Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past. However, existing methods can fail when directly applied to learn embedding models using supervised training data with a large class space. To achieve user-level DP for large image-to-embedding feature extractors, we propose DP-FedEmb, a variant of federated learning algorithms with per-user sensitivity control and noise addition, to train from user-partitioned data centralized in the datacenter. DP-FedEmb combines virtual clients, partial aggregation, private local fine-tuning, and public Pre-training to achieve strong privacy utility trade-offs. We apply DP-FedEmb to train image embedding models for faces, landmarks and natural species, and demonstrate its superior utility under same privacy budget on benchmark datasets DigiFace. EMNIST, GLD and iNaturalist. We further illustrate it is possible to achieve strong user-level DP guarantees of ∊ < 2 while controlling the utility drop within 5%, when millions of users can participate in training.

Understanding the nutritional content of food from visual data is a challenging computer vision problem, with the potential to have a positive and widespread impact on public health. Studies in this area are limited to existing datasets in the field that lack sufficient diversity or labels required for training models with nutritional understanding capability. We introduce Nutrition5k, a novel dataset of 5k diverse, real world food dishes with corresponding video streams, depth images, component weights, and high accuracy nutritional content annotation. We demonstrate the potential of this dataset by training a computer vision algorithm capable of predicting the caloric and macronutrient values of a complex, real world dish at an accuracy that outperforms professional nutritionists. Further we present a baseline for incorporating depth sensor data to improve nutrition predictions. We release Nutrition5k in the hope that it will accelerate innovation in the space of nutritional understanding. The dataset is available at https://github.com/google-research-datasets/Nutrition5k.

Cooperative coevolutionary algorithms have the potential to significantly speed up the search process by dividing the space into parts that can each be conquered separately. However, recent research presented theoretical and empirical arguments that these algorithms tend to converge to suboptimal solutions in the search space, and are thus not fit for optimization tasks. This paper details an extended formal model for cooperative coevolutionary algorithms, and uses it to explore possible reasons these algorithms converge to optimal or suboptimal solutions. We demonstrate that, under specific conditions, this theoretical model will converge to the globally optimal solution. The proofs provide the underlying theoretical foundation for a better application of cooperative coevolutionary algorithms. We demonstrate the practical advantages of applying ideas from this theoretical work to a simple problem domain.

Archive-based cooperative coevolutionary algorithms attempt to retain a set of individuals which act as good collaborators for other coevolved individuals in the evolutionary system. We introduce a new archive-based algorithm, called iCCEA, which compares favorably with other cooperative coevolutionary algorithms. We explain the current problems with cooperative coevolution which have given rise to archive methods, detail the iCCEA algorithm, compare it against other traditional and archive-based methods on basic problem domains, and discuss the reasons behind the performance of various algorithms.

Genetic programming has highlighted the problem of bloat, the uncontrolled growth of the average size of an individual in the population. The most common approach to dealing with bloat in tree-based genetic programming individuals is to limit their maximal allowed depth. An alternative to depth limiting is to punish individuals in some way based on excess size, and our experiments have shown that the combination of depth limiting with such a punitive method is generally more effective than either alone. Which such combinations are most effective at reducing bloat? In this article we augment depth limiting with nine bloat control methods and compare them with one another. These methods are chosen from past literature and from techniques of our own devising. esting with four genetic programming problems, we identify where each bloat control method performs well on a per-problem basis, and under what settings various methods are effective independent of problem. We report on the results of these tests, and discover an unexpected winner in the cross-platform category.

Cooperative coevolutionary algorithms (CEAs) offer great potential for concurrent multiagent learning domains and are of special utility to domains involving teams of multiple agents. Unfortunately, they also exhibit pathologies resulting from their game-theoretic nature, and these pathologies interfere with finding solutions that correspond to optimal collaborations of interacting agents. We address this problem by biasing a cooperative CEA in such a way that the fitness of an individual is based partly on the result of interactions with other individuals (as is usual), and partly on an estimate of the best possible reward for that individual if partnered with its optimal collaborator. We justify this idea using existing theoretical models of a relevant subclass of CEAs, demonstrate how to apply biasing in a way that is robust with respect to parameterization, and provide some experimental evidence to validate the biasing approach. We show that it is possible to bias coevolutionary methods to better search for optimal multiagent behaviors