Probabilistic, hierarchically coherent forecasting is a key problem in many practical forecasting applications – the goal is to obtain coherent probabilistic predictions for a large number of time series arranged in a pre-specified tree hierarchy. In this paper, we present an end-to-end deep probabilistic model for hierarchical forecasting that is motivated by a classical top-down strategy. It jointly learns the distribution of the root time series, and the (dirichlet) proportions according to which each parent time-series is split among its children at any point in time. The resulting forecasts are naturally coherent, and provide probabilistic predictions over all time series in the hierarchy. We experiment on several public datasets and demonstrate significant improvements of up to 26% on most datasets compared to state-of-the-art baselines. Finally, we also provide theoretical justification for the superiority of our top-down approach compared to the more traditional bottom-up modeling.

Large pretrained language models generate fluent text but are notoriously hard to controllably sample from.In this work, we study constrained sampling from such language models: generating text that satisfies user-defined constraints, while maintaining fluency and model's performance in a downstream task.We propose MUCOLA-a sampling procedure that combines the log-likelihood of the language model with arbitrary (differentiable) constraints in a single energy function, and then generates samples in a non-autoregressive manner.Specifically, it initializes the entire output sequence with noise and follows a Markov chain defined by Langevin Dynamics using the gradients of the energy function.We evaluate MUCOLA on text generation with soft and hard constraints as well as their combinations obtaining significant improvements over competitive baselines for toxicity avoidance, sentiment control, and keyword-guided generation. 1

Bayesian Optimisation (BO) refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently search for the optimum. While BO has been applied successfully in many applications, modern optimisation tasks usher in new challenges where conventional methods fail spectacularly. In this work, we present Dragonfly, an open source Python library for scalable and robust BO. Dragonfly incorporates multiple recently developed methods that allow BO to be applied in challenging real world settings; these include better methods for handling higher dimensional domains, methods for handling multi-fidelity evaluations when cheap approximations of an expensive function are available, methods for optimising over structured combinatorial spaces, such as the space of neural network architectures, and methods for handling parallel evaluations. Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and additional constraints. We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO. The Dragonfly library is available at dragonfly.github.io.

Multiview assisted learning has gained significant attention in recent years in supervised learning genre. Availability of high-performance computing devices enables learning algorithms to search simultaneously over multiple views or feature spaces to obtain an optimum classification performance. This paper is a pioneering attempt of formulating a mathematical foundation for realizing a multiview aided collaborative boosting architecture for multiclass classification. Most of the present algorithms apply multiview learning heuristically without exploring the fundamental mathematical changes imposed on traditional boosting. Also, most of the algorithms are restricted to two class or view setting. Our proposed mathematical framework enables collaborative boosting across any finite-dimensional view spaces for multiclass learning. The boosting framework is based on a forward stagewise additive model, which minimizes a novel exponential loss function. We show that the exponential loss function essentially captures the difficulty of a training sample space instead of the traditional "1/0" loss. The new algorithm restricts a weak view from overlearning and thereby preventing overfitting. The model is inspired by our earlier attempt on collaborative boosting, which was devoid of mathematical justification. The proposed algorithm is shown to converge much nearer to global minimum in the exponential loss space and thus supersedes our previous algorithm. This paper also presents analytical and numerical analyses of convergence and margin bounds for multiview boosting algorithms and we show that our proposed ensemble learning manifests lower error bound and higher margin compared with our previous model. Also, the proposed model is compared with traditional boosting and recent multiview boosting algorithms. In the majority of instances, the new algorithm manifests a faster rate of convergence on training set error and also simultaneously offers better generalization performance. The kappa-error diagram analysis reveals the robustness of the proposed boosting framework to labeling noise.