Adaptive optimization methods are well known to achieve superior convergence relative to vanilla gradient methods. The traditional viewpoint in optimization, particularly in convex optimization, explains this improved performance by arguing that, unlike vanilla gradient schemes, adaptive algorithms mimic the behavior of a second-order method by adapting to the global geometry of the loss function. We argue that in the context of neural network optimization, this traditional viewpoint is insufficient. Instead, we advocate for a local trajectory analysis. For iterate trajectories produced by running a generic optimization algorithm OPT, we introduce $R^{\text{OPT}}_{\text{med}}$, a statistic that is analogous to the condition number of the loss Hessian evaluated at the iterates. Through extensive experiments, we show that adaptive methods such as Adam bias the trajectories towards regions where $R^{\text{Adam}}_{\text{med}}$ is small, where one might expect faster convergence. By contrast, vanilla gradient methods like SGD bias the trajectories towards regions where $R^{\text{SGD}}_{\text{med}}$ is comparatively large. We complement these empirical observations with a theoretical result that provably demonstrates this phenomenon in the simplified setting of a two-layer linear network. We view our findings as evidence for the need of a new explanation of the success of adaptive methods, one that is different than the conventional wisdom.

This paper aims for a potential architectural improvement for multilingual learning and asks: Can different tasks from different languages be modeled in a monolithic framework, i.e. without any task/language-specific module? The benefit of achieving this could open new doors for future multilingual research, including allowing systems trained on low resources to be further assisted by other languages as well as other tasks. We approach this goal by developing a learning framework named Polyglot Prompting to exploit prompting methods for learning a unified semantic space for different languages and tasks with multilingual prompt engineering. We performed a comprehensive evaluation of 6 tasks, namely topic classification, sentiment classification, named entity recognition, question answering, natural language inference, and summarization, covering 24 datasets and 49 languages. The experimental results demonstrated the efficacy of multilingual multitask prompt-based learning and led to inspiring observations. We also present an interpretable multilingual evaluation methodology and show how the proposed framework, multilingual multitask prompt training, works. We release all datasets prompted in the best setting and code.

Federated Learning (FL) enables distributed training by learners using local data, thereby enhancing privacy and reducing communication. However, it presents numerous challenges relating to the heterogeneity of the data distribution, device capabilities, and participant availability as deployments scale, which can impact both model convergence and bias. Existing FL schemes use random participant selection to improve fairness; however, this can result in inefficient use of resources and lower quality training. In this work, we systematically address the question of resource efficiency in FL, showing the benefits of intelligent participant selection, and incorporation of updates from straggling participants. We demonstrate how these factors enable resource efficiency while also improving trained model quality.

If you've looked at videos collected from trail cameras, you might have found that a large fraction of them contain no visible animals. And if you've spent much time looking at blank videos, you might wish there was a better way! Using automatic classification from Zamba, an AI tool for wildlife research and conservation, you can eliminate a substantial fraction of blank videos, sight unseen, while losing only a small fraction of videos that actually contain animals. The goal of this article is to quantify that claim. Here's how we'll do it: To train Zamba's classification model, we collected more than 280,000 videos from researchers at the Max Planck Institute for Evolutionary Anthropology working in West, Central, and East Africa.

In the 36th week of war in Ukraine, Russia backed out of a United Nations-sponsored agreement guaranteeing the safe passage of grain ships through the Black Sea, only to rejoin it three days later. Moscow's withdrawal over the weekend renewed fears of a global food crisis – concerns that have not been completely quelled since it rejoined because its return came with conditions. President Vladimir Putin said he reserved the right to back out again if Kyiv used the humanitarian corridor for attacks, the reason Russia gave for the initial pullout. The Kremlin has also warned that it has not yet decided whether to extend the grain deal, which expires in two weeks. Officials in Moscow had said that grain ships may have acted as a cloak for an attack on its naval base on Saturday at Sevastopol on the Crimean Peninsula.

Standard causal inference characterizes treatment effect through averages, but the counterfactual distributions could be different in not only the central tendency but also spread and shape. To provide a comprehensive evaluation of treatment effects, we focus on estimating quantile treatment effects (QTEs). Existing methods that invert a nonsmooth estimator of the cumulative distribution functions forbid inference on probability density functions (PDFs), but PDFs can reveal more nuanced characteristics of the counterfactual distributions. We adopt a semiparametric conditional distribution regression model that allows inference on any functionals of counterfactual distributions, including PDFs and multiple QTEs. To account for the observational nature of the data and ensure an efficient model, we adjust for a double balancing score that augments the propensity score with individual covariates. We provide a Bayesian estimation framework that appropriately propagates modeling uncertainty. We show via simulations that the use of double balancing score for confounding adjustment improves performance over adjusting for any single score alone, and the proposed semiparametric model estimates QTEs more accurately than other semiparametric methods. We apply the proposed method to the North Carolina birth weight dataset to analyze the effect of maternal smoking on infant's birth weight.

The argument role in event extraction refers to the relation between an event and an argument participating in it. Despite the great progress in event extraction, existing studies still depend on roles pre-defined by domain experts. These studies expose obvious weakness when extending to emerging event types or new domains without available roles. Therefore, more attention and effort needs to be devoted to automatically customizing argument roles. In this paper, we define this essential but under-explored task: open-vocabulary argument role prediction. The goal of this task is to infer a set of argument roles for a given event type. We propose a novel unsupervised framework, RolePred for this task. Specifically, we formulate the role prediction problem as an in-filling task and construct prompts for a pre-trained language model to generate candidate roles. By extracting and analyzing the candidate arguments, the event-specific roles are further merged and selected. To standardize the research of this task, we collect a new event extraction dataset from WikiPpedia including 142 customized argument roles with rich semantics. On this dataset, RolePred outperforms the existing methods by a large margin. Source code and dataset are available on our GitHub repository: https://github.com/yzjiao/RolePred

ML module using commonly used RESTful framework. Explosion in the number of connected IoT devices brought Comprehensive ML module based on both classical and increasing concerns for IoT systems security [1]. Industrial deep learning methods is implemented as a cloud-based service. IoT systems are particularly vulnerable, since IoT devices The ML module employs representative methods for may participate in mission-critical industrial control processes supervised device identification due to the availability of [2]. In recent years, the IoT security methods that exploit a device IDs in the collected WF data sets. Due to different WFs combination of specific features unique to the device, called collected from NB-IoT and Wi-Fi devices, different MLAs fingerprints, and machine learning (ML) algorithms, became are considered for the two scenarios. The system is integrated increasingly popular [3]-[10]. In particular, wireless fingerprints and tested in our labs and an extensive device identification (WF) may be extracted at the physical (PHY) layer of a performance is presented and visualised. The setup is currently wireless receiver, based on the signals received from different being migrated to a real-world industrial IoT scenario, where wireless IoT devices [3], [4].

An accurate model of the environment and the dynamic agents acting in it offers great potential for improving motion planning. We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for autonomous driving. Our method leverages 3D geometry as an inductive bias and learns a highly compact latent space directly from high-resolution videos of expert demonstrations. Our model is trained on an offline corpus of urban driving data, without any online interaction with the environment. MILE improves upon prior state-of-the-art by 31% in driving score on the CARLA simulator when deployed in a completely new town and new weather conditions. Our model can predict diverse and plausible states and actions, that can be interpretably decoded to bird's-eye view semantic segmentation. Further, we demonstrate that it can execute complex driving manoeuvres from plans entirely predicted in imagination. Our approach is the first camera-only method that models static scene, dynamic scene, and ego-behaviour in an urban driving environment. The code and model weights are available at https://github.com/wayveai/mile.

Pretraining-based (PT-based) automatic evaluation metrics (e.g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e.g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods. Although PT-based methods have become the de facto standard for training grammatical error correction (GEC) systems, GEC evaluation still does not benefit from pretrained knowledge. This paper takes the first step towards understanding and improving GEC evaluation with pretraining. We first find that arbitrarily applying PT-based metrics to GEC evaluation brings unsatisfactory correlation results because of the excessive attention to inessential systems outputs (e.g., unchanged parts). To alleviate the limitation, we propose a novel GEC evaluation metric to achieve the best of both worlds, namely PT-M2 which only uses PT-based metrics to score those corrected parts. Experimental results on the CoNLL14 evaluation task show that PT-M2 significantly outperforms existing methods, achieving a new state-of-the-art result of 0.949 Pearson correlation. Further analysis reveals that PT-M2 is robust to evaluate competitive GEC systems. Source code and scripts are freely available at https://github.com/pygongnlp/PT-M2.