AISTATS 2021 Papers

Marked temporal point processes (MTPP) have emerged as a powerful framework to model the underlying generative mechanism of asynchronous events localized in continuous time. Most existing models and inference methods in MTPP framework consider only the complete observation scenario i.e. the event sequence being modeled is completely observed with no missing events – an ideal setting barely encountered in practice. A recent line of work which considers missing events uses supervised learning techniques which require a missing or observed label for each event. In this work, we provide a novel unsupervised model and inference method for MTPPs in presence of missing events. We first model the generative processes of observed events and missing events using two MTPPs, where the missing events are represented as latent random variables. Then we devise an unsupervised training method that jointly learns both the MTPPs by means of variational inference. Experiments with real datasets show that our modeling and inference frameworks can effectively impute the missing data among the observed events, which in turn enhances its predictive prowess.

This paper explores the statistical properties of fair representation learning, a pre-processing method that preemptively removes the correlations between features and sensitive attributes by mapping features to a fair representation space. We show that the demographic parity of a representation can be certified from a finite sample if and only if the mapping guarantees that the chi-squared mutual information between features and representations is finite for distributions of the features. Empirically, we find that smoothing representations with an additive Gaussian white noise provides generalization guarantees of fairness certificates, which improves upon existing fair representation learning approaches.

Probabilistic graphical models (PGMs) are effective for capturing the statistical dependencies in stochastic databases. In many domains (e.g., working with multimodal data), one faces multiple information layers that can be modeled by structurally similar PGMs. While learning the structures of PGMs in isolation is well-investigated, the algorithmic design and performance limits of learning from multiple coupled PGMs are investigated far less. This paper considers learning the structural similarities shared by a pair of Ising PGMs. The objective is learning the shared structure with no regard for the structures exclusive to either of the graphs, and significantly different from the existing approaches that focus on entire structure of the graphs. We propose an algorithm for the shared structure learning objective, evaluate its performance empirically, and compare with existing approaches on structure learning of single graphs.

We study the generation of prediction intervals in regression for uncertainty quantification. This task can be formalized as an empirical constrained optimization problem that minimizes the average interval width while maintaining the coverage accuracy across data. We strengthen the existing literature by studying two aspects of this empirical optimization. First is a general learning theory to characterize the optimality-feasibility tradeoff that encompasses Lipschitz continuity and VC-subgraph classes, which are exemplified in regression trees and neural networks. Second is a calibration machinery and the corresponding statistical theory to optimally select the regularization parameter that manages this tradeoff, which bypasses the overfitting issues in previous approaches in coverage attainment. We empirically demonstrate the strengths of our interval generation and calibration algorithms in terms of testing performances compared to existing benchmarks.

Neural Stochastic Differential Equations model a dynamical environment with neural nets assigned to their drift and diffusion terms. The high expressive power of their nonlinearity comes at the expense of instability in the identification of the large set of free parameters. This paper presents a recipe to improve the prediction accuracy of such models in three steps: i) accounting for epistemic uncertainty by assuming probabilistic weights, ii) incorporation of partial knowledge on the state dynamics, and iii) training the resultant hybrid model by an objective derived from a PAC-Bayesian generalization bound. We observe in our experiments that this recipe effectively translates partial and noisy prior knowledge into an improved model fit.

Organ transplantation can improve life expectancy for recipients, but the probability of a successful transplant depends on the compatibility between donor and recipient features. Current medical practice relies on coarse rules for donor-recipient matching, but is short of domain knowledge regarding the complex factors underlying organ compatibility. In this paper, we formulate the problem of learning data-driven rules for donor-recipient matching using observational data for organ allocations and transplant outcomes. This problem departs from the standard supervised learning setup in that it involves matching two feature spaces (for donors and recipients), and requires estimating transplant outcomes under counterfactual matches not observed in the data. To address this problem, we propose a model based on representation learning to predict donor-recipient compatibility—our model learns representations that cluster donor features, and applies donor-invariant transformations to recipient features to predict transplant outcomes under a given donor-recipient feature instance. Experiments on several semi-synthetic and real-world datasets show that our model outperforms state-of-art allocation models and real-world policies executed by human experts.

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we first propose a computationally inefficient algorithm with optimal O(\sqrt{T}) regret and another computationally efficient variant with O(T^{3/4}) regret, where T is the number of interactions. Next, taking inspiration from adversarial linear bandits, we develop yet another efficient algorithm with O(\sqrt{T}) regret under a different set of assumptions, improving the best existing result by Hao et al. (2020) with O(T^{2/3}) regret. Moreover, we draw a connection between this algorithm and the Natural Policy Gradient algorithm proposed by Kakade (2002), and show that our analysis improves the sample complexity bound recently given by Agarwal et al. (2020).

Machine learning is used to make decisions for individuals in various fields, which require us to achieve good prediction accuracy while ensuring fairness with respect to sensitive features (e.g., race and gender). This problem, however, remains difficult in complex real-world scenarios. To quantify unfairness under such situations, existing methods utilize path-specific causal effects. However, none of them can ensure fairness for each individual without making impractical functional assumptions about the data. In this paper, we propose a far more practical framework for learning an individually fair classifier. To avoid restrictive functional assumptions, we define the probability of individual unfairness (PIU) and solve an optimization problem where PIU’s upper bound, which can be estimated from data, is controlled to be close to zero. We elucidate why our method can guarantee fairness for each individual. Experimental results show that our method can learn an individually fair classifier at a slight cost of accuracy.

Gaussian Process Latent Variable Model (GPLVM) is a flexible framework to handle uncertain inputs in Gaussian Processes (GPs) and incorporate GPs as components of larger graphical models. Nonetheless, the standard GPLVM variational inference approach is tractable only for a narrow family of kernel functions. The most popular implementations of GPLVM circumvent this limitation using quadrature methods, which may become a computational bottleneck even for relatively low dimensions. For instance, the widely employed Gauss-Hermite quadrature has exponential complexity on the number of dimensions. In this work, we propose using the unscented transformation instead. Overall, this method presents comparable, if not better, performance than off-the-shelf solutions to GPLVM, and its computational complexity scales only linearly on dimension. In contrast to Monte Carlo methods, our approach is deterministic and works well with quasi-Newton methods, such as the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm. We illustrate the applicability of our method with experiments on dimensionality reduction and multistep-ahead prediction with uncertainty propagation.

Many applications of AI involve scoring individuals using a learned function of their attributes. These predictive risk scores are then used to take decisions based on whether the score exceeds a certain threshold, which may vary depending on the context. The level of delegation granted to such systems in critical applications like credit lending and medical diagnosis will heavily depend on how questions of fairness can be answered. In this paper, we study fairness for the problem of learning scoring functions from binary labeled data, a classic learning task known as bipartite ranking. We argue that the functional nature of the ROC curve, the gold standard measure of ranking accuracy in this context, leads to several ways of formulating fairness constraints. We introduce general families of fairness definitions based on the AUC and on ROC curves, and show that our ROC-based constraints can be instantiated such that classifiers obtained by thresholding the scoring function satisfy classification fairness for a desired range of thresholds. We establish generalization bounds for scoring functions learned under such constraints, design practical learning algorithms and show the relevance our approach with numerical experiments on real and synthetic data.

Learning physically structured representations of dynamical systems that include contact between different objects is an important problem for learning-based approaches in robotics. Black-box neural networks can learn to approximately represent discontinuous dynamics, but they typically require large quantities of data and often suffer from pathological behaviour when forecasting for longer time horizons. In this work, we use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations in settings that are traditionally difficult for black-box approaches and recent physics inspired neural networks. Our results indicate that an idealised form of touch feedback—which is heavily relied upon by biological systems—is a key component of making this learning problem tractable. Together with the inductive biases introduced through the network architectures, our techniques enable accurate learning of contact dynamics from observations.

Simulated annealing is an effective and general means of optimization. It is in fact inspired by metallurgy, where the temperature of a material determines its behavior in thermodynamics. Likewise, in simulated annealing, the actions that the algorithm takes depend entirely on the value of a variable which captures the notion of temperature. Typically, simulated annealing starts with a high temperature, which makes the algorithm pretty unpredictable, and gradually cools the temperature down to become more stable. A key component that plays a crucial role in the performance of simulated annealing is the criteria under which the temperature changes namely, the cooling schedule. Motivated by this, we study the following question in this work: "Given enough samples to the instances of a specific class of optimization problems, can we design optimal (or approximately optimal) cooling schedules that minimize the runtime or maximize the success rate of the algorithm on average when the underlying problem is drawn uniformly at random from the same class?" We provide positive results both in terms of sample complexity and simulation complexity. For sample complexity, we show that O (m^1/2) samples suffice to find an approximately optimal cooling schedule of length m. We complement this result by giving a lower bound of Ω (m^1/3) on the sample complexity of any learning algorithm that provides an almost optimal cooling schedule. These results are general and rely on no assumption. For simulation complexity, however, we make additional assumptions to measure the success rate of an algorithm. To this end, we introduce the monotone stationary graph that models the performance of simulated annealing. Based on this model, we present polynomial time algorithms with provable guarantees for the learning problem.

Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing probabilistic deep generative models (DGMs), which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. Given the complexities of jointly training such a hybrid model, we introduce novel theory that constrains linear ICA to lie close to the manifold of orthogonal rectangular matrices, the Stiefel manifold. By doing so we create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.

Domain generalization is the problem of machine learning when the training data and the test data come from different “domains” (data distributions). We propose an elementary theoretical model of the domain generalization problem, introducing the concept of a meta-distribution over domains. In our model, the training data available to a learning algorithm consist of multiple datasets, each from a single domain, drawn in turn from the meta-distribution. We show that our model can capture a rich range of learning phenomena specific to domain generalization for three different settings: learning with Massart noise, learning decision trees, and feature selection. We demonstrate approaches that leverage domain generalization to reduce computational or data requirements in each of these settings. Experiments demonstrate that our feature selection algorithm indeed ignores spurious correlations and improves generalization.

Gaussian process-based latent variable models are flexible and theoretically grounded tools for nonlinear dimension reduction, but generalizing to non-Gaussian data likelihoods within this nonlinear framework is statistically challenging. Here, we use random features to develop a family of nonlinear dimension reduction models that are easily extensible to non-Gaussian data likelihoods; we call these random feature latent variable models (RFLVMs). By approximating a nonlinear relationship between the latent space and the observations with a function that is linear with respect to random features, we induce closed-form gradients of the posterior distribution with respect to the latent variable. This allows the RFLVM framework to support computationally tractable nonlinear latent variable models for a variety of data likelihoods in the exponential family without specialized derivations. Our generalized RFLVMs produce results comparable with other state-of-the-art dimension reduction methods on diverse types of data, including neural spike train recordings, images, and text data.

Clinical patient records are an example of high-dimensional data that is typically collected from disparate sources and comprises of multiple likelihoods with noisy as well as missing values. In this work, we propose an unsupervised generative model that can learn a low-dimensional representation among the observations in a latent space, while making use of all available data in a heterogeneous data setting with missing values. We improve upon the existing Gaussian process latent variable model (GPLVM) by incorporating multiple likelihoods and deep neural network parameterised back-constraints to create a non-linear dimensionality reduction technique for heterogeneous data. In addition, we develop a variational inference method for our model that uses numerical quadrature. We establish the effectiveness of our model and compare against existing GPLVM methods on a standard benchmark dataset as well as on clinical data of Parkinson’s disease patients treated at the HUS Helsinki University Hospital.

Bayesian neural networks (BNN) are powerful parametric models for nonlinear regression with uncertainty quantification. However, the approximate inference techniques for weight space priors suffer from several drawbacks. The ‘Bayesian last layer’ (BLL) is an alternative BNN approach that learns the feature space for an exact Bayesian linear model with explicit predictive distributions. However, its predictions outside of the data distribution (OOD) are typically overconfident, as the marginal likelihood objective results in a learned feature space that overfits to the data. We overcome this weakness by introducing a functional prior on the model’s derivatives w.r.t. the inputs. Treating these Jacobians as latent variables, we incorporate the prior into the objective to influence the smoothness and diversity of the features, which enables greater predictive uncertainty. For the BLL, the Jacobians can be computed directly using forward mode automatic differentiation, and the distribution over Jacobians may be obtained in closed-form. We demonstrate this method enhances the BLL to Gaussian process-like performance on tasks where calibrated uncertainty is critical: OOD regression, Bayesian optimization and active learning, which include high-dimensional real-world datasets.

In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, Daskalakis et al 2018, Liang-Stokes 2019, show last iterate convergence of the so called “Optimistic Gradient Descent/Ascent" for the case of \textit{unconstrained} min-max optimization. Moreover, in Mertikopoulos et al 2019 the authors show that Mirror Descent with an extra gradient step displays last iterate convergence for convex-concave problems (both constrained and unconstrained), though their algorithm uses \textit{vanishing stepsizes}. In this work, we show that "Optimistic Multiplicative-Weights Update (OMWU)" with \textit{constant stepsize}, exhibits last iterate convergence locally for convex-concave games, generalizing the results of Daskalakis and Panageas 2019 where last iterate convergence of OMWU was shown only for the \textit{bilinear case}. To the best of our knowledge, this is the first result about last-iterate convergence for constrained zero sum games (beyond the bilinear case) in which the dynamics use constant step-sizes.

Much work has been done recently to make neural networks more interpretable, and one approach is to arrange for the network to use only a subset of the available features. In linear models, Lasso (or $\ell_1$-regularized) regression assigns zero weights to the most irrelevant or redundant features, and is widely used in data science. However the Lasso only applies to linear models. Here we introduce LassoNet, a neural network framework with global feature selection. Our approach achieves feature sparsity by allowing a feature to participate in a hidden unit only if its linear representative is active. Unlike other approaches to feature selection for neural nets, our method uses a modified objective function with constraints, and so integrates feature selection with the parameter learning directly. As a result, it delivers an entire regularization path of solutions with a range of feature sparsity. In experiments with real and simulated data, LassoNet significantly outperforms state-of-the-art methods for feature selection and regression. The LassoNet method uses projected proximal gradient descent, and generalizes directly to deep networks. It can be implemented by adding just a few lines of code to a standard neural network.