mainly depends on the choice of parameters.

The classification of individual traffic participants is a complex task, especially for challenging scenarios with multiple road users or under bad weather conditions. Radar sensors provide an - with respect to well established camera systems - orthogonal way of measuring such scenes. In order to gain accurate classification results, 50 different features are extracted from the measurement data and tested on their performance. From these features a suitable subset is chosen and passed to random forest and long short-term memory (LSTM) classifiers to obtain class predictions for the radar input. Moreover, it is shown why data imbalance is an inherent problem in automotive radar classification when the dataset is not sufficiently large. To overcome this issue, classifier binarization is used among other techniques in order to better account for underrepresented classes. A new method to couple the resulting probabilities is proposed and compared to others with great success. Final results show substantial improvements when compared to ordinary multiclass classification

Inference in Gaussian process (GP) models is computationally challenging for large data, and often difficult to approximate with a small number of inducing points. We explore an alternative approximation that employs stochastic inference networks for a flexible inference. Unfortunately, for such networks, minibatch training is difficult to be able to learn meaningful correlations over function outputs for a large dataset. We propose an algorithm that enables such training by tracking a stochastic, functional mirror-descent algorithm. At each iteration, this only requires considering a finite number of input locations, resulting in a scalable and easy-to-implement algorithm. Empirical results show comparable and, sometimes, superior performance to existing sparse variational GP methods.

We propose NovoGrad, a first-order stochastic gradient method with layer-wise gradient normalization via second moment estimators and with decoupled weight decay for a better regularization. The method requires half as much memory as Adam/AdamW. We evaluated NovoGrad on a diverse set of problems, including image classification, speech recognition, neural machine translation and language modeling. On these problems, NovoGrad performed equal to or better than SGD and Adam/AdamW. Empirically we show that NovoGrad (1) is very robust during the initial training phase and does not require learning rate warm-up, (2) works well with the same learning rate policy for different problems, and (3) generally performs better than other optimizers for very large batch sizes.

In this work, we consider to improve the model estimation efficiency by aggregating the neighbors' information as well as identify the subgroup membership for each node in the network. A tree-based $l_1$ penalty is proposed to save the computation and communication cost. We design a decentralized generalized alternating direction method of multiplier algorithm for solving the objective function in parallel. The theoretical properties are derived to guarantee both the model consistency and the algorithm convergence. Thorough numerical experiments are also conducted to back up our theory, which also show that our approach outperforms in the aspects of the estimation accuracy, computation speed and communication cost.

Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets, and highlight directions for future research.

Machine learning tasks such as optimizing the hyper-parameters of a model for a new dataset or few-shot learning can be vastly accelerated if they are not done from scratch for every new dataset, but carry over findings from previous runs. Meta-learning makes use of features of a whole dataset such as its number of instances, its number of predictors, the means of the predictors etc., so called meta-features, dataset summary statistics or simply dataset characteristics, which so far have been hand-crafted, often specifically for the task at hand. More recently, unsupervised dataset encoding models based on variational auto-encoders have been successful in learning such characteristics for the special case when all datasets follow the same schema, but not beyond. In this paper we design a novel model, Dataset2Vec, that is able to characterize datasets with a latent feature vector based on batches and thus is able to generalize beyond datasets having the same schema to arbitrary (tabular) datasets. To do so, we employ auxiliary learning tasks on batches of datasets, esp. to distinguish batches from different datasets. We show empirically that the meta-features collected from batches of similar datasets are concentrated within a small area in the latent space, hence preserving similarity. We also show that using the dataset characteristics learned by Dataset2Vec in a state-of-the-art hyper-parameter optimization model outperforms the hand-crafted meta-features that have been used in the hyper-parameter optimization literature so far. As a result, we advance the current state-of-the-art results for hyper-parameter optimization.

In machine learning, it is observed that probabilistic predictions sometimes disagree with averaged actual outcomes on certain subsets of data. This is also known as miscalibration that is responsible for unreliability and unfairness of practical machine learning systems. In this paper, we put forward an evaluation metric for calibration, coined field-level calibration error, that measures bias in predictions over the input fields that the decision maker concerns. We show that existing calibration methods perform poorly under our new metric. Specifically, after learning a calibration mapping over the validation dataset, existing methods have limited improvements in our error metric and completely fail to improve other non-calibration metrics such as the AUC score. We propose Neural Calibration, a new calibration method, which learns to calibrate by making full use of all input information over the validation set. We test our method on five large-scale real-world datasets. The results show that Neural Calibration significantly improves against uncalibrated predictions in all well-known metrics such as the negative log-likelihood, the Brier score, the AUC score, as well as our proposed field-level calibration error.