Recent studies suggest that the representations learned by large language models (LLMs) are partially aligned to those of the human brain. However, whether this representational alignment arises from a similar sequence of computations remains elusive. In this study, we explore this question by examining temporally-resolved brain signals of participants listening to 10 hours of an audiobook. We study these neural dynamics jointly with a benchmark encompassing 17 LLMs varying in size and architecture type. Our analyses reveal that LLMs and the brain generate representations in a similar order: specifically, activations in the initial layers of LLMs tend to best align with early brain responses, while the deeper layers of LLMs tend to best align with later brain responses. This brain-LLM alignment is consistent across transformers and recurrent architectures. However, its emergence depends on both model size and context length. Overall, the alignment between LLMs and the brain provides novel elements supporting a partial convergence between biological and artificial neural networks.

The growing ubiquity of machine learning (ML) has led it to enter various areas of computer science, including black-box optimization (BBO). Recent research is particularly concerned with Bayesian optimization (BO). BO-based algorithms are popular in the ML community, as they are used for hyperparameter optimization and more generally for algorithm configuration. However, their efficiency decreases as the dimensionality of the problem and the budget of evaluations increase. Meanwhile, derivative-free optimization methods have evolved independently in the optimization community. Therefore, we urge to understand whether cross-fertilization is possible between the two communities, ML and BBO, i.e., whether algorithms that are heavily used in ML also work well in BBO and vice versa. Comparative experiments often involve rather small benchmarks and show visible problems in the experimental setup, such as poor initialization of baselines, overfitting due to problem-specific setting of hyperparameters, and low statistical significance. With this paper, we update and extend a comparative study presented by Hutter et al. in 2013. We compare BBO tools for ML with more classical heuristics, first on the well-known BBOB benchmark suite from the COCO environment and then on Direct Policy Search for OpenAI Gym, a reinforcement learning benchmark. Our results confirm that BO-based optimizers perform well on both benchmarks when budgets are limited, albeit with a higher computational cost, while they are often outperformed by algorithms from other families when the evaluation budget becomes larger. We also show that some algorithms from the BBO community perform surprisingly well on ML tasks.

Existing studies in black-box optimization suffer from low generalizability, caused by a typically selective choice of problem instances used for training and testing of different optimization algorithms. Among other issues, this practice promotes overfitting and poor-performing user guidelines. We address this shortcoming by introducing in this work a general-purpose algorithm selection wizard that was designed and tested on a previously unseen breadth of black-box optimization problems, ranging from academic benchmarks to real-world applications, from discrete over numerical to mixed-integer problems, from small to very large-scale problems, from noisy over dynamic to static problems, etc. Not only did we use the already very extensive benchmark environment available in Nevergrad, but we also extended it significantly by adding a number of additional benchmark suites, including Pyomo, Photonics, large-scale global optimization (LSGO), and MuJoCo. Our wizard achieves competitive performance on all benchmark suites. It significantly outperforms previous state-of-the-art algorithms on some of the suites, including YABBOB and LSGO. Its excellent performance is obtained without any task-specific parametrization. The algorithm selection wizard, all of its base solvers, as well as the benchmark suites are available for reproducible research in the open-source Nevergrad platform.

The task of image generation started receiving some attention from artists and designers, providing inspiration for new creations. However, exploiting the results of deep generative models such as Generative Adversarial Networks can be long and tedious given the lack of existing tools. In this work, we propose a simple strategy to inspire creators with new generations learned from a dataset of their choice, while providing some control over the output. We design a simple optimization method to find the optimal latent parameters corresponding to the closest generation to any input inspirational image. Specifically, we allow the generation given an inspirational image of the user's choosing by performing several optimization steps to recover optimal parameters from the model's latent space. We tested several exploration methods from classical gradient descents to gradient-free optimizers. Many gradient-free optimizers just need comparisons (better/worse than another image), so they can even be used without numerical criterion nor inspirational image, only with human preferences. Thus, by iterating on one's preferences we can make robust facial composite or fashion generation algorithms. Our results on four datasets of faces, fashion images, and textures show that satisfactory images are effectively retrieved in most cases.

Choosing automatically the right algorithm using problem descriptors is a classical component of combinatorial optimization. It is also a good tool for making evolutionary algorithms fast, robust and versatile. We present Shiwa, an algorithm good at both discrete and continuous, noisy and noise-free, sequential and parallel, black-box optimization. Our algorithm is experimentally compared to competitors on YABBOB, a BBOB comparable testbed, and on some variants of it, and then validated on several real world testbeds.

Space-filling designs such as Low Discrepancy Sequence (LDS), Latin Hypercube Sampling (LHS) and Jittered Sampling (JS) were proposed for fully parallel hyperparameter search, and were shown to be more effective than random and grid search. We prove that LHS and JS outperform random search only by a constant factor. Consequently, we introduce a new sampling approach based on the reshaping of the search distribution, and we show both theoretically and numerically that it leads to significant gains over random search. Two methods are proposed for the reshaping: Recentering (when the distribution of the optimum is known), and Cauchy transformation (when the distribution of the optimum is unknown). The proposed methods are first validated on artificial experiments and simple real-world tests on clustering and Salmon mappings. Then we demonstrate that they drive performance improvement in a wide range of expensive artificial intelligence tasks, namely attend/infer/repeat, video next frame segmentation forecasting and progressive generative adversarial networks.

Resampling methods, based on averaging the fitness of several clones, are the classical solution for dealing with noise. Population control has been proposed as a different tool for faster convergence of evolution strategies when the variance does not vanish around the optimum. However, we show that convergence may not hold even in the case of centered noise and construct a counterexample with variance dissymmetry, i.e. more variance on one side of the optimum than on the other. We propose a fix termed consistent population control and formally derive uniform constraints on deviations between averages and expectations within the proposed algorithm under either subgaussianity or finite variance assumptions on measurement noise. We prove convergence guarantees of consistent population control, verify it experimentally and show the effectiveness of population control in direct policy search, either with our fix or, in overparameterized cases, without our fix.

Blind source separation is a widely used technique to analyze multichannel data. In many real-world applications, its results can be significantly hampered by the presence of unknown outliers. In this paper, a novel algorithm coined rGMCA (robust Generalized Morphological Component Analysis) is introduced to retrieve sparse sources in the presence of outliers. It explicitly estimates the sources, the mixing matrix, and the outliers. It also takes advantage of the estimation of the outliers to further implement a weighting scheme, which provides a highly robust separation procedure. Numerical experiments demonstrate the efficiency of rGMCA to estimate the mixing matrix in comparison with standard BSS techniques.

Blind source separation (BSS) is a very popular technique to analyze data which can be modeled as linear mixtures of elementary sources. Standard approaches generally make the assumption that such sources are statistically independent or at least uncorrelated. However, this is barely the case for real-world sources which are very often partially correlated. We present a new sparsity-enforcing BSS method coined Adaptive Morphological Component Analysis (AMCA) designed to retrieve sparse and partially correlated sources based on an adaptive weighting scheme. Numerical experiments have been carried out which show that the proposed method is robust to the partial correlation of the sources while standard BSS techniques fail. The performances of the proposed algorithm are further illustrated with simulations in the context of astrophysics.

Nonnegative blind source separation, which is also referred to as nonnegative matrix factorization (NMF), is a very active field in domains as different as astrophysics, audio processing, and biomedical signal processing. In this context, the efficient retrieval of the sources requires the use of signal priors such as sparsity. Although NMF has been well studied with sparse constraints in the direct domain, only very few algorithms can encompass nonnegativity together with sparsity in a transformed domain since simultaneously dealing with two priors in two different domains is challenging. In this paper, we show how a sparse NMF algorithm called nonnegative generalized morphological component analysis (nGMCA) can be extended to impose nonnegativity in the direct domain along with sparsity in a transformed domain, with both analysis and synthesis formulations. To the best of our knowledge, this work presents the first comparison of analysis and synthesis priors---as well as their reweighted versions---in the context of blind source separation. Comparisons with state-of-the-art NMF algorithms on realistic data show the efficiency as well as the robustness of the proposed algorithms.