Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices. However, identifying the utility function specifications that best model and explain the observed choices can be a very challenging and time-consuming task. This paper seeks to help modellers by leveraging the Bayesian framework and the concept of automatic relevance determination (ARD), in order to automatically determine an optimal utility function specification from an exponentially large set of possible specifications in a purely data-driven manner. Based on recent advances in approximate Bayesian inference, a doubly stochastic variational inference is developed, which allows the proposed DCM-ARD model to scale to very large and high-dimensional datasets. Using semi-artificial choice data, the proposed approach is shown to very accurately recover the true utility function specifications that govern the observed choices. Moreover, when applied to real choice data, DCM-ARD is shown to be able discover high quality specifications that can outperform previous ones from the literature according to multiple criteria, thereby demonstrating its practical applicability.

There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression. In this setting, a neural data structure is instantiated by training a network over many epochs of its inputs until convergence. In applications where inputs arrive at high throughput, or are ephemeral, training a network from scratch is not practical. This motivates the need for few-shot neural data structures. In this paper we explore the learning of approximate set membership over a set of data in one-shot via meta-learning. We propose a novel memory architecture, the Neural Bloom Filter, which is able to achieve significant compression gains over classical Bloom Filters and existing memory-augmented neural networks.

The ability to extract sequences of game events for high-resolution e-sport games has traditionally required access to the game's engine. This serves as a barrier to groups who don't possess this access. It is possible to apply deep learning to derive these logs from gameplay video, but it requires computational power that serves as an additional barrier. These groups would benefit from access to these logs, such as small e-sport tournament organizers who could better visualize gameplay to inform both audience and commentators. In this paper we present a combined solution to reduce the required computational resources and time to apply a convolutional neural network (CNN) to extract events from e-sport gameplay videos. This solution consists of techniques to train a CNN faster and methods to execute predictions more quickly. This expands the types of machines capable of training and running these models, which in turn extends access to extracting game logs with this approach. We evaluate the approaches in the domain of DOTA2, one of the most popular e-sports. Our results demonstrate our approach outperforms standard backpropagation baselines.

A number of applications (e.g., AI bot tournaments, sports, peer grading, crowdsourcing) use pairwise comparison data and the Bradley-Terry-Luce (BTL) model to evaluate a given collection of items (e.g., bots, teams, students, search results). Past work has shown that under the BTL model, the widely-used maximum-likelihood estimator (MLE) is minimax-optimal in estimating the item parameters, in terms of the mean squared error. However, another important desideratum for designing estimators is fairness. In this work, we consider fairness modeled by the notion of bias in statistics. We show that the MLE incurs a suboptimal rate in terms of bias. We then propose a simple modification to the MLE, which "stretches" the bounding box of the maximum-likelihood optimizer by a small constant factor from the underlying ground truth domain. We show that this simple modification leads to an improved rate in bias, while maintaining minimax-optimality in the mean squared error. In this manner, our proposed class of estimators provably improves fairness represented by bias without loss in accuracy.

Likelihood-free methods refer to procedures that perform likelihood-based statistical inference, but without direct evaluation of the likelihood function. This is attractive when the likelihood function is computationally prohibitive to evaluate due to dataset size or model complexity, or when the likelihood function is only known through a data generation process. Some classes of likelihood-free methods include pseudo-marginal methods (Beaumont 2003; Andrieu and Roberts 2009), indirect inference (Gourieroux et al. 1993) and approximate Bayesian computation (Sisson et al. 2018a). In particular, approximate Bayesian computation (ABC) methods form an approximation to the computationally intractable posterior distribution by firstly sampling parameter vectors from the prior, and conditional on these, generating synthetic datasets under the model. The parameter vectors are then weighted by how well a vector of summary statistics of the synthetic datasets matches the same summary statistics of the observed data. ABC methods have seen extensive application and development over the past 15 years.

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable to real robotics setups. In this paper, we propose a formulation for exploration inspired by the work in active learning literature. Specifically, we train an ensemble of dynamics models and incentivize the agent to explore such that the disagreement of those ensembles is maximized. This allows the agent to learn skills by exploring in a self-supervised manner without any external reward. Notably, we further leverage the disagreement objective to optimize the agent's policy in a differentiable manner, without using reinforcement learning, which results in a sample-efficient exploration. We demonstrate the efficacy of this formulation across a variety of benchmark environments including stochastic-Atari, Mujoco and Unity. Finally, we implement our differentiable exploration on a real robot which learns to interact with objects completely from scratch. Project videos and code are at https://pathak22.github.io/exploration-by-disagreement/

The medoid of a set of $n$ points is the point in the set that minimizes the sum of distances to other points. Computing the medoid can be solved exactly in $O(n^2)$ time by computing the distances between all pairs of points. Previous work shows that one can significantly reduce the number of distance computations needed by adaptively querying distances. The resulting randomized algorithm is obtained by a direct conversion of the computation problem to a multi-armed bandit statistical inference problem. In this work, we show that we can better exploit the structure of the underlying computation problem by modifying the traditional bandit sampling strategy and using it in conjunction with a suitably chosen multi-armed bandit algorithm. Four to five orders of magnitude gains over exact computation are obtained on real data, in terms of both number of distance computations needed and wall clock time. Theoretical results are obtained to quantify such gains in terms of data parameters. Our code is publicly available online at https://github.com/NEURIPS-anonymous-2019/Correlated-Sequential-Halving.

Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the source, and (b) aligning the source and target domains. Traditionally, these tasks have either been considered as separate, or assumed to be implicitly addressed together with high-capacity feature extractors. In this paper, we advance a third broad approach; which we term SALT. The core idea is to consider alignment as an auxiliary task to the primary task of maximizing performance on the source. The auxiliary task is made rather simple by assuming a tractable data geometry in the form of subspaces. We synergistically allow certain parameters derived from the closed-form auxiliary solution, to be affected by gradients from the primary task. The proposed approach represents a unique fusion of geometric and model-based alignment with gradient-flows from a data-driven primary task. SALT is simple, rooted in theory, and outperforms state-of-the-art on multiple standard benchmarks.

To save manual effort, developers often translate programs from one programming language to another, instead of implementing it from scratch. Translating application program interfaces (APIs) used in one language to functionally equivalent ones available in another language is an important aspect of program translation. Existing approaches facilitate the translation by automatically identifying the API mappings across programming languages. However, all these approaches still require large amount of manual effort in preparing parallel program corpora, ranging from pairs of APIs, to manually identified code in different languages that are considered as functionally equivalent. To minimize the manual effort in identifying parallel program corpora and API mappings, this paper aims at an automated approach to map APIs across languages with much less knowledge a priori needed than other existing approaches. The approach is based on an realization of the notion of domain adaption combined with code embedding, which can better align two vector spaces: taking as input large sets of programs, our approach first generates numeric vector representations of the programs, especially the APIs used in each language, and it adapts generative adversarial networks (GAN) to align the vectors from the spaces of two languages. For a better alignment, we initialize the GAN with parameters derived from optional API mapping seeds that can be identified accurately with a simple automatic signature-based matching heuristic. Then the cross-language API mappings can be identified via nearest-neighbors queries in the aligned vector spaces.