Understanding the gradient variance of blackbox Despite the advances of BBVI, little is known about its theoretical variational inference (BBVI) is a crucial step properties. Even when restricted to the locationscale for establishing its convergence and developing family (Definition 2), it is unknown whether BBVI algorithmic improvements. However, existing is guaranteed to converge without having to modify the studies have yet to show that the gradient variance algorithms used in practice, for example, by enforcing of BBVI satisfies the conditions used to bounded domains, bounded support, bounded gradients, study the convergence of stochastic gradient descent and such. This theoretical insight is necessary since BBVI (SGD), the workhorse of BBVI. In this methods are known to be less robust (Yao et al., 2018; work, we show that BBVI satisfies a matching Dhaka et al., 2020; Welandawe et al., 2022; Dhaka et al., bound corresponding to the condition used 2021; Domke, 2020) compared to other inference methods in the SGD literature when applied to smooth and such as Markov chain Monte Carlo. Although progress has quadratically-growing log-likelihoods. Our results been made to formalize the theory of BBVI with some generality, generalize to nonlinear covariance parameterizations the gap between our understanding of BBVI and the widely used in the practice of BBVI.

Dynamical system state estimation and parameter calibration problems are ubiquitous across science and engineering. Bayesian approaches to the problem are the gold standard as they allow for the quantification of uncertainties and enable the seamless fusion of different experimental modalities. When the dynamics are discrete and stochastic, one may employ powerful techniques such as Kalman, particle, or variational filters. Practitioners commonly apply these methods to continuous-time, deterministic dynamical systems after discretizing the dynamics and introducing fictitious transition probabilities. However, approaches based on time-discretization suffer from the curse of dimensionality since the number of random variables grows linearly with the number of time-steps. Furthermore, the introduction of fictitious transition probabilities is an unsatisfactory solution because it increases the number of model parameters and may lead to inference bias. To address these drawbacks, the objective of this paper is to develop a scalable Bayesian approach to state and parameter estimation suitable for continuous-time, deterministic dynamical systems. Our methodology builds upon information field theory. Specifically, we construct a physics-informed prior probability measure on the function space of system responses so that functions that satisfy the physics are more likely. This prior allows us to quantify model form errors. We connect the system's response to observations through a probabilistic model of the measurement process. The joint posterior over the system responses and all parameters is given by Bayes' rule. To approximate the intractable posterior, we develop a stochastic variational inference algorithm. In summary, the developed methodology offers a powerful framework for Bayesian estimation in dynamical systems.

Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the latents. A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization. For algorithms based on expectation-maximization (EM), the E-step is often intractable without restrictive approximations to the posterior. We propose the use of GFlowNets, algorithms for sampling from an unnormalized density by learning a stochastic policy for sequential construction of samples, for this intractable E-step. By training GFlowNets to sample from the posterior over latents, we take advantage of their strengths as amortized variational inference algorithms for complex distributions over discrete structures. Our approach, GFlowNet-EM, enables the training of expressive LVMs with discrete compositional latents, as shown by experiments on non-context-free grammar induction and on images using discrete variational autoencoders (VAEs) without conditional independence enforced in the encoder.

Intuitively, label-DP presents an easier task for the learner compared to DP since the training features are assumed to be public. Indeed, prior work showed that label-DP learning Label differential privacy (label-DP) is a popular algorithms can achieve much higher test accuracy compared framework for training private ML models on to the best DP counterparts on benchmark datasets. However, datasets with public features and sensitive private such models also attain a high accuracy on the training labels. Despite its rigorous privacy guarantee, it set, which enables an adversary to simply evaluate the model has been observed that in practice label-DP does on the public training features to (correctly) predict the private not preclude label inference attacks (LIAs): Models labels (Busa-Fekete et al., 2021)--a method that we trained with label-DP can be evaluated on the refer to as the simple prediction attack (SPA). The existence public training features to recover, with high accuracy, of such a paradoxical adversary raises the question the very private labels that it was designed of whether label-DP is truly a meaningful privacy notion to to protect. In this work, we argue that this phenomenon strive for.

Message passing on factor graphs is a powerful framework for probabilistic inference, which finds important applications in various scientific domains. The most wide-spread message passing scheme is the sum-product algorithm (SPA) which gives exact results on trees but often fails on graphs with many small cycles. We search for an alternative message passing algorithm that works particularly well on such cyclic graphs. Therefore, we challenge the extrinsic principle of the SPA, which loses its objective on graphs with cycles. We further replace the local SPA message update rule at the factor nodes of the underlying graph with a generic mapping, which is optimized in a data-driven fashion. These modifications lead to a considerable improvement in performance while preserving the simplicity of the SPA. We evaluate our method for two classes of cyclic graphs: the 2x2 fully connected Ising grid and factor graphs for symbol detection on linear communication channels with inter-symbol interference. To enable the method for large graphs as they occur in practical applications, we develop a novel loss function that is inspired by the Bethe approximation from statistical physics and allows for training in an unsupervised fashion.

We study the Inexact Langevin Dynamics (ILD), Inexact Langevin Algorithm (ILA), and Score-based Generative Modeling (SGM) when utilizing estimated score functions for sampling. Our focus lies in establishing stable biased convergence guarantees in terms of the Kullback-Leibler (KL) divergence. To achieve these guarantees, we impose two key assumptions: 1) the target distribution satisfies the log-Sobolev inequality (LSI), and 2) the score estimator exhibits a bounded Moment Generating Function (MGF) error. Notably, the MGF error assumption we adopt is more lenient compared to the $L^\infty$ error assumption used in existing literature. However, it is stronger than the $L^2$ error assumption utilized in recent works, which often leads to unstable bounds. We explore the question of how to obtain a provably accurate score estimator that satisfies the MGF error assumption. Specifically, we demonstrate that a simple estimator based on kernel density estimation fulfills the MGF error assumption for sub-Gaussian target distribution, at the population level.

Measurement error occurs when a set of covariates influencing a response variable are corrupted by noise. This can lead to misleading inference outcomes, particularly in problems where accurately estimating the relationship between covariates and response variables is crucial, such as causal effect estimation. Existing methods for dealing with measurement error often rely on strong assumptions such as knowledge of the error distribution or its variance and availability of replicated measurements of the covariates. We propose a Bayesian Nonparametric Learning framework which is robust to mismeasured covariates, does not require the preceding assumptions, and is able to incorporate prior beliefs about the true error distribution. Our approach gives rise to two methods that are robust to measurement error via different loss functions: one based on the Total Least Squares objective and the other based on Maximum Mean Discrepancy (MMD). The latter allows for generalisation to non-Gaussian distributed errors and non-linear covariate-response relationships. We provide bounds on the generalisation error using the MMD-loss and showcase the effectiveness of the proposed framework versus prior art in real-world mental health and dietary datasets that contain significant measurement errors.

Score matching is an alternative to maximum likelihood (ML) for estimating a probability distribution parametrized up to a constant of proportionality. By fitting the ''score'' of the distribution, it sidesteps the need to compute this constant of proportionality (which is often intractable). While score matching and variants thereof are popular in practice, precise theoretical understanding of the benefits and tradeoffs with maximum likelihood -- both computational and statistical -- are not well understood. In this work, we give the first example of a natural exponential family of distributions such that the score matching loss is computationally efficient to optimize, and has a comparable statistical efficiency to ML, while the ML loss is intractable to optimize using a gradient-based method. The family consists of exponentials of polynomials of fixed degree, and our result can be viewed as a continuous analogue of recent developments in the discrete setting. Precisely, we show: (1) Designing a zeroth-order or first-order oracle for optimizing the maximum likelihood loss is NP-hard. (2) Maximum likelihood has a statistical efficiency polynomial in the ambient dimension and the radius of the parameters of the family. (3) Minimizing the score matching loss is both computationally and statistically efficient, with complexity polynomial in the ambient dimension.

Cooperative multi-agent reinforcement learning (MARL) methods equip a group of autonomous agents with the capability Executing actions in a correlated manner is a common of planning and learning to maximize their joint strategy for human coordination that often utility, or reward signals in the reinforcement learning (RL) leads to better cooperation, which is also potentially literature, which provides a promising paradigm for a range beneficial for cooperative multi-agent reinforcement of real-world applications, such as traffic control (Chu et al., learning (MARL). However, the recent 2019), coordination of multi-robot systems (Corke et al., success of MARL relies heavily on the convenient 2005), and power grid management (Callaway & Hiskens, paradigm of purely decentralized execution, 2010). As a key distinction from the single-agent setting, where there is no action correlation among agents multi-agent joint action spaces grow exponentially with for scalability considerations. In this work, we the number of agents, which imposes significant scalability introduce a Bayesian network to inaugurate correlations issues. As a convenient and commonly adopted solution, between agents' action selections in their most existing cooperative MARL methods only consider joint policy. Theoretically, we establish a theoretical product policies, i.e., each agent selects its local action independently justification for why action dependencies given the state or its observations. Restricting are beneficial by deriving the multi-agent policy to product policies, however, does come at a cost for cooperative gradient formula under such a Bayesian network tasks: consider an example where cars wait at a joint policy and proving its global convergence crossroads, it would be hard for the cars to coordinate their to Nash equilibria under tabular softmax policy movements without knowing others' intentions, potentially parameterization in cooperative Markov games.

Thalassemia is a group of inherited blood disorders that happen when hemoglobin, the protein in red blood cells that carries oxygen, is not made enough. It is found all over the body and is needed for survival. If both parents have thalassemia, a child's chance of getting it increases. Genetic counselling and early diagnosis are essential for treating thalassemia and stopping it from being passed on to future generations. It may be hard for healthcare professionals to differentiate between people with thalassemia carriers and those without. The current blood tests for beta thalassemia carriers are too expensive, take too long, and require too much screening equipment. The World Health Organization says there is a high death rate for people with thalassemia. Therefore, it is essential to find thalassemia carriers to act quickly. High-performance liquid chromatography (HPLC), the standard test method, has problems such as cost, time, and equipment needs. So, there must be a quick and cheap way to find people carrying the thalassemia gene. Using federated learning (FL) techniques, this study shows a new way to find people with the beta-thalassemia gene. FL allows data to be collected and processed on-site while following privacy rules, making it an excellent choice for sensitive health data. Researchers used FL to train a model for beta-thalassemia carriers by looking at the complete blood count results and red blood cell indices. The model was 92.38 % accurate at telling the difference between beta-thalassemia carriers and people who did not have the disease. The proposed FL model is better than other published methods in terms of how well it works, how reliable it is, and how private it is. This research shows a promising, quick, accurate, and low-cost way to find thalassemia carriers and opens the door for screening them on a large scale.