Clustering is a fundamental task in theoretical computer science and machine learning aimed at dividing a set of data items into several groups or clusters, such that each group contains similar data items. Typically, the similarity between data items is measured using a metric distance function. Clustering is often modeled as an optimization problem where the objective is to minimize a global cost function that reflects the quality of the clusters; this function varies depending on the application. Among the many cost functions studied for clustering, the most popular are k-median, k-means, and k-center. These objectives generally aim to minimize the variance within the clusters, serving as a proxy for grouping similar data items In this work, we study clustering problems with fairness constraints, commonly known as fair clustering problems. Fair clustering emerged as one of the most active research areas in algorithms motivated by the recent trend of research on fairness in artificial intelligence. In a seminal work, Chierichetti et al. [18] introduced a fair clustering problem, where given a set R of red points, a set B of blue points, and an integer balance parameter t 1, a clustering is said to be balanced if, in every cluster, the number of red points is at least 1/t times the number of blue points and at most t times the number of blue points.

In this work, a robust autoencoder ensemble-based approach designed to address anomaly detection in text corpora is introduced. Each autoencoder within the ensemble incorporates a local robust subspace recovery projection of the original data in its encoding embedding, leveraging the geometric properties of the k-nearest neighbors to optimize subspace recovery and identify anomalous patterns in textual data. The evaluation of such an approach needs an experimental setting dedicated to the context of textual anomaly detection. Thus, beforehand, a comprehensive real-world taxonomy is introduced to distinguish between independent anomalies and contextual anomalies. Such a study to identify clearly the kinds of anomalies appearing in a textual context aims at addressing a critical gap in the existing literature. Then, extensive experiments on classical text corpora have been conducted and their results are presented that highlights the efficiency, both in robustness and in performance, of the robust autoencoder ensemble-based approach when detecting both independent and contextual anomalies. Diverse range of tasks, including classification, sentiment analysis, and spam detection, across eight different corpora, have been studied in these experiments.

Large pre-trained vision-language models such as CLIP provide compact and general-purpose representations of text and images that are demonstrably effective across multiple downstream zero-shot prediction tasks. However, owing to the nature of their training process, these models have the potential to 1) propagate or amplify societal biases in the training data and 2) learn to rely on spurious features. This paper proposes FairerCLIP, a general approach for making zero-shot predictions of CLIP more fair and robust to spurious correlations. We formulate the problem of jointly debiasing CLIP's image and text representations in reproducing kernel Hilbert spaces (RKHSs), which affords multiple benefits: 1) Flexibility: Unlike existing approaches, which are specialized to either learn with or without ground-truth labels, FairerCLIP is adaptable to learning in both scenarios. 2) Ease of Optimization: FairerCLIP lends itself to an iterative optimization involving closed-form solvers, which leads to $4\times$-$10\times$ faster training than the existing methods. 3) Sample Efficiency: Under sample-limited conditions, FairerCLIP significantly outperforms baselines when they fail entirely. And, 4) Performance: Empirically, FairerCLIP achieves appreciable accuracy gains on benchmark fairness and spurious correlation datasets over their respective baselines.

The Learning-to-match (LTM) framework proves to be an effective inverse optimal transport approach for learning the underlying ground metric between two sources of data, facilitating subsequent matching. However, the conventional LTM framework faces scalability challenges, necessitating the use of the entire dataset each time the parameters of the ground metric are updated. In adapting LTM to the deep learning context, we introduce the mini-batch Learning-to-match (m-LTM) framework for audio-text retrieval problems. Moreover, to cope with misaligned training data in practice, we propose a variant using partial optimal transport to mitigate the harm of misaligned data pairs in training data. We conduct extensive experiments on audio-text matching problems using three datasets: AudioCaps, Clotho, and ESC-50. Results demonstrate that our proposed method is capable of learning rich and expressive joint embedding space, which achieves SOTA performance. Beyond this, the proposed m-LTM framework is able to close the modality gap across audio and text embedding, which surpasses both triplet and contrastive loss in the zero-shot sound event detection task on the ESC-50 dataset. Notably, our strategy of employing partial optimal transport with m-LTM demonstrates greater noise tolerance than contrastive loss, especially under varying noise ratios in training data on the AudioCaps dataset.

This paper introduces a novel approach to predicting periodic time series using reservoir computing. The model is tailored to deliver precise forecasts of rhythms, a crucial aspect for tasks such as generating musical rhythm. Leveraging reservoir computing, our proposed method is ultimately oriented towards predicting human perception of rhythm. Our network accurately predicts rhythmic signals within the human frequency perception range. The model architecture incorporates primary and intermediate neurons tasked with capturing and transmitting rhythmic information. Two parameter matrices, denoted as c and k, regulate the reservoir's overall dynamics. We propose a loss function to adapt c post-training and introduce a dynamic selection (DS) mechanism that adjusts $k$ to focus on areas with outstanding contributions. Experimental results on a diverse test set showcase accurate predictions, further improved through real-time tuning of the reservoir via c and k. Comparative assessments highlight its superior performance compared to conventional models.

Encryption on the internet with the shift to HTTPS has been an important step to improve the privacy of internet users. However, there is an increasing body of work about extracting information from encrypted internet traffic without having to decrypt it. Such attacks bypass security guarantees assumed to be given by HTTPS and thus need to be understood. Prior works showed that the variable bitrates of video streams are sufficient to identify which video someone is watching. These works generally have to make trade-offs in aspects such as accuracy, scalability, robustness, etc. These trade-offs complicate the practical use of these attacks. To that end, we propose a deep metric learning framework based on the triplet loss method. Through this framework, we achieve robust, generalisable, scalable and transferable encrypted video stream detection. First, the triplet loss is better able to deal with video streams not seen during training. Second, our approach can accurately classify videos not seen during training. Third, we show that our method scales well to a dataset of over 1000 videos. Finally, we show that a model trained on video streams over Chrome can also classify streams over Firefox. Our results suggest that this side-channel attack is more broadly applicable than originally thought. We provide our code alongside a diverse and up-to-date dataset for future research.

Learning in simulation and transferring the learned policy to the real world has the potential to enable generalist robots. The key challenge of this approach is to address simulation-to-reality (sim-to-real) gaps. Previous methods often require domain-specific knowledge a priori. We argue that a straightforward way to obtain such knowledge is by asking humans to observe and assist robot policy execution in the real world. The robots can then learn from humans to close various sim-to-real gaps. We propose TRANSIC, a data-driven approach to enable successful sim-to-real transfer based on a human-in-the-loop framework. TRANSIC allows humans to augment simulation policies to overcome various unmodeled sim-to-real gaps holistically through intervention and online correction. Residual policies can be learned from human corrections and integrated with simulation policies for autonomous execution. We show that our approach can achieve successful sim-to-real transfer in complex and contact-rich manipulation tasks such as furniture assembly. Through synergistic integration of policies learned in simulation and from humans, TRANSIC is effective as a holistic approach to addressing various, often coexisting sim-to-real gaps. It displays attractive properties such as scaling with human effort. Videos and code are available at https://transic-robot.github.io/

Understaffing has been consistently identified as the major challenge facing Healthcare today [7, 1, 2, 21, 55, 82, 97, 87, 124]. Automation tools that make use of Machine Learning (also known as Healthcare 4.0 [126]) have been consistently identified as crucial for reducing the workload of Healthcare professionals and improving the quality of care [5, 34, 44, 46, 78, 86, 94, 136]. In turn, the shortage of standard benchmarks has been consistently identified as a central roadblock for machine learning in Healthcare [27, 31, 49, 52, 59, 76, 81, 95, 110]. Whether it's ImageNet [32] in Computer Vision or GLUE [128] in natural language processing, benchmarks are a core research tool in mature applications of machine learning, enabling quantitative analysis of learning methodologies to guide and orient their development.

In many cases, they are fundamental elements of the created systems and significantly impact their performance. Therefore, it is important to select the appropriate embedding model based on the results of its evaluation. Most often, evaluation is conducted on individual tasks using a limited set of datasets, leaving the open question of how such embedding models would work for other tasks. To solve this problem, Muennighoff et al. [2023] created a Massive Text Embedding Benchmark (MTEB). MTEB provides a simple and clear way to examine how the model behaves for different types of tasks. Most of the tasks in MTEB are based on English-language datasets, and only a few are multilingual, making it impossible to do a good comparison of models for languages other than English. Therefore, extensions to MTEB with language-specific task sets have begun to appear, among which are C-MTEB [Xiao et al., 2023] for Chinese, F-MTEB

Federated learning (FL) requires edge devices to perform local training and exchange information with a parameter server, leading to substantial energy consumption. A critical challenge in practical FL systems is the rapid energy depletion of battery-limited edge devices, which curtails their operational lifespan and affects the learning performance. To address this issue, we apply energy harvesting technique in FL systems to extract ambient energy for continuously powering edge devices. We first establish the convergence bound for the wireless FL system with energy harvesting devices, illustrating that the convergence is impacted by partial device participation and packet drops, both of which depend on the energy supply. To accelerate the convergence, we formulate a joint device scheduling and power control problem and model it as a Markov decision process (MDP). By solving this MDP, we derive the optimal transmission policy and demonstrate that it possesses a monotone structure with respect to the battery and channel states. To overcome the curse of dimensionality caused by the exponential complexity of computing the optimal policy, we propose a low-complexity algorithm, which is asymptotically optimal as the number of devices increases. Furthermore, for unknown channels and harvested energy statistics, we develop a structure-enhanced deep reinforcement learning algorithm that leverages the monotone structure of the optimal policy to improve the training performance. Finally, extensive numerical experiments on real-world datasets are presented to validate the theoretical results and corroborate the effectiveness of the proposed algorithms.