Counterexample-driven genetic programming (CDGP) uses specifications provided as formal constraints to generate the training cases used to evaluate evolving programs. It has also been extended to combine formal constraints and user-provided training data to solve symbolic regression problems. Here we show how the ideas underlying CDGP can also be applied using only user-provided training data, without formal specifications. We demonstrate the application of this method, called ``informal CDGP,'' to software synthesis problems. Our results show that informal CDGP finds solutions faster (i.e. with fewer program executions) than standard GP. Additionally, we propose two new variants to informal CDGP, and find that one produces significantly more successful runs on about half of the tested problems. Finally, we study whether the addition of counterexample training cases to the training set is useful by comparing informal CDGP to using a static subsample of the training set, and find that the addition of counterexamples significantly improves performance.

Lexicase selection has been shown to provide advantages over other selection algorithms in several areas of evolutionary computation and machine learning. In its standard form, lexicase selection filters a population or other collection based on randomly ordered training cases that are considered one at a time. This iterated filtering process can be time-consuming, particularly in settings with large numbers of training cases. In this paper, we propose a new method that is nearly equivalent to lexicase selection in terms of the individuals that it selects, but which does so significantly more quickly. The new method, called DALex (for Diversely Aggregated Lexicase), selects the best individual with respect to a weighted sum of training case errors, where the weights are randomly sampled. This allows us to formulate the core computation required for selection as matrix multiplication instead of recursive loops of comparisons, which in turn allows us to take advantage of optimized and parallel algorithms designed for matrix multiplication for speedup. Furthermore, we show that we can interpolate between the behavior of lexicase selection and its "relaxed" variants, such as epsilon or batch lexicase selection, by adjusting a single hyperparameter, named "particularity pressure," which represents the importance granted to each individual training case. Results on program synthesis, deep learning, symbolic regression, and learning classifier systems demonstrate that DALex achieves significant speedups over lexicase selection and its relaxed variants while maintaining almost identical problem-solving performance. Under a fixed computational budget, these savings free up resources that can be directed towards increasing population size or the number of generations, enabling the potential for solving more difficult problems.

Data Science in Context: Foundations, Challenges, Opportunities.

One potential drawback of using aggregated performance measurement in machine learning is that models may learn to accept higher errors on some training cases as compromises for lower errors on others, with the lower errors actually being instances of overfitting. This can lead to both stagnation at local optima and poor generalization. Lexicase selection is an uncompromising method developed in evolutionary computation, which selects models on the basis of sequences of individual training case errors instead of using aggregated metrics such as loss and accuracy. In this paper, we investigate how lexicase selection, in its general form, can be integrated into the context of deep learning to enhance generalization. We propose Gradient Lexicase Selection, an optimization framework that combines gradient descent and lexicase selection in an evolutionary fashion. Our experimental results demonstrate that the proposed method improves the generalization performance of various widely-used deep neural network architectures across three image classification benchmarks. Additionally, qualitative analysis suggests that our method assists networks in learning more diverse representations. Modern data-driven learning algorithms, in general, define an optimization objective, e.g., a fitness function for parent selection in genetic algorithms (Holland, 1992) or a loss function for gradient descent in deep learning (LeCun et al., 2015), which computes the aggregate performance on the training data to guide the optimization process. Taking the image classification problem as an example, most recent approaches use Cross-Entropy loss with gradient descent (Bottou, 2010) and backpropagation (Rumelhart et al., 1985) to train deep neural networks (DNNs) on batches of training images. Despite the success that advanced DNNs can reach human-level performance on the image recognition task (Russakovsky et al., 2015), one potential drawback for such aggregated performance measurement is that the model may learn to seek "compromises" during the learning procedure, e.g., optimizing model weights to intentionally keep some errors in order to gain higher likelihood on correct predictions.

We describe a design principle for adaptive systems under which adaptation is driven by particular challenges that the environment poses, as opposed to average or otherwise aggregated measures of performance over many challenges. We trace the development of this "particularity" approach from the use of lexicase selection in genetic programming to "particularist" approaches to other forms of machine learning and to the design of adaptive systems more generally.

The maximization of diversity of neuronal response properties has been recently suggested as an organizing principle for the formation of such prominent features of the functional architecture of the brain as the corti(cid:173) cal columns and the associated patchy projection patterns (Malach, 1994). We show that (1) maximal diversity is attained when the ratio of dendritic and axonal arbor sizes is equal to one, as found in many cortical areas and across species (Lund et al., 1993; Malach, 1994), and (2) that maxi(cid:173) mization of diversity leads to better performance in systems of receptive fields implementing steerable/shiftable filters, and in matching spatially distributed signals, a problem that arises in many high-level visual tasks. A fundamental feature of cortical architecture is its columnar organization, mani(cid:173) fested in the tendency of neurons with similar properties to be organized in columns that run perpendicular to the cortical surface. This organization of the cortex was ini(cid:173) tially discovered by physiological experiments (Mouncastle, 1957; Hubel and Wiesel, 1962), and subsequently confirmed with the demonstration of histologically defined columns. Tracing experiments have shown that axonal projections throughout the cerebral cortex tend to be organized in vertically aligned clusters or patches.

In genetic programming, an evolutionary method for producing computer programs that solve specified computational problems, parent selection is ordinarily based on aggregate measures of performance across an entire training set. Lexicase selection, by contrast, selects on the basis of performance on random sequences of training cases; this has been shown to enhance problem-solving power in many circumstances. Lexicase selection can also be seen as better reflecting biological evolution, by modeling sequences of challenges that organisms face over their lifetimes. Recent work has demonstrated that the advantages of lexicase selection can be amplified by down-sampling, meaning that only a random subsample of the training cases is used each generation. This can be seen as modeling the fact that individual organisms encounter only subsets of the possible environments, and that environments change over time. Here we provide the most extensive benchmarking of down-sampled lexicase selection to date, showing that its benefits hold up to increased scrutiny. The reasons that down-sampling helps, however, are not yet fully understood. Hypotheses include that down-sampling allows for more generations to be processed with the same budget of program evaluations; that the variation of training data across generations acts as a changing environment, encouraging adaptation; or that it reduces overfitting, leading to more general solutions. We systematically evaluate these hypotheses, finding evidence against all three, and instead draw the conclusion that down-sampled lexicase selection's main benefit stems from the fact that it allows the evolutionary process to examine more individuals within the same computational budget, even though each individual is examined less completely.

The ACM constitution provides that our Association holds a general election in the even-numbered years for the positions of President, Vice President, Secretary/Treasurer, and Members-at-Large. Biographical information and statements of the candidates appear on the following pages (candidates' names appear in random order). In addition to the election of ACM's officers--President, Vice President, Secretary/Treasurer--five Members-at-Large will be elected to serve on ACM Council. Please refer to the instructions posted at https://www.esc-vote.com/acm. To access the secure voting site, you will need to enter your email address (the email address associated with your ACM member record) and your unique PIN provided by Election Services Co. Please return your ballot in the enclosed envelope, which must be signed by you on the outside in the space provided. The signed ballot envelope may be inserted into a separate envelope for mailing if you prefer this method. All ballots must be received by no later than 16:00 UTC on 22 May 2020. Validation by the Tellers Committee will take place at 14:00 UTC on 26 May 2020. Elizabeth Churchill is a Director of User Experience at Google. Her field of study is Human Computer Interaction (HCI) and User Experience (UX), with a current focus on the design of effective designer and developer tools. Churchill has built research groups and led research in a number of well-known companies, including as Director of Human Computer Interaction at eBay Research Labs in San Jose, CA, as a Principal Research Scientist and Research Manager at Yahoo! in Santa Clara, CA, and as a Senior Scientist at the Palo Alto Research Center (PARC) and FXPAL, Fuji Xerox's Research lab in Silicon Valley. Working across a number of research areas, she has over 100 peer reviewed top-tier journal and conference publications in theoretical and applied psychology, cognitive science, human-computer interaction, mobile and ubiquitous computing, computer-mediated communication, and social media, more than 50 patents granted or pending, and 7 academic books. Her team produces research that impacts a large number of Google's products (by shaping Google's Flutter and Material Design), influencing the work of hundreds of thousands of designers and developers globally, and thus affecting the user experience of millions of end-users. She continues to guest lecture at universities and to mentor early stage career professionals and students.

Dietary advice seems to change every decade. Fat is bad, then suddenly it's good again. Nowadays, for many people, carbs are the enemy. But it turns out that healthy dietary guidelines can't be boiled down into simple rules. A new crop of studies, which leverage the latest health testing and machine learning technologies, are finding that there's no single diet that works for everyone.

My tongue is orange!" my 2-year-old daughter shrieked after licking a dollop of clear hand sanitizer. "Mommy, my ear feels orange," she moaned when an earache struck. It's orange," she whined from inside her snowsuit when a scratchy tag in her new white glove rubbed uncomfortably against her wrist. As her vocabulary blossomed, she started to associate colors with scents. "What smells pink?" (Dryer exhaust puffing out of a neighbor's basement vent.) Anyone who has spent time around toddlers knows they say some strange things.