As machine learning is increasingly used in essential systems, it is important to reduce or eliminate the incidence of serious bugs. A growing body of research has developed machine learning algorithms with formal guarantees about performance, robustness, or fairness. Yet, the analysis of these algorithms is often complex, and implementing such systems in practice introduces room for error. Proof assistants can be used to formally verify machine learning systems by constructing machine checked proofs of correctness that rule out such bugs. However, reasoning about probabilistic claims inside of a proof assistant remains challenging. We show how a probabilistic program can be automatically represented in a theorem prover using the concept of \emph{reparameterization}, and how some of the tedious proofs of measurability can be generated automatically from the probabilistic program. To demonstrate that this approach is broad enough to handle rather different types of machine learning systems, we verify both a classic result from statistical learning theory (PAC-learnability of decision stumps) and prove that the null model used in a Bayesian hypothesis test satisfies a fairness criterion called demographic parity.

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to overconfident models that generalize poorly to samples that are not from the original training distribution. Moreover, such standard DNNs do not allow to leverage information from heterogeneously annotated training data, where for example, labels may be provided with different levels of granularity. Furthermore, DNNs do not produce results with simultaneous different levels of confidence for different levels of detail, they are most commonly an all or nothing approach. To address these challenges, we introduce the concept of nested learning: how to obtain a hierarchical representation of the input such that a coarse label can be extracted first, and sequentially refine this representation, if the sample permits, to obtain successively refined predictions, all of them with the corresponding confidence. We explicitly enforce this behavior by creating a sequence of nested information bottlenecks. Looking at the problem of nested learning from an information theory perspective, we design a network topology with two important properties. First, a sequence of low dimensional (nested) feature embeddings are enforced. Then we show how the explicit combination of nested outputs can improve both the robustness and the accuracy of finer predictions. Experimental results on Cifar-10, Cifar-100, MNIST, Fashion-MNIST, Dbpedia, and Plantvillage demonstrate that nested learning outperforms the same network trained in the standard end-to-end fashion.

Each year, almost 10% of claims are denied by payers (i.e., health insurance plans). With the cost to recover these denials and underpayments, predicting payer response (likelihood of payment) from claims data with a high degree of accuracy and precision is anticipated to improve healthcare staffs' performance productivity and drive better patient financial experience and satisfaction in the revenue cycle (Barkholz, 2017). However, constructing advanced predictive analytics models has been considered challenging in the last twenty years. That said, we propose a (low-level) context-dependent compact representation of patients' historical claim records by effectively learning complicated dependencies in the (high-level) claim inputs. Built on this new latent representation, we demonstrate that a deep learning-based framework, Deep Claim, can accurately predict various responses from multiple payers using 2,905,026 de-identified claims data from two US health systems. Deep Claim's improvements over carefully chosen baselines in predicting claim denials are most pronounced as 22.21% relative recall gain (at 95% precision) on Health System A, which implies Deep Claim can find 22.21% more denials than the best baseline system.

The use of black-box optimization for the design of new biological sequences is an emerging research area with potentially revolutionary impact. The cost and latency of wet-lab experiments requires methods that find good sequences in few experimental rounds of large batches of sequences--a setting that off-the-shelf black-box optimization methods are ill-equipped to handle. We find that the performance of existing methods varies drastically across optimization tasks, posing a significant obstacle to real-world applications. To improve robustness, we propose Population-Based Black-Box Optimization (P3BO), which generates batches of sequences by sampling from an ensemble of methods. The number of sequences sampled from any method is proportional to the quality of sequences it previously proposed, allowing P3BO to combine the strengths of individual methods while hedging against their innate brittleness. Adapting the hyper-parameters of each of the methods online using evolutionary optimization further improves performance. Through extensive experiments on in-silico optimization tasks, we show that P3BO outperforms any single method in its population, proposing higher quality sequences as well as more diverse batches. As such, P3BO and Adaptive-P3BO are a crucial step towards deploying ML to real-world sequence design.

Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disentangling Variational AutoEncoder (FD-VAE) for fair representation learning. This network disentangles latent space into three subspaces with a decorrelation loss that encourages each subspace to contain independent information: 1) target attribute information, 2) protected attribute information, 3) mutual attribute information. After the representation learning, this disentangled representation is leveraged for fairer downstream classification by excluding the subspace with the protected attribute information. We demonstrate the effectiveness of our model through extensive experiments on CelebA and UTK Face datasets. Our method outperforms the previous state-of-the-art method by large margins in terms of equal opportunity and equalized odds.

To explore heterogeneous information networks (HINs), network representation learning (NRL) is proposed, which represents a network in a low-dimension space. Recently, graph neural networks (GNNs) have drawn a lot of attention which are very expressive for mining a HIN, while they suffer from low efficiency issue. In this paper, we propose a pre-training and fine-tuning framework PF-HIN to capture the features of a HIN. Unlike traditional GNNs that have to train the whole model for each downstream task, PF-HIN only needs to fine-tune the model using the pre-trained parameters and minimal extra task-specific parameters, thus improving the model efficiency and effectiveness. Specifically, in pre-training phase, we first use a ranking-based BFS strategy to form the input node sequence. Then inspired by BERT, we adopt deep bi-directional transformer encoders to train the model, which is a variant of GNN aggregator that is more powerful than traditional deep neural networks like CNN and LSTM. The model is pre-trained based on two tasks, i.e., masked node modeling (MNM) and adjacent node prediction (ANP). Additionally, we leverage factorized embedding parameterization and cross-layer parameter sharing to reduce the parameters. In fine-tuning stage, we choose four benchmark downstream tasks, i.e., link prediction, similarity search, node classification and node clustering. We use node sequence pairs as input for link prediction and similarity search, and a single node sequence as input for node classification and clustering. The experimental results of the above tasks on four real-world datasets verify the advancement of PF-HIN, as it outperforms state-of-the-art alternatives consistently and significantly.

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. The most common non-invasive BCI modality, electroencephalogram (EEG), is sensitive to noise/artifact and suffers between-subject/within-subject non-stationarity. Therefore, it is difficult to build a generic pattern recognition model in an EEG-based BCI system that is optimal for different subjects, during different sessions, for different devices and tasks. Usually, a calibration session is needed to collect some training data for a new subject, which is time-consuming and user unfriendly. Transfer learning (TL), which utilizes data or knowledge from similar or relevant subjects/sessions/devices/tasks to facilitate learning for a new subject/session/device/task, is frequently used to reduce the amount of calibration effort. This paper reviews journal publications on TL approaches in EEG-based BCIs in the last few years, i.e., since 2016. Six paradigms and applications -- motor imagery, event-related potentials, steady-state visual evoked potentials, affective BCIs, regression problems, and adversarial attacks -- are considered. For each paradigm/application, we group the TL approaches into cross-subject/session, cross-device, and cross-task settings and review them separately. Observations and conclusions are made at the end of the paper, which may point to future research directions.

The Variational Auto-Encoder (VAE) belongs to a class of models, which we will refer to as deep maximum likelihood models, that uses a deep neural network to learn a maximum likelihood model for some input data. They are perhaps the most simple and efficient deep maximum likelihood model available, and have thus gained popularity in representation learning and generative image modeling. Unfortunately, in my opinion, in some circles the term "VAE" has become somewhat synonymous with "an auto-encoder with stochastic regularization that generates useful or beautiful samples", which has led to various misconceptions about VAEs. In this tutorial, we will return to the probabilistic and information theoretic roots of VAEs, clarify common misconceptions about VAEs, and look at a toy example on 2D data that will illustrate the capabilities and limitations of VAEs. In Section 2, we will give an overview of what is a maximum likelihood model and what a VAE looks like.

The Traveling Salesperson Problem (TSP) is a classical N P-hard optimization problem of utmost relevance, e.g., in transportation logistics, bioinformatics or circuit board fabrication. The goal is to route a salesperson through a set of cities such that each city is visited exactly once and the tour is of minimal length. In the past decades tremendous progress has been made in the development of high-performing heuristic TSP solvers. The local search-based Lin-Kernigham Heuristic (LKH) [14] and the genetic algorithm Edge-Assembly-Crossover (EAX) [35], along with their respective restart versions introduced in Kotthoff et al. [25], undeniably pose the state-of-the-art in inexact TSP solving. Automated Algorithm Selection (AS), originally proposed by Rice [39] back in 1976, is a powerful framework to predict the best-performing solver(s) from a portfolio of candidate solvers by means of machine learning. It has been successfully applied to a wide spectrum of challenging optimization problems in both the combinatorial [24, 29, 30, 40, 48] and continuous domain [21, 4] with partly astonishing performance gains - see the recent survey by Kerschke et al. [19] for a comprehensive overview. In particular, the TSP was subject to several successful ASstudies [25, 20, 33, 34, 37] which exploited the complementary performance profiles of simple heuristics on the one hand and the state-of-the-art solvers LKH and EAX on classical TSP benchmark sets on the other hand.

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a change in the classifier output statistics. To construct these explanations, we design a learning framework that leverages a generative model and information-theoretic measures of causal influence. Our objective function encourages both the generative model to faithfully represent the data distribution and the latent factors to have a large causal influence on the classifier output. Our method learns both global and local explanations, is compatible with any classifier that admits class probabilities and a gradient, and does not require labeled attributes or knowledge of causal structure. Using carefully controlled test cases, we provide intuition that illuminates the function of our causal objective. We then demonstrate the practical utility of our method on image recognition tasks.