Recent years have witnessed the emergence of 3D medical imaging techniques with the development of 3D sensors and technology. Due to the presence of noise in image acquisition, registration researchers focused on an alternative way to represent medical images. An alternative way to analyze medical imaging is by understanding the 3D shapes represented in terms of point-cloud. Though in the medical imaging community, 3D point-cloud processing is not a ``go-to'' choice, it is a ``natural'' way to capture 3D shapes. However, as the number of samples for medical images are small, researchers have used pre-trained models to fine-tune on medical images. Furthermore, due to different modality in medical images, standard generative models can not be used to generate new samples of medical images. In this work, we use the advantage of point-cloud representation of 3D structures of medical images and propose a Gaussian mixture model-based generation scheme. Our proposed method is robust to outliers. Experimental validation has been performed to show that the proposed scheme can generate new 3D structures using interpolation techniques, i.e., given two 3D structures represented as point-clouds, we can generate point-clouds in between. We have also generated new point-clouds for subjects with and without dementia and show that the generated samples are indeed closely matched to the respective training samples from the same class.

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model inter-pretability and explanation has become more critical. Classical approaches that assess feature importance ( e.g., saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually change the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a "tuning knob" to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input. With the explosive adoption of deep learning for real-world applications, explanation and model interpretability have received substantial attention from the research community (Kim, 2015; Doshi-V elez & Kim, 2017; Molnar, 2019; Guidotti et al., 2019). Explaining an outcome of a model in high stake applications, such as medical diagnosis from radiology images, is of paramount importance to detect hidden biases in data (Cramer et al., 2018), evaluate the fairness of the model (Doshi-V elez & Kim, 2017), and build trust in the system (Glass et al., 2008). For example, consider evaluating a computer-aided diagnosis of Alzheimer's disease from medical images. The physician should be able to assess whether or not the model pays attention to age-related or disease-related variations in an image in order to trust the system. Given a query, our model provides an explanation that gradually exaggerates the semantic effect of one class, which is equivalent to traversing the decision boundary from side to another. Although not always clear, there are subtle differences between interpretability and explanation (Turner, 2016). While the former mainly focuses on building or approximating models that are locally or globally interpretable (Ribeiro et al., 2016), the latter aims at explaining a predictor a-posteriori.

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused on trying to improve these models by enhancing the pre-training phase, either via better choice of hyperparameters or by leveraging an improved formulation. However, the pre-training phase is computationally expensive and often done on private datasets. In this work, we present a method that leverages BERT's fine-tuning phase to its fullest, by applying an extensive number of parallel classifier heads, which are enforced to be orthogonal, while adaptively eliminating the weaker heads during training. Our method allows the model to converge to an optimal number of parallel classifiers, depending on the given dataset at hand. We conduct an extensive inter- and intra-dataset evaluations, showing that our method improves the robustness of BERT, sometimes leading to a +9\% gain in accuracy. These results highlight the importance of a proper fine-tuning procedure, especially for relatively smaller-sized datasets. Our code is attached as supplementary and our models will be made completely public.

An active learning algorithm for the classification of high-dimensional images is proposed in which spatially-regularized nonlinear diffusion geometry is used to characterize cluster cores. The proposed method samples from estimated cluster cores in order to generate a small but potent set of training labels which propagate to the remainder of the dataset via the underlying diffusion process. By spatially regularizing the rich, high-dimensional spectral information of the image to efficiently estimate the most significant and influential points in the data, our approach avoids redundancy in the training dataset. This allows it to produce high-accuracy labelings with a very small number of training labels. The proposed algorithm admits an efficient numerical implementation that scales essentially linearly in the number of data points under a suitable data model and enjoys state-of-the-art performance on real hyperspectral images.

Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors. As the cardinality of the entities increases, the embedding components can easily contain millions of parameters and become the bottleneck in both storage and inference due to large memory consumption. This work focuses on post-training 4-bit quantization on the continuous embeddings. We propose row-wise uniform quantization with greedy search and codebook-based quantization that consistently outperforms state-of-the-art quantization approaches on reducing accuracy degradation. We deploy our uniform quantization technique on a production model in Facebook and demonstrate that it can reduce the model size to only 13.89% of the single-precision version while the model quality stays neutral.

We study the problem, introduced by Qiao and Valiant, of learning from untrusted batches. Here, we assume $m$ users, all of whom have samples from some underlying distribution $p$ over $1, \ldots, n$. Each user sends a batch of $k$ i.i.d. samples from this distribution; however an $\epsilon$-fraction of users are untrustworthy and can send adversarially chosen responses. The goal is then to learn $p$ in total variation distance. When $k = 1$ this is the standard robust univariate density estimation setting and it is well-understood that $\Omega (\epsilon)$ error is unavoidable. Suprisingly, Qiao and Valiant gave an estimator which improves upon this rate when $k$ is large. Unfortunately, their algorithms run in time exponential in either $n$ or $k$. We first give a sequence of polynomial time algorithms whose estimation error approaches the information-theoretically optimal bound for this problem. Our approach is based on recent algorithms derived from the sum-of-squares hierarchy, in the context of high-dimensional robust estimation. We show that algorithms for learning from untrusted batches can also be cast in this framework, but by working with a more complicated set of test functions. It turns out this abstraction is quite powerful and can be generalized to incorporate additional problem specific constraints. Our second and main result is to show that this technology can be leveraged to build in prior knowledge about the shape of the distribution. Crucially, this allows us to reduce the sample complexity of learning from untrusted batches to polylogarithmic in $n$ for most natural classes of distributions, which is important in many applications. To do so, we demonstrate that these sum-of-squares algorithms for robust mean estimation can be made to handle complex combinatorial constraints (e.g. those arising from VC theory), which may be of independent technical interest.

While model selection is a well-studied topic in parametric and nonparametric regression or density estimation, model selection of possibly high dimensional nuisance parameters in semiparametric problems is far less developed. In this paper, we propose a new model selection framework for making inferences about a finite dimensional functional defined on a semiparametric model, when the latter admits a doubly robust estimating function. The class of such doubly robust functionals is quite large, including many missing data and causal inference problems. Under double robustness, the estimated functional should incur no bias if either of two nuisance parameters is evaluated at the truth while the other spans a large collection of candidate models. We introduce two model selection criteria for bias reduction of functional of interest, each based on a novel definition of pseudo-risk for the functional that embodies this double robustness property and thus may be used to select the candidate model that is nearest to fulfilling this property even when all models are wrong. Both selection criteria have a bias awareness property that selection of one nuisance parameter can be made to compensate for excessive bias due to poor learning of the other nuisance parameter. We establish an oracle property for a multi-fold cross-validation version of the new model selection criteria which states that our empirical criteria perform nearly as well as an oracle with a priori knowledge of the pseudo-risk for each candidate model. We also describe a smooth approximation to the selection criteria which allows for valid post-selection inference. Finally, we perform model selection of a semiparametric estimator of average treatment effect given an ensemble of candidate machine learning methods to account for confounding in a study of right heart catheterization in the ICU of critically ill patients.

Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant also in the calculation of the dot product ("convolution") in a 1-D convolution layer. In this work a method is proposed for aligning the convolution filter and the input where they are locally out of phase utilising an algorithm similar to the Dynamic Time Warp. The proposed method enables embedding a non-parametric warping of temporal sequences for increasing similarity directly in deep networks and can expand on the generalisation capabilities and the capacity of standard 1-D convolution layer where local sequential deformations are present in the input. Experimental results demonstrate the proposed method exceeds or matches the standard 1-D convolution layer in terms of the maximum accuracy achieved on a number of time series classification tasks. In addition the impact of different hyperparameters settings is investigated given different datasets and the results support the conclusions of previous work done in relation to the choice of DTW parameter values. The proposed layer can be freely integrated with other typical layers to compose deep artificial neural networks of an arbitrary architecture that are trained using standard stochastic gradient descent.

Wessel Bruinsma ‡ wpb23@cam.ac.uk 1. Introduction A principled approach to prediction tasks is to choose a statistical model that explains the data. The choice of the model class is crucial and has to observe the bias-variance tradeoff, which motivates the need for principled approaches to selecting the best model class from a set of options. Whilst model selection can be done manually by trial and error, the process tends to consume considerable time and resources and be prone to human biases. Bayesian model selection (MacKay, 1992; Rasmussen and Ghahramani, 2001), treats the model class as a random variable and computes its posterior distribution. It offers a built-in complexity regulariser, commonly known as Bayesian Occams razor, which penalises models whose complexity is excessive or too modest.

Whether stochastic or parametric, the Pareto/NBD model can only be utilized for an in-sample prediction rather than an out-of-sample prediction. This research thus provides a neural network based extension of the Pareto/NBD model to estimate the out-of-sample parameters, which overrides the estimation burden and the application dilemma of the Pareto/NBD approach. The empirical results indicate that the Pareto/NBD model and neural network algorithms have similar predictability for identifying inactive customers. Even with a strong trend fitting on the customer count of each repeat purchase point, the Pareto/NBD model underestimates repeat purchases at both the individual and aggregate levels. Nonetheless, when embedding the likelihood function of the Pareto/NBD model into the loss function, the proposed parameter estimation method shows extraordinary predictability on repeat purchases at these two levels. Furthermore, the proposed neural network based method is highly efficient and resource-friendly and can be deployed in cloud computing to handle with big data analysis.