Performing event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full $n^2$ pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference, common in many applications. As a result cross-document coreference algorithms are rarely applied to downstream tasks. We draw on an insight from discourse coherence theory: potential coreferences are constrained by the reader's discourse focus. We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters. We then use these neighborhoods to sample only hard negatives to train a fine-grained classifier on mention pairs and their local discourse features. Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora. Furthermore, training on multiple corpora improves average performance across all datasets by 17.2 F1 points, leading to a robust coreference resolution model for use in downstream tasks where link distribution is unknown.

Despite the recent success in many applications, the high computational requirements of vision transformers limit their use in resource-constrained settings. While many existing methods improve the quadratic complexity of attention, in most vision transformers, self-attention is not the major computation bottleneck, e.g., more than 80% of the computation is spent on fully-connected layers. To improve the computational complexity of all layers, we propose a novel token downsampling method, called Token Pooling, efficiently exploiting redundancies in the images and intermediate token representations. We show that, under mild assumptions, softmax-attention acts as a high-dimensional low-pass (smoothing) filter. Thus, its output contains redundancy that can be pruned to achieve a better trade-off between the computational cost and accuracy. Our new technique accurately approximates a set of tokens by minimizing the reconstruction error caused by downsampling. We solve this optimization problem via cost-efficient clustering. We rigorously analyze and compare to prior downsampling methods. Our experiments show that Token Pooling significantly improves the cost-accuracy trade-off over the state-of-the-art downsampling. Token Pooling is a simple and effective operator that can benefit many architectures. Applied to DeiT, it achieves the same ImageNet top-1 accuracy using 42% fewer computations.

The uncertainty of the energy generated by photovoltaic systems incurs an additional cost for a guaranteed, reliable supply of energy (i.e., energy storage). This investigation aims to decrease the additional cost by introducing probabilistic multi-task intra-hour solar forecasting (feasible in real time applications) to increase the penetration of photovoltaic systems in power grids. The direction of moving clouds is estimated in consecutive sequences of sky images by extracting features of cloud dynamics with the objective of forecasting the global solar irradiance that reaches photovoltaic systems. The sky images are acquired using a low-cost infrared sky imager mounted on a solar tracker. The solar forecasting algorithm is based on kernel learning methods, and uses the clear sky index as predictor and features extracted from clouds as feature vectors. The proposed solar forecasting algorithm achieved 16.45\% forecasting skill 8 minutes ahead with a resolution of 15 seconds. In contrast, previous work reached 15.4\% forecasting skill with the resolution of 1 minute. Therefore, this solar forecasting algorithm increases the performances with respect to the state-of-the-art, providing grid operators with the capability of managing the inherent uncertainties of power grids with a high penetration of photovoltaic systems.

The least mean square (LMS) algorithms are of paramount importance in the field of signal processing since their emergence [61, 62, 60]. In particular, they are used profusely in adaptive filtering and signal analysis [27, 64, 24, 5]. The key aspects that make LMS algorithms attractive are their low complexity, stability, and an unbiased mean convergence to the so-called Wiener solution in stationary environments [48]. Unfortunately, its rate of convergence depends on the eigenvalue spread of the correlation matrix of the input signal in non-stationary environments [62, 27]. Accordingly, many variant algorithms were proposed to achieve better performance by curtailing the influence of the spectral properties of the input signal correlation matrix; see, for instance, the LMS-Newton algorithm [25], transform-domain algorithm [37], and affine projection algorithm [49]. On the other hand, a desire for computationally simpler algorithms has also led to the development of many variants such as quantized-error algorithms [6, 19, 30] and normalized LMS algorithms [65, 48, 36]. A decent list of these variant algorithms along with the details of their key features is provided in [24, Ch. 4]. We also refer to fairly recent survey articles [63, 26] on the history of adaptive filtering and the development of the LMS algorithms.

This work presents a supervised method for generating a classifier model of the stances held by Chinese-speaking politicians and other Twitter users. Many previous works of political tweets prediction exist on English tweets, but to the best of our knowledge, this is the first work that builds prediction model on Chinese political tweets. It firstly collects data by scraping tweets of famous political figure and their related users. It secondly defines the political spectrum in two groups: the group that shows approvals to the Chinese Communist Party and the group that does not. Since there are not space between words in Chinese to identify the independent words, it then completes segmentation and vectorization by Jieba, a Chinese segmentation tool. Finally, it trains the data collected from political tweets and produce a classification model with high accuracy for understanding users' political stances from their tweets on Twitter.

Modern machine learning systems are traditionally designed and tested with the overall goal of achieving the best possible performance on average. In this work, we consider an approach to building learning systems which treats the question of "how should we quantify good off-sample performance?" as a key design decision. We describe this proposal using a simple and general formulation, place the current dominant paradigm within the proper historical context, and then survey the literature for more recent developments that depart from tradition and can be viewed as special cases of our proposed methodology.

As an important problem in causal inference, we discuss the identification and estimation of treatment effects (TEs) under limited overlap; that is, when subjects with certain features belong to a single treatment group. We use a latent variable to model a prognostic score which is widely used in biostatistics and sufficient for TEs; i.e., we build a generative prognostic model. We prove that the latent variable recovers a prognostic score, and the model identifies individualized treatment effects. The model is then learned as \beta-Intact-VAE--a new type of variational autoencoder (VAE). We derive the TE error bounds that enable representations balanced for treatment groups conditioned on individualized features. The proposed method is compared with recent methods using (semi-)synthetic datasets.

Alzheimer's disease is characterized by alterations of the brain's structural and functional connectivity during its progressive degenerative processes. Existing auxiliary diagnostic methods have accomplished the classification task, but few of them can accurately evaluate the changing characteristics of brain connectivity. In this work, a prior guided adversarial representation learning and hypergraph perceptual network (PGARL-HPN) is proposed to predict abnormal brain connections using triple-modality medical images. Concretely, a prior distribution from the anatomical knowledge is estimated to guide multimodal representation learning using an adversarial strategy. Also, the pairwise collaborative discriminator structure is further utilized to narrow the difference of representation distribution. Moreover, the hypergraph perceptual network is developed to effectively fuse the learned representations while establishing high-order relations within and between multimodal images. Experimental results demonstrate that the proposed model outperforms other related methods in analyzing and predicting Alzheimer's disease progression. More importantly, the identified abnormal connections are partly consistent with the previous neuroscience discoveries. The proposed model can evaluate characteristics of abnormal brain connections at different stages of Alzheimer's disease, which is helpful for cognitive disease study and early treatment.

This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to enhance the performance of the BERT-based models on the `Offensive Language Detection' task. Therefore, we customize attention probabilities by changing the `Attention Mask' input to create more efficacious word embeddings. To do this, we firstly tokenize the training set of the exploited datasets (by BERT tokenizer). Then, we apply Multinomial Naive Bayes to map these tokens to two probabilities. These probabilities indicate the likelihood of making a text non-offensive or offensive, provided that it contains that token. Afterwards, we use these probabilities to define a new term, namely Offensive Score. Next, we create two separate (because of the differences in the types of the employed datasets) equations based on Offensive Scores for each language to re-distribute the `Attention Mask' input for paying more attention to more offensive phrases. Eventually, we put the F1-macro score as our evaluation metric and fine-tune several combinations of BERT with ANNs, CNNs and RNNs to examine the effect of using this methodology on various combinations. The results indicate that all models will enhance with this methodology. The most improvement was 2% and 10% for English and Persian languages, respectively.

Real-time bidding (RTB) has become a critical way of online advertising. In RTB, an advertiser can participate in bidding ad impressions to display its advertisements. The advertiser determines every impression's bidding price according to its bidding strategy. Therefore, a good bidding strategy can help advertisers improve cost efficiency. This paper focuses on optimizing a single advertiser's bidding strategy using reinforcement learning (RL) in RTB. Unfortunately, it is challenging to optimize the bidding strategy through RL at the granularity of impression due to the highly dynamic nature of the RTB environment. In this paper, we first utilize a widely accepted linear bidding function to compute every impression's base price and optimize it by a mutable adjustment factor derived from the RTB auction environment, to avoid optimizing every impression's bidding price directly. Specifically, we use the maximum entropy RL algorithm (Soft Actor-Critic) to optimize the adjustment factor generation policy at the impression-grained level. Finally, the empirical study on a public dataset demonstrates that the proposed bidding strategy has superior performance compared with the baselines.