Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embedding space in which corresponding items from the two modalities end up close together. Since audio-caption datasets typically only contain matching pairs of recordings and descriptions, it has become common practice to create mismatching pairs by pairing the audio with a caption randomly drawn from the dataset. This is not ideal because the randomly sampled caption could, just by chance, partly or entirely describe the audio recording. However, correspondence information for all possible pairs is costly to annotate and thus typically unavailable; we, therefore, suggest substituting it with estimated correspondences. To this end, we propose a two-staged training procedure in which multiple retrieval models are first trained as usual, i.e., without estimated correspondences. In the second stage, the audio-caption correspondences predicted by these models then serve as prediction targets. We evaluate our method on the ClothoV2 and the AudioCaps benchmark and show that it improves retrieval performance, even in a restricting self-distillation setting where a single model generates and then learns from the estimated correspondences. We further show that our method outperforms the current state of the art by 1.6 pp. mAP@10 on the ClothoV2 benchmark.

We present a probabilistic model for stochastic iterative algorithms with the use case of optimization algorithms in mind. Based on this model, we present PAC-Bayesian generalization bounds for functions that are defined on the trajectory of the learned algorithm, for example, the expected (non-asymptotic) convergence rate and the expected time to reach the stopping criterion. Thus, not only does this model allow for learning stochastic algorithms based on their empirical performance, it also yields results about their actual convergence rate and their actual convergence time. We stress that, since the model is valid in a more general setting than learning-to-optimize, it is of interest for other fields of application, too. Finally, we conduct five practically relevant experiments, showing the validity of our claims.

Global Climate Models (GCMs) are crucial for predicting future climate changes by simulating the Earth systems. However, GCM outputs exhibit systematic biases due to model uncertainties, parameterization simplifications, and inadequate representation of complex climate phenomena. Traditional bias correction methods, which rely on historical observation data and statistical techniques, often neglect unobserved confounders, leading to biased results. This paper proposes a novel bias correction approach to utilize both GCM and observational data to learn a factor model that captures multi-cause latent confounders. Inspired by recent advances in causality based time series deconfounding, our method first constructs a factor model to learn latent confounders from historical data and then applies them to enhance the bias correction process using advanced time series forecasting models. The experimental results demonstrate significant improvements in the accuracy of precipitation outputs. By addressing unobserved confounders, our approach offers a robust and theoretically grounded solution for climate model bias correction.

Large vision-language models (VLMs) have shown significant performance boost in various application domains. However, adopting them to deal with several sequentially encountered tasks has been challenging because finetuning a VLM on a task normally leads to reducing its generalization power and the capacity of learning new tasks as well as causing catastrophic forgetting on previously learned tasks. Enabling using VLMs in multimodal continual learning (CL) settings can help to address such scenarios. To improve generalization capacity and prevent catastrophic forgetting, we propose a novel prompt-based CL method for VLMs, namely $\textbf{Clu}$ster-based $\textbf{Mo}$dality Fusion Prompt (\textbf{CluMo}). We design a novel \textbf{Key-Key-Prompt} pair, where each prompt is associated with a visual prompt key and a textual prompt key. We adopt a two-stage training strategy. During the first stage, the single-modal keys are trained via $K$-means clustering algorithm to help select the best semantically matched prompt. During the second stage, the prompt keys are frozen, the selected prompt is attached to the input for training the VLM in the CL scenario. Experiments on two benchmarks demonstrate that our method achieves SOTA performance.

Well-calibrated predictions of user preferences are essential for many applications. Since recommender systems typically select the top-N items for users, calibration for those top-N items, rather than for all items, is important. We show that previous calibration methods result in miscalibrated predictions for the top-N items, despite their excellent calibration performance when evaluated on all items. In this work, we address the miscalibration in the top-N recommended items. We first define evaluation metrics for this objective and then propose a generic method to optimize calibration models focusing on the top-N items. It groups the top-N items by their ranks and optimizes distinct calibration models for each group with rank-dependent training weights. We verify the effectiveness of the proposed method for both explicit and implicit feedback datasets, using diverse classes of recommender models.

The nasopharyngeal (NP) swab sample test, commonly used to detect COVID-19 and other respiratory illnesses, involves moving a swab through the nasal cavity to collect samples from the nasopharynx. While typically this is done by human healthcare workers, there is a significant societal interest to enable robots to do this test to reduce exposure to patients and to free up human resources. The task is challenging from the robotics perspective because of the dexterity and safety requirements. While other works have implemented specific hardware solutions, our research differentiates itself by using a ubiquitous rigid robotic arm. This work presents a case study where we investigate the strengths and challenges using compliant control system to accomplish NP swab tests with such a robotic configuration. To accomplish this, we designed a force sensing end-effector that integrates with the proposed torque controlled compliant control loop. We then conducted experiments where the robot inserted NP swabs into a 3D printed nasal cavity phantom. Ultimately, we found that the compliant control system outperformed a basic position controller and shows promise for human use. However, further efforts are needed to ensure the initial alignment with the nostril and to address head motion.

Existing symbolic regression methods organize the space of candidate mathematical expressions primarily based on their syntactic, structural similarity. However, this approach overlooks crucial equivalences between expressions that arise from mathematical symmetries, such as commutativity, associativity, and distribution laws for arithmetic operations. Consequently, expressions with similar errors on a given data set are apart from each other in the search space. This leads to a rough error landscape in the search space that efficient local, gradient-based methods cannot explore. This paper proposes and implements a measure of a behavioral distance, BED, that clusters together expressions with similar errors. The experimental results show that the stochastic method for calculating BED achieves consistency with a modest number of sampled values for evaluating the expressions. This leads to computational efficiency comparable to the tree-based syntactic distance. Our findings also reveal that BED significantly improves the smoothness of the error landscape in the search space for symbolic regression.

Forecasting in probabilistic time series is a complex endeavor that extends beyond predicting future values to also quantifying the uncertainty inherent in these predictions. Gaussian process regression stands out as a Bayesian machine learning technique adept at addressing this multifaceted challenge. This paper introduces a novel approach that blends the robustness of this Bayesian technique with the nuanced insights provided by the kernel perspective on quantum models, aimed at advancing quantum kernelized probabilistic forecasting. We incorporate a quantum feature map inspired by Ising interactions and demonstrate its effectiveness in capturing the temporal dependencies critical for precise forecasting. The optimization of our model's hyperparameters circumvents the need for computationally intensive gradient descent by employing gradient-free Bayesian optimization. Comparative benchmarks against established classical kernel models are provided, affirming that our quantum-enhanced approach achieves competitive performance.

Abstract--Within the context of intelligent manufacturing, industrial robots have a pivotal function. Nonetheless, extended operational periods cause a decline in their absolute positioning accuracy, preventing them from meeting high precision. To address this issue, this paper presents a novel robot algorithm that combines an adaptive and momental bound algorithm with decoupled weight decay (AdaModW), which has three-fold ideas: a) adopting an adaptive moment estimation (Adam) algorithm to achieve a high convergence rate, b) introducing a hyperparameter into the Adam algorithm to define the length of memory, effectively addressing the issue of the abnormal learning rate, and c) interpolating a weight decay coefficient to improve its generalization. Numerous experiments on an HRS-JR680 industrial robot show that the presented algorithm significantly outperforms state-of-the-art algorithms in robot calibration performance. Thus, in light of its reliability, this algorithm provides an efficient way to address robot calibration concerns.

In particular, developing data-driven machine learning models can provide early identification of patients with high risk for diabetes, potentially leading to more effective therapeutic strategies and reduced healthcare costs. However, regulation restrictions create barriers to developing centralized predictive models. This paper addresses the challenges by introducing a federated learning approach, which amalgamates predictive models without centralized data storage and processing, thus avoiding privacy issues. This marks the first application of federated learning to predict diabetes using real clinical datasets in Canada extracted from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) without crossprovince patient data sharing. We address class-imbalance issues through downsampling techniques and compare federated learning performance against province-based and centralized models. Experimental results show that the federated MLP model presents a similar or higher performance compared to the model trained with the centralized approach. However, the federated logistic regression model showed inferior performance compared to its centralized peer. Introduction Predicting diabetes based on patient risk factors is paramount for the Canadian and global populations due to its significant impact on public health and healthcare costs. The number of patients with chronic disease, including diabetes, in Ontario, Canada alone, increased by 11.0% over the 10-year study period to 9.8 million in 2017/18, and the number with multimorbidity increased by 12.2% to 6.5 million