We consider the problem of designing minimax estimators for estimating the parameters of a probability distribution. Unlike classical approaches such as the MLE and minimum distance estimators, we consider an algorithmic approach for constructing such estimators. We view the problem of designing minimax estimators as finding a mixed strategy Nash equilibrium of a zero-sum game. By leveraging recent results in online learning with non-convex losses, we provide a general algorithm for finding a mixed-strategy Nash equilibrium of general non-convex non-concave zero-sum games. Our algorithm requires access to two subroutines: (a) one which outputs a Bayes estimator corresponding to a given prior probability distribution, and (b) one which computes the worst-case risk of any given estimator. Given access to these two subroutines, we show that our algorithm outputs both a minimax estimator and a least favorable prior. To demonstrate the power of this approach, we use it to construct provably minimax estimators for classical problems such as estimation in the finite Gaussian sequence model, and linear regression.

Estimating parameters of mixture model has wide applications Determining the number of components in a finite mixture model ranging from classification problems to estimating of complex distributions. is crucial in many application areas such as financial data [16, 31, 35], Most of the current literature on estimating the parameters biomedical studies [17, 36] and low-frequency accident occurrence of the mixture densities are based on iterative Expectation Maximization prediction [27, 32]. Existing literature have witnessed numerous (EM) type algorithms which require the use of either computational methods, and in particular Markov Chain Monte taking expectations over the latent label variables or generating Carlo methods [7, 14, 33] and EM algorithms [20-22] have been samples from the conditional distribution of such latent labels using used with a lot of success. However, either these methods are computationally the Bayes rule. Moreover, when the number of components is demanding and/or these methods are developed under unknown, the problem becomes computationally more demanding the assumption of data being generated from mixtures of densities due to well-known label switching issues [28]. In this paper, we from the exponential family, in part because the family of exponential propose a robust and quick approach based on change-point methods distribution has a sufficient statistic of constant dimension (i.e., to determine the number of mixture components that works the dimension of the sufficient statistic remains fixed for any sample for almost any location-scale families even when the components size) and so the updates of the data augmentation type algorithm are heavy tailed (e.g., Cauchy). We present several numerical illustrations involve their smaller dimensional sufficient statistics [11, 12, 24].

Matrix square roots and their inverses arise frequently in machine learning, e.g., when sampling from high-dimensional Gaussians $\mathcal{N}(\mathbf 0, \mathbf K)$ or whitening a vector $\mathbf b$ against covariance matrix $\mathbf K$. While existing methods typically require $O(N^3)$ computation, we introduce a highly-efficient quadratic-time algorithm for computing $\mathbf K^{1/2} \mathbf b$, $\mathbf K^{-1/2} \mathbf b$, and their derivatives through matrix-vector multiplication (MVMs). Our method combines Krylov subspace methods with a rational approximation and typically achieves $4$ decimal places of accuracy with fewer than $100$ MVMs. Moreover, the backward pass requires little additional computation. We demonstrate our method's applicability on matrices as large as $50,\!000 \times 50,\!000$ - well beyond traditional methods - with little approximation error. Applying this increased scalability to variational Gaussian processes, Bayesian optimization, and Gibbs sampling results in more powerful models with higher accuracy.

Value function approximation has demonstrated phenomenal empirical success in reinforcement learning (RL). Nevertheless, despite a handful of recent progress on developing theory for RL with linear function approximation, the understanding of general function approximation schemes largely remains missing. In this paper, we establish a provably efficient RL algorithm with general value function approximation. We show that if the value functions admit an approximation with a function class $\mathcal{F}$, our algorithm achieves a regret bound of $\widetilde{O}(\mathrm{poly}(dH)\sqrt{T})$ where $d$ is a complexity measure of $\mathcal{F}$ that depends on the eluder dimension [Russo and Van Roy, 2013] and log-covering numbers, $H$ is the planning horizon, and $T$ is the number interactions with the environment. Our theory generalizes recent progress on RL with linear value function approximation and does not make explicit assumptions on the model of the environment. Moreover, our algorithm is model-free and provides a framework to justify the effectiveness of algorithms used in practice.

Reward-free reinforcement learning (RL) is a framework which is suitable for both the batch RL setting and the setting where there are many reward functions of interest. During the exploration phase, an agent collects samples without using a pre-specified reward function. After the exploration phase, a reward function is given, and the agent uses samples collected during the exploration phase to compute a near-optimal policy. Jin et al. [2020] showed that in the tabular setting, the agent only needs to collect polynomial number of samples (in terms of the number states, the number of actions, and the planning horizon) for reward-free RL. However, in practice, the number of states and actions can be large, and thus function approximation schemes are required for generalization. In this work, we give both positive and negative results for reward-free RL with linear function approximation. We give an algorithm for reward-free RL in the linear Markov decision process setting where both the transition and the reward admit linear representations. The sample complexity of our algorithm is polynomial in the feature dimension and the planning horizon, and is completely independent of the number of states and actions. We further give an exponential lower bound for reward-free RL in the setting where only the optimal $Q$-function admits a linear representation. Our results imply several interesting exponential separations on the sample complexity of reward-free RL.

Neural Computing & Applications is an international journal which publishes original research and other information in the field of practical applications of neural computing and related techniques such as genetic algorithms, fuzzy logic and neuro-fuzzy systems. Featured contributions fall into several categories: Original Articles, Review Articles, Book Reviews, and Announcements. The Original Articles will be high-quality contributions, representing new and significant research, developments or applications of practical use and value. They will be reviewed by at least two referees. For all queries relating to papers after submission, please contact the Journal Editorial Office via "contact us" at Editorial Manager.

In the Logistic Regression for Machine Learning using Python blog, I have introduced the basic idea of the logistic function. We have discussed the cost function. And in the iterative method, we focus on the Gradient descent optimization method. Now so in this section, we are going to introduce the Maximum Likelihood cost function. And we would like to maximize this cost function.

Dependability assurance of systems embedding machine learning(ML) components---so called learning-enabled systems (LESs)---is a key step for their use in safety-critical applications. In emerging standardization and guidance efforts, there is a growing consensus in the value of using assurance cases for that purpose. This paper develops a quantitative notion of assurance that an LES is dependable, as a core component of its assurance case, also extending our prior work that applied to ML components. Specifically, we characterize LES assurance in the form of assurance measures: a probabilistic quantification of confidence that an LES possesses system-level properties associated with functional capabilities and dependability attributes. We illustrate the utility of assurance measures by application to a real world autonomous aviation system, also describing their role both in i) guiding high-level, runtime risk mitigation decisions and ii) as a core component of the associated dynamic assurance case.

We study probabilistic safety for Bayesian Neural Networks (BNNs) under adversarial input perturbations. Given a compact set of input points, $T \subseteq \mathbb{R}^m$, we study the probability w.r.t. the BNN posterior that all the points in $T$ are mapped to the same region $S$ in the output space. In particular, this can be used to evaluate the probability that a network sampled from the BNN is vulnerable to adversarial attacks. We rely on relaxation techniques from non-convex optimization to develop a method for computing a lower bound on probabilistic safety for BNNs, deriving explicit procedures for the case of interval and linear function propagation techniques. We apply our methods to BNNs trained on a regression task, airborne collision avoidance, and MNIST, empirically showing that our approach allows one to certify probabilistic safety of BNNs with millions of parameters.

For instance, Tucker (Tucker, Tensor decomposition methods have recently 1966) and canonical polyadic (CP) (Caroll & Chang, 1970) proven to be efficient for compressing and accelerating tensor decompositions are widely known for compressing neural networks. However, the problem and accelerating convolutional networks (Lebedev of optimal decomposition structure determination et al., 2015; Kim et al., 2016; Kossaifi et al., 2019), and is still not well studied while being quite important. Tensor Train (TT) (Oseledets, 2011) decomposition has Specifically, decomposition ranks present been successfully applied for compressing fully-connected the crucial parameter controlling the compressionaccuracy (FC) (Novikov et al., 2015), convolutional (Garipov et al., tradeoff. In this paper, we introduce 2016), recurrent (Yang et al., 2017; Yu et al., 2017), embedding MARS -- a new efficient method for the automatic (Khrulkov et al., 2019) layers.