Explicit deep generative models (DGMs), e.g., VAEs and Normalizing Flows, have shown to offer an effective data modelling alternative for lossless compression. However, DGMs themselves normally require large storage space and thus contaminate the advantage brought by accurate data density estimation. To eliminate the requirement of saving separate models for different target datasets, we propose a novel setting that starts from a pretrained deep generative model and compresses the data batches while adapting the model with a dynamical system for only one epoch. We formalise this setting as that of One-Shot Online Adaptation (OSOA) of DGMs for lossless compression and propose a vanilla algorithm under this setting. Experimental results show that vanilla OSOA can save significant time versus training bespoke models and space versus using one model for all targets. With the same adaptation step number or adaptation time, it is shown vanilla OSOA can exhibit better space efficiency, e.g., $47\%$ less space, than fine-tuning the pretrained model and saving the fine-tuned model. Moreover, we showcase the potential of OSOA and motivate more sophisticated OSOA algorithms by showing further space or time efficiency with multiple updates per batch and early stopping.

Researchers have successfully developed an AI system capable of completing mathematics problems at a grade school level, a new report asserts. Traditionally, while AI models are proficient at manipulating language to formulate sentences, the multi-step reasoning required to solve math problems has been a step too far. However, researchers at OpenAI (the company behind language model GPT-3) say they have trained a model to recognize its own mistakes, which means it can repeatedly reassess until it discovers a workable solution. In testing, the AI system was able to solve almost as many problems as a sample of children between the ages of nine and twelve. The children scored 60% on a test drawn down from the OpenAI database, while the AI system scored 55%.

OpenAI, the "capped" for-profit company founded by Elon Musk, is continuing to improve its GPT-3 language model and is developing a tool for summarising books or texts. It's a development that could benefit businesses in particular. It has now become possible to create summaries for entire books with artificial intelligence. While the field already counts some specialised companies such as Primer plus some trial work in the area from the likes of Facebook and Google, OpenAI is now positioning itself in the sector. The association has developed an AI model capable of summarising books, or more simply texts, documentation and even studies. In fact, the model summarizes small sections of a text and then adds them together before creating a more refined and precise summary.

For several years, there has been a lot of discussion around AI's capabilities. Many believe that AI will outperform humans in solving certain areas. As the innovation is in its outset, scientists are anticipating human-like independent frameworks in the following coming years. OpenAI has a main position in the computerized reasoning exploration space. Established in December 2015, the organization will probably progress advanced knowledge in a manner that can help mankind in general. Since its exploration is liberated from monetary commitments, OpenAI can all the more likely spotlight on a positive human effect.

The open-source software developer GitHub says as much as 30% of newly written code on its network is being done with the help of the company's AI programming tool Copilot. Why it matters: Copilot can look at code written by a human programmer and suggest further lines or alternative code, eliminating some of the repetitive labor that goes into coding. How it works: Copilot is built on the OpenAI Codex algorithm, which was trained on terabytes of openly available source code and can translate human language into programming language. It serves as a more sophisticated autocomplete tool for programmers.

We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. We describe a novel tool, Cross-Barcode(P,Q), that, given a pair of distributions in a high-dimensional space, tracks multiscale topology spacial discrepancies between manifolds on which the distributions are concentrated. Based on the Cross-Barcode, we introduce the Manifold Topology Divergence score (MTop-Divergence) and apply it to assess the performance of deep generative models in various domains: images, 3D-shapes, time-series, and on different datasets: MNIST, Fashion MNIST, SVHN, CIFAR10, FFHQ, chest X-ray images, market stock data, ShapeNet. We demonstrate that the MTop-Divergence accurately detects various degrees of mode-dropping, intra-mode collapse, mode invention, and image disturbance. Our algorithm scales well (essentially linearly) with the increase of the dimension of the ambient high-dimensional space. It is one of the first TDA-based practical methodologies that can be applied universally to datasets of different sizes and dimensions, including the ones on which the most recent GANs in the visual domain are trained. The proposed method is domain agnostic and does not rely on pre-trained networks.

Quantifying the pathogenicity of protein variants in human disease-related genes would have a marked effect on clinical decisions, yet the overwhelming majority (over 98%) of these variants still have unknown consequences1–3. In principle, computational methods could support the large-scale interpretation of genetic variants. However, state-of-the-art methods4–10 have relied on training machine learning models on known disease labels. As these labels are sparse, biased and of variable quality, the resulting models have been considered insufficiently reliable11. Here we propose an approach that leverages deep generative models to predict variant pathogenicity without relying on labels. By modelling the distribution of sequence variation across organisms, we implicitly capture constraints on the protein sequences that maintain fitness. Our model EVE (evolutionary model of variant effect) not only outperforms computational approaches that rely on labelled data but also performs on par with, if not better than, predictions from high-throughput experiments, which are increasingly used as evidence for variant classification12–16. We predict the pathogenicity of more than 36 million variants across 3,219 disease genes and provide evidence for the classification of more than 256,000 variants of unknown significance. Our work suggests that models of evolutionary information can provide valuable independent evidence for variant interpretation that will be widely useful in research and clinical settings. A new computational method, EVE, classifies human genetic variants in disease genes using deep generative models trained solely on evolutionary sequences.

Real-world datasets often have missing values associated with complex generative processes, where the cause of the missingness may not be fully observed. This is known as missing not at random (MNAR) data. However, many imputation methods do not take into account the missingness mechanism, resulting in biased imputation values when MNAR data is present. Although there are a few methods that have considered the MNAR scenario, their model's identifiability under MNAR is generally not guaranteed. That is, model parameters can not be uniquely determined even with infinite data samples, hence the imputation results given by such models can still be biased. This issue is especially overlooked by many modern deep generative models. In this work, we fill in this gap by systematically analyzing the identifiability of generative models under MNAR. Furthermore, we propose a practical deep generative model which can provide identifiability guarantees under mild assumptions, for a wide range of MNAR mechanisms. Our method demonstrates a clear advantage for tasks on both synthetic data and multiple real-world scenarios with MNAR data.

Can visual artworks created using generative visual algorithms inspire human creativity in storytelling? We asked writers to write creative stories from a starting prompt, and provided them with visuals created by generative AI models from the same prompt. Compared to a control group, writers who used the visuals as story writing aid wrote significantly more creative, original, complete and visualizable stories, and found the task more fun. Of the generative algorithms used (BigGAN, VQGAN, DALL-E, CLIPDraw), VQGAN was the most preferred. The control group that did not view the visuals did significantly better in integrating the starting prompts. Findings indicate that cross modality inputs by AI can benefit divergent aspects of creativity in human-AI co-creation, but hinders convergent thinking.

Model-free Reinforcement Learning (RL) requires the ability to sample trajectories by taking actions in the original problem environment or a simulated version of it. Breakthroughs in the field of RL have been largely facilitated by the development of dedicated open source simulators with easy to use frameworks such as OpenAI Gym and its Atari environments. In this paper we propose to use the OpenAI Gym framework on discrete event time based Discrete Event Multi-Agent Simulation (DEMAS). We introduce a general technique to wrap a DEMAS simulator into the Gym framework. We expose the technique in detail and implement it using the simulator ABIDES as a base. We apply this work by specifically using the markets extension of ABIDES, ABIDES-Markets, and develop two benchmark financial markets OpenAI Gym environments for training daily investor and execution agents. As a result, these two environments describe classic financial problems with a complex interactive market behavior response to the experimental agent's action.