Automatic legal text classification systems have been proposed in the literature to address knowledge extraction from judgments and detect their aspects. However, most of these systems are black boxes even when their models are interpretable. This may raise concerns about their trustworthiness. Accordingly, this work contributes with a system combining Natural Language Processing (NLP) with Machine Learning (ML) to classify legal texts in an explainable manner. We analyze the features involved in the decision and the threshold bifurcation values of the decision paths of tree structures and present this information to the users in natural language. This is the first work on automatic analysis of legal texts combining NLP and ML along with Explainable Artificial Intelligence techniques to automatically make the models' decisions understandable to end users. Furthermore, legal experts have validated our solution, and this knowledge has also been incorporated into the explanation process as "expert-in-the-loop" dictionaries. Experimental results on an annotated data set in law categories by jurisdiction demonstrate that our system yields competitive classification performance, with accuracy values well above 90%, and that its automatic explanations are easily understandable even to non-expert users.

Finance-related news such as Bloomberg News, CNN Business and Forbes are valuable sources of real data for market screening systems. In news, an expert shares opinions beyond plain technical analyses that include context such as political, sociological and cultural factors. In the same text, the expert often discusses the performance of different assets. Some key statements are mere descriptions of past events while others are predictions. Therefore, understanding the temporality of the key statements in a text is essential to separate context information from valuable predictions. We propose a novel system to detect the temporality of finance-related news at discourse level that combines Natural Language Processing and Machine Learning techniques, and exploits sophisticated features such as syntactic and semantic dependencies. More specifically, we seek to extract the dominant tenses of the main statements, which may be either explicit or implicit. We have tested our system on a labelled dataset of finance-related news annotated by researchers with knowledge in the field. Experimental results reveal a high detection precision compared to an alternative rule-based baseline approach. Ultimately, this research contributes to the state-of-the-art of market screening by identifying predictive knowledge for financial decision making.

Alzheimer's disease is a progressive, debilitating neurodegenerative disease that affects 50 million people globally. Despite this substantial health burden, available treatments for the disease are limited and its fundamental causes remain poorly understood. Previous work has suggested the existence of clinically-meaningful sub-types, which it is suggested may correspond to distinct etiologies, disease courses, and ultimately appropriate treatments. Here, we use unsupervised learning techniques on electronic health records (EHRs) from a cohort of memory disorder patients to characterise heterogeneity in this disease population. Pre-trained embeddings for medical codes as well as transformer-derived Clinical BERT embeddings of free text are used to encode patient EHRs. We identify the existence of sub-populations on the basis of comorbidities and shared textual features, and discuss their clinical significance.

This position paper proposes a systematic approach towards developing a framework to help select the most effective embedding models for natural language processing (NLP) tasks, addressing the challenge posed by the proliferation of both proprietary and open-source encoder models.

Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that effectively balances individual channel treatment for improved forecasting performance without overlooking essential interactions between channels. Motivated by our observation of a correlation between the time series model's performance boost against channel mixing and the intrinsic similarity on a pair of channels, we developed a novel and adaptable Channel Clustering Module (CCM). CCM dynamically groups channels characterized by intrinsic similarities and leverages cluster identity instead of channel identity, combining the best of CD and CI worlds. Extensive experiments on real-world datasets demonstrate that CCM can (1) boost the performance of CI and CD models by an average margin of 2.4% and 7.2% on long-term and short-term forecasting, respectively; (2) enable zero-shot forecasting with mainstream time series forecasting models; (3) uncover intrinsic time series patterns among channels and improve interpretability of complex time series models.

The popularity of transfer learning stems from the fact that it can borrow information from useful auxiliary datasets. Existing statistical transfer learning methods usually adopt a global similarity measure between the source data and the target data, which may lead to inefficiency when only local information is shared. In this paper, we propose a novel Bayesian transfer learning method named "CONCERT" to allow robust local information transfer for high-dimensional data analysis. A novel conditional spike-and-slab prior is introduced in the joint distribution of target and source parameters for information transfer. By incorporating covariate-specific priors, we can characterize the local similarities and make the sources work collaboratively to help improve the performance on the target. Distinguished from existing work, CONCERT is a one-step procedure, which achieves variable selection and information transfer simultaneously. Variable selection consistency is established for our CONCERT. To make our algorithm scalable, we adopt the variational Bayes framework to facilitate implementation. Extensive experiments and a genetic data analysis demonstrate the validity and the advantage of CONCERT over existing cutting-edge transfer learning methods. We also extend our CONCERT to the logistical models with numerical studies showing its superiority over other methods.

Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of linear regression a notable gap still exists in the theoretical understanding of transfer learning. In-distribution research on high-dimensional linear regression has led to the identification of a phenomenon known as \textit{benign overfitting}, in which linear interpolators overfit to noisy training labels and yet still generalize well. This behavior occurs under specific conditions on the source covariance matrix and input data dimension. Therefore, it is natural to wonder how such high-dimensional linear models behave under transfer learning. We prove the first non-asymptotic excess risk bounds for benignly-overfit linear interpolators in the transfer learning setting. From our analysis, we propose a taxonomy of \textit{beneficial} and \textit{malignant} covariate shifts based on the degree of overparameterization. We follow our analysis with empirical studies that show these beneficial and malignant covariate shifts for linear interpolators on real image data, and for fully-connected neural networks in settings where the input data dimension is larger than the training sample size.

Language models (LMs) may lead their users to make suboptimal downstream decisions when they confidently hallucinate. This issue can be mitigated by having the LM verbally convey the probability that its claims are correct, but existing models cannot produce text with calibrated confidence statements. Through the lens of decision-making, we formalize linguistic calibration for long-form generations: an LM is linguistically calibrated if its generations enable its users to make calibrated probabilistic predictions. This definition enables a training framework where a supervised finetuning step bootstraps an LM to emit long-form generations with confidence statements such as "I estimate a 30% chance of..." or "I am certain that...", followed by a reinforcement learning step which rewards generations that enable a user to provide calibrated answers to related questions. We linguistically calibrate Llama 2 7B and find in automated and human evaluations of long-form generations that it is significantly more calibrated than strong finetuned factuality baselines with comparable accuracy. These findings generalize under distribution shift on question-answering and under a significant task shift to person biography generation. Our results demonstrate that long-form generations may be calibrated end-to-end by constructing an objective in the space of the predictions that users make in downstream decision-making.

The Lion optimizer has been a promising competitor with the AdamW for training large AI models, with advantages on memory, computation, and sample efficiency. In this paper, we introduce Distributed Lion, an innovative adaptation of Lion for distributed training environments. Leveraging the sign operator in Lion, our Distributed Lion only requires communicating binary or lower-precision vectors between workers to the center server, significantly reducing the communication cost. Our theoretical analysis confirms Distributed Lion's convergence properties. Empirical results demonstrate its robustness across a range of tasks, worker counts, and batch sizes, on both vision and language problems. Notably, Distributed Lion attains comparable performance to standard Lion or AdamW optimizers applied on aggregated gradients, but with significantly reduced communication bandwidth. This feature is particularly advantageous for training large models. In addition, we also demonstrate that Distributed Lion presents a more favorable performance-bandwidth balance compared to existing efficient distributed methods such as deep gradient compression and ternary gradients.

Additive Gaussian Processes (GPs) are popular approaches for nonparametric feature selection. The common training method for these models is Bayesian Back-fitting. However, the convergence rate of Back-fitting in training additive GPs is still an open problem. By utilizing a technique called Kernel Packets (KP), we prove that the convergence rate of Back-fitting is no faster than $(1-\mathcal{O}(\frac{1}{n}))^t$, where $n$ and $t$ denote the data size and the iteration number, respectively. Consequently, Back-fitting requires a minimum of $\mathcal{O}(n\log n)$ iterations to achieve convergence. Based on KPs, we further propose an algorithm called Kernel Multigrid (KMG). This algorithm enhances Back-fitting by incorporating a sparse Gaussian Process Regression (GPR) to process the residuals after each Back-fitting iteration. It is applicable to additive GPs with both structured and scattered data. Theoretically, we prove that KMG reduces the required iterations to $\mathcal{O}(\log n)$ while preserving the time and space complexities at $\mathcal{O}(n\log n)$ and $\mathcal{O}(n)$ per iteration, respectively. Numerically, by employing a sparse GPR with merely 10 inducing points, KMG can produce accurate approximations of high-dimensional targets within 5 iterations.