This Agreement shall begin on the date hereof. Certain parts of this website offer the opportunity for users to post opinions, information and material including without limitation academic papers and data ('Material') in areas of the website. FACULTY OPINIONS does not claim any ownership in the Material that you or any other user posts. FACULTY OPINIONS does not screen, edit, publish or review Material prior to its appearance on the website and is not responsible for it. Material does not reflect the views or opinions of FACULTY OPINIONS, its agents or affiliates.

The problem of domain adaptation conventionally considers the setting where a source domain has plenty of labeled data, and a target domain (with a different data distribution) has plenty of unlabeled data but none or very limited labeled data. In this paper, we address the setting where the target domain has only limited labeled data from a distribution that is expected to change frequently. We first propose a fast and light-weight method for adapting a Gaussian mixture density network (MDN) using only a small set of target domain samples. This method is well-suited for the setting where the distribution of target data changes rapidly (e.g., a wireless channel), making it challenging to collect a large number of samples and retrain. We then apply the proposed MDN adaptation method to the problem of end-of-end learning of a wireless communication autoencoder. A communication autoencoder models the encoder, decoder, and the channel using neural networks, and learns them jointly to minimize the overall decoding error rate. However, the error rate of an autoencoder trained on a particular (source) channel distribution can degrade as the channel distribution changes frequently, not allowing enough time for data collection and retraining of the autoencoder to the target channel distribution. We propose a method for adapting the autoencoder without modifying the encoder and decoder neural networks, and adapting only the MDN model of the channel. The method utilizes feature transformations at the decoder to compensate for changes in the channel distribution, and effectively present to the decoder samples close to the source distribution. Experimental evaluation on simulated datasets and real mmWave wireless channels demonstrate that the proposed methods can quickly adapt the MDN model, and improve or maintain the error rate of the autoencoder under changing channel conditions.

Tensor models play an increasingly prominent role in many fields, notably in machine learning. In several applications of such models, such as community detection, topic modeling and Gaussian mixture learning, one must estimate a low-rank signal from a noisy tensor. Hence, understanding the fundamental limits and the attainable performance of estimators of that signal inevitably calls for the study of random tensors. Substantial progress has been achieved on this subject thanks to recent efforts, under the assumption that the tensor dimensions grow large. Yet, some of the most significant among these results--in particular, a precise characterization of the abrupt phase transition (in terms of signal-to-noise ratio) that governs the performance of the maximum likelihood (ML) estimator of a symmetric rank-one model with Gaussian noise--were derived on the basis of statistical physics ideas, which are not easily accessible to non-experts. In this work, we develop a sharply distinct approach, relying instead on standard but powerful tools brought by years of advances in random matrix theory. The key idea is to study the spectra of random matrices arising from contractions of a given random tensor. We show how this gives access to spectral properties of the random tensor itself. In the specific case of a symmetric rank-one model with Gaussian noise, our technique yields a hitherto unknown characterization of the local maximum of the ML problem that is global above the phase transition threshold. This characterization is in terms of a fixed-point equation satisfied by a formula that had only been previously obtained via statistical physics methods. Moreover, our analysis sheds light on certain properties of the landscape of the ML problem in the large-dimensional setting. Our approach is versatile and can be extended to other models, such as asymmetric, non-Gaussian and higher-order ones.

This survey gives an overview of Monte Carlo methodologies using surrogate models, for dealing with densities which are intractable, costly, and/or noisy. This type of problem can be found in numerous real-world scenarios, including stochastic optimization and reinforcement learning, where each evaluation of a density function may incur some computationally-expensive or even physical (real-world activity) cost, likely to give different results each time. The surrogate model does not incur this cost, but there are important trade-offs and considerations involved in the choice and design of such methodologies. We classify the different methodologies into three main classes and describe specific instances of algorithms under a unified notation. A modular scheme which encompasses the considered methods is also presented. A range of application scenarios is discussed, with special attention to the likelihood-free setting and reinforcement learning. Several numerical comparisons are also provided.

Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for machine learning models. They cause significant gaps between model performance in the lab and in the real world. Our work is a solution to prevalence bias. Prevalence bias is the discrepancy between the prevalence of a pathology and its sampling rate in the training dataset, introduced upon collecting data or due to the practioner rebalancing the training batches. This paper lays the theoretical and computational framework for training models, and for prediction, in the presence of prevalence bias. Concretely a bias-corrected loss function, as well as bias-corrected predictive rules, are derived under the principles of Bayesian risk minimization. The loss exhibits a direct connection to the information gain. It offers a principled alternative to heuristic training losses and complements test-time procedures based on selecting an operating point from summary curves. It integrates seamlessly in the current paradigm of (deep) learning using stochastic backpropagation and naturally with Bayesian models.

Information-based Bayesian optimization (BO) algorithms have achieved state-of-the-art performance in optimizing a black-box objective function. However, they usually require several approximations or simplifying assumptions (without clearly understanding their effects on the BO performance) and/or their generalization to batch BO is computationally unwieldy, especially with an increasing batch size. To alleviate these issues, this paper presents a novel trusted-maximizers entropy search (TES) acquisition function: It measures how much an input query contributes to the information gain on the maximizer over a finite set of trusted maximizers, i.e., inputs optimizing functions that are sampled from the Gaussian process posterior belief of the objective function. Evaluating TES requires either only a stochastic approximation with sampling or a deterministic approximation with expectation propagation, both of which are investigated and empirically evaluated using synthetic benchmark objective functions and real-world optimization problems, e.g., hyperparameter tuning of a convolutional neural network and synthesizing 'physically realizable' faces to fool a black-box face recognition system. Though TES can naturally be generalized to a batch variant with either approximation, the latter is amenable to be scaled to a much larger batch size in our experiments.

Particle-based approximate Bayesian inference approaches such as Stein Variational Gradient Descent (SVGD) combine the flexibility and convergence guarantees of sampling methods with the computational benefits of variational inference. In practice, SVGD relies on the choice of an appropriate kernel function, which impacts its ability to model the target distribution -- a challenging problem with only heuristic solutions. We propose Neural Variational Gradient Descent (NVGD), which is based on parameterizing the witness function of the Stein discrepancy by a deep neural network whose parameters are learned in parallel to the inference, mitigating the necessity to make any kernel choices whatsoever. We empirically evaluate our method on popular synthetic inference problems, real-world Bayesian linear regression, and Bayesian neural network inference.

We propose a models with lower latency and power consumption while Bayesian approach to trend detection in which also ensuring privacy. However, as there is no access to the probability of a keyword being trendy, given actual data from participating devices, it poses a problem a dataset, is computed via Bayes' Theorem; the for the analysis of federated learning models. Federated analytics probability of a dataset, given that a keyword (Ramage & Mazzocchi) is a practice introduced to is trendy, is computed through secure aggregation solve this problem. It uses the same infrastructure as federated of such conditional probabilities over local learning to aggregate the computed metric by each datasets of users. We propose a protocol, named participating device using local data and shared models. SAFE, for Bayesian federated analytics that offers Federated analytics has already gone beyond just measuring sufficient privacy for production-grade use the quality metric to computing descriptive statistics cases and reduces the computational burden of (Ramage & Mazzocchi; Zhu et al., 2020), generating synthetic users and an aggregator. We illustrate this approach data (Xin et al., 2020; Chaulwar, 2020) and learning with a trend detection experiment and discuss new insights (Chen et al., 2019). These methods are generally how this approach could be extended further combined with secure aggregation protocols to ensure to make it production-ready.

We perform approximate inference in state-space models that allow for nonlinear higher-order Markov chains in latent space. The conditional independencies of the generative model enable us to parameterize only an inference model, which learns to estimate clean states in a self-supervised manner using maximum likelihood. First, we propose a recurrent method that is trained directly on noisy observations. Afterward, we cast the model such that the optimization problem leads to an update scheme that backpropagates through a recursion similar to the classical Kalman filter and smoother. In scientific applications, domain knowledge can give a linear approximation of the latent transition maps. We can easily incorporate this knowledge into our model, leading to a hybrid inference approach. In contrast to other methods, experiments show that the hybrid method makes the inferred latent states physically more interpretable and accurate, especially in low-data regimes. Furthermore, we do not rely on an additional parameterization of the generative model or supervision via uncorrupted observations or ground truth latent states. Despite our model's simplicity, we obtain competitive results on the chaotic Lorenz system compared to a fully supervised approach and outperform a method based on variational inference.

Linear mixed models (LMMs) are instrumental for regression analysis with structured dependence, such as grouped, clustered, or multilevel data. However, selection among the covariates--while accounting for this structured dependence--remains a challenge. We introduce a Bayesian decision analysis for subset selection with LMMs. Using a Mahalanobis loss function that incorporates the structured dependence, we derive optimal linear actions for any subset of covariates and under any Bayesian LMM. Crucially, these actions inherit shrinkage or regularization and uncertainty quantification from the underlying Bayesian LMM. Rather than selecting a single "best" subset, which is often unstable and limited in its information content, we collect the acceptable family of subsets that nearly match the predictive ability of the "best" subset. The acceptable family is summarized by its smallest member and key variable importance metrics. Customized subset search and out-of-sample approximation algorithms are provided for more scalable computing. These tools are applied to simulated data and a longitudinal physical activity dataset, and in both cases demonstrate excellent prediction, estimation, and selection ability.