One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate Representations (IRs) for extracting features from source code. Most such works target specific tasks, or are designed with a pre-defined set of heuristics. So far, pre-trained models are rare in this domain, but the possibilities have been widely discussed. Especially approaches mimicking large-language models (LLMs) have been proposed. But these have prohibitively large training costs. In this paper, we propose MIREncoder, a M}ulti-modal IR-based Auto-Encoder that can be pre-trained to generate a learned embedding space to be used for downstream tasks by machine learning-based approaches. A multi-modal approach enables us to better extract features from compilable programs. It allows us to better model code syntax, semantics and structure. For code-based performance optimizations, these features are very important while making optimization decisions. A pre-trained model/embedding implicitly enables the usage of transfer learning, and helps move away from task-specific trained models. Additionally, a pre-trained model used for downstream performance optimization should itself have reduced overhead, and be easily usable. These considerations have led us to propose a modeling approach that i) understands code semantics and structure, ii) enables use of transfer learning, and iii) is small and simple enough to be easily re-purposed or reused even with low resource availability. Our evaluations will show that our proposed approach can outperform the state of the art while reducing overhead.

Multimodal Retrieval Augmented Generation (MMRAG) is a powerful approach to questionanswering over multimodal documents. A key challenge with evaluating MMRAG is the paucity of high-quality datasets matching the question styles and modalities of interest. In light of this, we propose SMMQG, a synthetic data generation framework. SMMQG leverages interplay between a retriever, large language model (LLM) and large multimodal model (LMM) to generate question and answer pairs directly from multimodal documents, with the questions conforming to specified styles and modalities. We use SMMQG to generate an MMRAG dataset of 1024 questions Figure 1: An overview of SMMQG. Given userprovided over Wikipedia documents and evaluate stateof-the-art question style and modality requirements, SMmodels using it, revealing insights MQG selects question sources and produces questions into model performance that are attainable only and answers. The questions are grounded in the selected through style-and modality-specific evaluation question sources, and adhere to the question and modality data. Next, we measure the quality of data produced requirements.

Gaussian Processes have become an indispensable part of the spatial statistician's toolbox but are unsuitable for analyzing large dataset because of the significant time and memory needed to fit the associated model exactly. Vecchia Approximation is widely used to reduce the computational complexity and can be calculated with embarrassingly parallel algorithms. While multi-core software has been developed for Vecchia Approximation, such as the GpGp R package, software designed to run on graphics processing units (GPU) is lacking, despite the tremendous success GPUs have had in statistics and machine learning. We compare three different ways to implement Vecchia Approximation on a GPU: two of which are similar to methods used for other Gaussian Process approximations and one that is new. The impact of memory type on performance is investigated and the final method is optimized accordingly. We show that our new method outperforms the other two and then present it in the GpGpU R package. We compare GpGpU to existing multi-core and GPU-accelerated software by fitting Gaussian Process models on various datasets, including a large spatial-temporal dataset of $n>10^6$ points collected from an earth-observing satellite. Our results show that GpGpU achieves faster runtimes and better predictive accuracy.

In distributed machine learning, efficient training across multiple agents with different data distributions poses significant challenges. Even with a centralized coordinator, current algorithms that achieve optimal communication complexity typically require either large minibatches or compromise on gradient complexity. In this work, we tackle both centralized and decentralized settings across strongly convex, convex, and nonconvex objectives. We first demonstrate that a basic primal-dual method, (Accelerated) Gradient Ascent Multiple Stochastic Gradient Descent (GA-MSGD), applied to the Lagrangian of distributed optimization inherently incorporates local updates, because the inner loops of running Stochastic Gradient Descent on the primal variable require no inter-agent communication. Notably, for strongly convex objectives, we show (Accelerated) GA-MSGD achieves linear convergence in communication rounds despite the Lagrangian being only linear in the dual variables. This is due to a unique structural property where the dual variable is confined to the span of the coupling matrix, rendering the dual problem strongly concave. When integrated with the Catalyst framework, our approach achieves nearly optimal communication complexity across various settings without the need for minibatches. Moreover, in stochastic decentralized problems, it attains communication complexities comparable to those in deterministic settings, improving over existing algorithms.

In this paper, we demonstrate a surprising capability of large language models (LLMs): given only input feature names and a description of a prediction task, they are capable of selecting the most predictive features, with performance rivaling the standard tools of data science. Remarkably, these models exhibit this capacity across various query mechanisms. For example, we zero-shot prompt an LLM to output a numerical importance score for a feature (e.g., "blood pressure") in predicting an outcome of interest (e.g., "heart failure"), with no additional context. In particular, we find that the latest models, such as GPT-4, can consistently identify the most predictive features regardless of the query mechanism and across various prompting strategies. We illustrate these findings through extensive experiments on real-world data, where we show that LLM-based feature selection consistently achieves strong performance competitive with data-driven methods such as the LASSO, despite never having looked at the downstream training data. Our findings suggest that LLMs may be useful not only for selecting the best features for training but also for deciding which features to collect in the first place. This could potentially benefit practitioners in domains like healthcare, where collecting high-quality data comes at a high cost.

Landmark universal function approximation results for neural networks with trained weights and biases provided impetus for the ubiquitous use of neural networks as learning models in Artificial Intelligence (AI) and neuroscience. Recent work has pushed the bounds of universal approximation by showing that arbitrary functions can similarly be learned by tuning smaller subsets of parameters, for example the output weights, within randomly initialized networks. Motivated by the fact that biases can be interpreted as biologically plausible mechanisms for adjusting unit outputs in neural networks, such as tonic inputs or activation thresholds, we investigate the expressivity of neural networks with random weights where only biases are optimized. We provide theoretical and numerical evidence demonstrating that feedforward neural networks with fixed random weights can be trained to perform multiple tasks by learning biases only. We further show that an equivalent result holds for recurrent neural networks predicting dynamical system trajectories. Our results are relevant to neuroscience, where they demonstrate the potential for behaviourally relevant changes in dynamics without modifying synaptic weights, as well as for AI, where they shed light on multi-task methods such as bias fine-tuning and unit masking.

Accurate precipitation forecasts have a high socio-economic value due to their role in decision-making in various fields such as transport networks and farming. We propose a global statistical postprocessing method for grid-based precipitation ensemble forecasts. This U-Net-based distributional regression method predicts marginal distributions in the form of parametric distributions inferred by scoring rule minimization. Distributional regression U-Nets are compared to state-of-the-art postprocessing methods for daily 21-h forecasts of 3-h accumulated precipitation over the South of France. Training data comes from the M\'et\'eo-France weather model AROME-EPS and spans 3 years. A practical challenge appears when consistent data or reforecasts are not available. Distributional regression U-Nets compete favorably with the raw ensemble. In terms of continuous ranked probability score, they reach a performance comparable to quantile regression forests (QRF). However, they are unable to provide calibrated forecasts in areas associated with high climatological precipitation. In terms of predictive power for heavy precipitation events, they outperform both QRF and semi-parametric QRF with tail extensions.

Midjourney, a popular AI-powered image generator, is creating images of Donald Trump and Joe Biden despite saying that it would block users from doing so earlier this year ahead of the upcoming US presidential election. When Engadget prompted the service to create an image of "the president of the United States," Midjourney generated four images in various styles of former president Donald Trump. When asked to create an image of "the next president of the United States," the tool generated four images of Trump as well. When Engadget prompted Midjourney to create an image of "the current president of the United States," the service generated three images of Trump and one image of former president Barack Obama. The only time Midjourney refused to create an image of Trump or Biden was when it was asked to do so explicitly.

British female politicians have become the victims of fake pornography, with some of their faces used in nude images created using artificial intelligence. Political candidates targeted on one prominent fake pornography website include the Labour deputy leader, Angela Rayner; the education secretary, Gillian Keegan; the Commons leader, Penny Mordaunt; the former home secretary, Priti Patel; and the Labour backbencher Stella Creasy, according to Channel 4 News. Many of the images have been online for several years and attracted hundreds of thousands of views. While some are crude Photoshops featuring the politician's head imposed on to another person's naked body, other images appears to be more complicated deepfakes that have been created using artificial intelligence technology. Some of the politicians targeted have now contacted the police.

In a crucial election year for the world, with the UK, US and France among the countries going to the polls, disinformation is swirling around social media. There is much concern about deepfakes, or artificial intelligence-generated images or audio of leading political figures designed to mislead voters, and whether they will affect results. They have not been a huge feature of the UK election so far, but there has been a steady supply of examples from around the world, including in the US where a presidential election looms. Here are the visual elements to look out for. In deepfake videos the area around the mouth can be the biggest giveaway.