Split learning enables efficient and privacy-aware training of a deep neural network by splitting a neural network so that the clients (data holders) compute the first layers and only share the intermediate output with the central compute-heavy server. This paradigm introduces a new attack medium in which the server has full control over what the client models learn, which has already been exploited to infer the private data of clients and to implement backdoors in the client models. Although previous work has shown that clients can successfully detect such training-hijacking attacks, the proposed methods rely on heuristics, require tuning of many hyperparameters, and do not fully utilize the clients' capabilities. In this work, we show that given modest assumptions regarding the clients' compute capabilities, an out-of-the-box outlier detection method can be used to detect existing training-hijacking attacks with almost-zero false positive rates. We conclude through experiments on different tasks that the simplicity of our approach we name SplitOut makes it a more viable and reliable alternative compared to the earlier detection methods.

Deep image prior (DIP) and its variants have showed remarkable potential for solving inverse problems in computer vision, without any extra training data. Practical DIP models are often substantially overparameterized. During the fitting process, these models learn mostly the desired visual content first, and then pick up the potential modeling and observational noise, i.e., overfitting. Thus, the practicality of DIP often depends critically on good early stopping (ES) that captures the transition period. In this regard, the majority of DIP works for vision tasks only demonstrates the potential of the models -- reporting the peak performance against the ground truth, but provides no clue about how to operationally obtain near-peak performance without access to the groundtruth. In this paper, we set to break this practicality barrier of DIP, and propose an efficient ES strategy, which consistently detects near-peak performance across several vision tasks and DIP variants. Based on a simple measure of dispersion of consecutive DIP reconstructions, our ES method not only outpaces the existing ones -- which only work in very narrow domains, but also remains effective when combined with a number of methods that try to mitigate the overfitting. The code is available at https://github.com/sun-umn/Early_Stopping_for_DIP.

Navigating the complex landscape of single-cell transcriptomic data presents significant challenges. Central to this challenge is the identification of a meaningful representation of high-dimensional gene expression patterns that sheds light on the structural and functional properties of cell types. Pursuing model interpretability and computational simplicity, we often look for a linear transformation of the original data that aligns with key phenotypic features of cells. In response to this need, we introduce factorized linear discriminant analysis (FLDA), a novel method for linear dimensionality reduction. The crux of FLDA lies in identifying a linear function of gene expression levels that is highly correlated with one phenotypic feature while minimizing the influence of others. To augment this method, we integrate it with a sparsity-based regularization algorithm. This integration is crucial as it selects a subset of genes pivotal to a specific phenotypic feature or a combination thereof. To illustrate the effectiveness of FLDA, we apply it to transcriptomic datasets from neurons in the Drosophila optic lobe. We demonstrate that FLDA not only captures the inherent structural patterns aligned with phenotypic features but also uncovers key genes associated with each phenotype.

One of the important types of data in several applications is censored survival data processed in the framework of survival analysis [1, 2]. This type of data can be found in applications where objects are characterized by times to some events of interest, for example, by times to failure in reliability, times to recovery or times to death in medicine, times to bankruptcy of a bank or times to an economic crisis in economics. The important peculiarity of survival data is that the corresponding event does not necessarily occur during its observation period. In this case, we say about the so-called censored or right-censored data [3]. There are many machine learning models dealing with survival data, including models based on applying and extending the Cox proportional hazard model [4], for example, models presented in [5, 6], models based on a survival modification of random forests and called random survival forests (RSF) [7, 8, 9, 10, 11], models extending the neural networks [6, 12, 13, 14]. These models have gained considerable attention for their ability to analyze time-to-event data and to predict survival outcomes accurately. However, most models are perceived as black boxes, lacking interpretability.

Non-parametric machine learning models, such as random forests and gradient boosted trees, are frequently used to estimate house prices due to their predictive accuracy, but such methods are often limited in their ability to quantify prediction uncertainty. Conformal Prediction (CP) is a model-agnostic framework for constructing confidence sets around machine learning prediction models with minimal assumptions. However, due to the spatial dependencies observed in house prices, direct application of CP leads to confidence sets that are not calibrated everywhere, i.e., too large of confidence sets in certain geographical regions and too small in others. We survey various approaches to adjust the CP confidence set to account for this and demonstrate their performance on a data set from the housing market in Oslo, Norway. Our findings indicate that calibrating the confidence sets on a \textit{locally weighted} version of the non-conformity scores makes the coverage more consistently calibrated in different geographical regions. We also perform a simulation study on synthetically generated sale prices to empirically explore the performance of CP on housing market data under idealized conditions with known data-generating mechanisms.

Large learning rates, when applied to gradient descent for nonconvex optimization, yield various implicit biases including the edge of stability (Cohen et al., 2021), balancing (Wang et al., 2022a), and catapult (Lewkowycz et al., 2020). These phenomena cannot be well explained by classical optimization theory. Though significant theoretical progress has been made in understanding these implicit biases, it remains unclear for which objective functions would they be more likely. This paper provides an initial step in answering this question and also shows that these implicit biases are in fact various tips of the same iceberg. To establish these results, we develop a global convergence theory under large learning rates, for a family of nonconvex functions without globally Lipschitz continuous gradient, which was typically assumed in existing convergence analysis. Specifically, these phenomena are more likely to occur when the optimization objective function has good regularity. This regularity, together with gradient descent using a large learning rate that favors flatter regions, results in these nontrivial dynamical behaviors. Another corollary is the first non-asymptotic convergence rate bound for large-learning-rate gradient descent optimization of nonconvex functions. Although our theory only applies to specific functions so far, the possibility of extrapolating it to neural networks is also experimentally validated, for which different choices of loss, activation functions, and other techniques such as batch normalization can all affect regularity significantly and lead to very different training dynamics.

In spatial statistics, fast and accurate parameter estimation, coupled with a reliable means of uncertainty quantification, can be challenging when fitting a spatial process to real-world data because the likelihood function might be slow to evaluate or wholly intractable. In this work, we propose using convolutional neural networks to learn the likelihood function of a spatial process. Through a specifically designed classification task, our neural network implicitly learns the likelihood function, even in situations where the exact likelihood is not explicitly available. Once trained on the classification task, our neural network is calibrated using Platt scaling which improves the accuracy of the neural likelihood surfaces. To demonstrate our approach, we compare neural likelihood surfaces and the resulting maximum likelihood estimates and approximate confidence regions with the equivalent for exact or approximate likelihood for two different spatial processes: a Gaussian process and a Brown-Resnick process which have computationally intensive and intractable likelihoods, respectively. We conclude that our method provides fast and accurate parameter estimation with a reliable method of uncertainty quantification in situations where standard methods are either undesirably slow or inaccurate. The method is applicable to any spatial process on a grid from which fast simulations are available.

High-dimensional and complex spectral structures make the clustering of hyperspectral images (HSI) a challenging task. Subspace clustering is an effective approach for addressing this problem. However, current subspace clustering algorithms are primarily designed for a single view and do not fully exploit the spatial or textural feature information in HSI. In this study, contrastive multi-view subspace clustering of HSI was proposed based on graph convolutional networks. Pixel neighbor textural and spatial-spectral information were sent to construct two graph convolutional subspaces to learn their affinity matrices. To maximize the interaction between different views, a contrastive learning algorithm was introduced to promote the consistency of positive samples and assist the model in extracting robust features. An attention-based fusion module was used to adaptively integrate these affinity matrices, constructing a more discriminative affinity matrix. The model was evaluated using four popular HSI datasets: Indian Pines, Pavia University, Houston, and Xu Zhou. It achieved overall accuracies of 97.61%, 96.69%, 87.21%, and 97.65%, respectively, and significantly outperformed state-of-the-art clustering methods. In conclusion, the proposed model effectively improves the clustering accuracy of HSI.

A fundamental trait of intelligence involves finding novel and creative solutions to address a given challenge or to adapt to unforeseen situations. Reflecting this, Quality-Diversity optimization is a family of Evolutionary Algorithms, that generates collections of both diverse and high-performing solutions. Among these, MAP-Elites is a prominent example, that has been successfully applied to a variety of domains, including evolutionary robotics. However, MAP-Elites performs a divergent search with random mutations originating from Genetic Algorithms, and thus, is limited to evolving populations of low-dimensional solutions. PGA-MAP-Elites overcomes this limitation using a gradient-based variation operator inspired by deep reinforcement learning which enables the evolution of large neural networks. Although high-performing in many environments, PGA-MAP-Elites fails on several tasks where the convergent search of the gradient-based variation operator hinders diversity. In this work, we present three contributions: (1) we enhance the Policy Gradient variation operator with a descriptor-conditioned critic that reconciles diversity search with gradient-based methods, (2) we leverage the actor-critic training to learn a descriptor-conditioned policy at no additional cost, distilling the knowledge of the population into one single versatile policy that can execute a diversity of behaviors, (3) we exploit the descriptor-conditioned actor by injecting it in the population, despite network architecture differences. Our method, DCG-MAP-Elites, achieves equal or higher QD score and coverage compared to all baselines on seven challenging continuous control locomotion tasks.

Text classification is an important topic in the field of natural language processing. It has been preliminarily applied in information retrieval, digital library, automatic abstracting, text filtering, word semantic discrimination and many other fields. The aim of this research is to use a variety of algorithms to test the ability to identify offensive posts and evaluate their performance against a variety of assessment methods. The motivation for this project is to reduce the harm of these languages to human censors by automating the screening of offending posts. The field is a new one, and despite much interest in the past two years, there has been no focus on the object of the offence. Through the experiment of this project, it should inspire future research on identification methods as well as identification content.