Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference. We introduce the Variational Open-Domain (VOD) framework for end-to-end training and evaluation of retrieval-augmented models, focusing on open-domain question answering and language modelling. The VOD objective, a self-normalized estimate of the R\'enyi variational bound, approximates the task marginal likelihood and is evaluated under samples drawn from an auxiliary sampling distribution (cached retriever and/or approximate posterior). It remains tractable, even for retriever distributions defined on large corpora. We demonstrate VOD's versatility by training reader-retriever BERT-sized models on multiple-choice medical exam questions. On the MedMCQA dataset, we outperform the domain-tuned Med-PaLM by +5.3% despite using 2.500$\times$ fewer parameters. Our retrieval-augmented BioLinkBERT model scored 62.9% on the MedMCQA and 55.0% on the MedQA-USMLE. Last, we show the effectiveness of our learned retriever component in the context of medical semantic search.

Many important problems in AI, among them #SAT, parameter learning and probabilistic inference go beyond the classical satisfiability problem. Here, instead of finding a solution we are interested in a quantity associated with the set of solutions, such as the number of solutions, the optimal solution or the probability that a query holds in a solution. To model such quantitative problems in a uniform manner, a number of frameworks, e.g. Algebraic Model Counting and Semiring-based Constraint Satisfaction Problems, employ what we call the semiring paradigm. In the latter the abstract algebraic structure of the semiring serves as a means of parameterizing the problem definition, thus allowing for different modes of quantitative computations by choosing different semirings. While efficiently solvable cases have been widely studied, a systematic study of the computational complexity of such problems depending on the semiring parameter is missing. In this work, we characterize the latter by NP(R), a novel generalization of NP over semiring R, and obtain NP(R)-completeness results for a selection of semiring frameworks. To obtain more tangible insights into the hardness of NP(R), we link it to well-known complexity classes from the literature. Interestingly, we manage to connect the computational hardness to properties of the semiring. Using this insight, we see that, on the one hand, NP(R) is always at least as hard as NP or ModpP depending on the semiring R and in general unlikely to be in FPSPACEpoly. On the other hand, for broad subclasses of semirings relevant in practice we can employ reductions to NP, ModpP and #P. These results show that in many cases solutions are only mildly harder to compute than functions in NP, ModpP and #P, give us new insights into how problems that involve counting on semirings can be approached, and provide a means of assessing whether an algorithm is appropriate for a given class of problems.

=One of the most frequently farmed crops is the tomato crop. Late blight is the most prevalent tomato disease in the world, and often causes a significant reduction in the production of tomato crops. The importance of tomatoes as an agricultural product necessitates early detection of late blight. It is produced by the fungus Phytophthora. The earliest signs of late blight on tomatoes are unevenly formed, water-soaked lesions on the leaves located on the plant canopy's younger leave White cottony growth may appear in humid environments evident on the undersides of the leaves that have been impacted. Lesions increase as the disease proceeds, turning the leaves brown to shrivel up and die. Using picture segmentation and the Multi-class SVM technique, late blight disorder is discovered in this work. Image segmentation is employed for separating damaged areas on leaves, and the Multi-class SVM method is used for reliable disease categorization. 30 reputable studies were chosen from a total of 2770 recognized papers. The primary goal of this study is to compile cutting-edge research that identifies current research trends, problems, and prospects for late blight detection. It also looks at current approaches for applying image processing to diagnose and detect late blight. A suggested taxonomy for late blight detection has also been provided. In the same way, a model for the development of the solutions to problems is also presented. Finally, the research gaps have been presented in terms of open issues for the provision of future directions in image processing for the researchers.

We study dynamic discrete choice models, where a commonly studied problem involves estimating parameters of agent reward functions (also known as "structural" parameters), using agent behavioral data. Maximum likelihood estimation for such models requires dynamic programming, which is limited by the curse of dimensionality. In this work, we present a novel algorithm that provides a data-driven method for selecting and aggregating states, which lowers the computational and sample complexity of estimation. Our method works in two stages. In the first stage, we use a flexible inverse reinforcement learning approach to estimate agent Q-functions. We use these estimated Q-functions, along with a clustering algorithm, to select a subset of states that are the most pivotal for driving changes in Q-functions. In the second stage, with these selected "aggregated" states, we conduct maximum likelihood estimation using a commonly used nested fixed-point algorithm. The proposed two-stage approach mitigates the curse of dimensionality by reducing the problem dimension. Theoretically, we derive finite-sample bounds on the associated estimation error, which also characterize the trade-off of computational complexity, estimation error, and sample complexity. We demonstrate the empirical performance of the algorithm in two classic dynamic discrete choice estimation applications.

Quantum computing is a rapidly evolving field that promises to revolutionize various domains, and finance is no exception. There is a variety of computationally hard financial problems for which quantum algorithms can potentially offer advantages [24, 16, 39, 6], for example in combinatorial optimization [34, 42], convex optimization [30, 43], monte carlo simulations [15, 44, 21], and machine learning [41, 18, 1]. In this work, we explore the potential of quantum machine learning methods in improving the performance of forecasting in finance, specifically focusing on two use cases within the business of Itaú Unibanco, the largest bank in Latin America. In the first use case, we aim to improve the performance of Random Forest methods for churn prediction. We introduce quantum algorithms for Determinantal Point Processes (DPP) sampling [29], and develop a method of DPP sampling to enhance Random Forest models.

This paper proposes a multi-spectral random forest classifier with suitable feature selection and masking for tree cover estimation in urban areas. The key feature of the proposed classifier is filtering out the built-up region using spectral indices followed by random forest classification on the remaining mask with carefully selected features. Using Sentinel-2 satellite imagery, we evaluate the performance of the proposed technique on a specified area (approximately 82 acres) of Lahore University of Management Sciences (LUMS) and demonstrate that our method outperforms a conventional random forest classifier as well as state-of-the-art methods such as European Space Agency (ESA) WorldCover 10m 2020 product as well as a DeepLabv3 deep learning architecture.

Two-Tower Vision-Language (VL) models have shown promising improvements on various downstream VL tasks. Although the most advanced work improves performance by building bridges between encoders, it suffers from ineffective layer-by-layer utilization of uni-modal representations and cannot flexibly exploit different levels of uni-modal semantic knowledge. In this work, we propose ManagerTower, a novel VL model architecture that gathers and combines the insights of pre-trained uni-modal experts at different levels. The managers introduced in each cross-modal layer can adaptively aggregate uni-modal semantic knowledge to facilitate more comprehensive cross-modal alignment and fusion. ManagerTower outperforms previous strong baselines both with and without Vision-Language Pre-training (VLP). With only 4M VLP data, ManagerTower achieves superior performances on various downstream VL tasks, especially 79.15% accuracy on VQAv2 Test-Std, 86.56% IR@1 and 95.64% TR@1 on Flickr30K. Code and checkpoints are available at https://github.com/LooperXX/ManagerTower.

A key component of automated algorithm selection and configuration, which in most cases are performed using supervised machine learning (ML) methods is a good-performing predictive model. The predictive model uses the feature representation of a set of problem instances as input data and predicts the algorithm performance achieved on them. Common machine learning models struggle to make predictions for instances with feature representations not covered by the training data, resulting in poor generalization to unseen problems. In this study, we propose a workflow to estimate the generalizability of a predictive model for algorithm performance, trained on one benchmark suite to another. The workflow has been tested by training predictive models across benchmark suites and the results show that generalizability patterns in the landscape feature space are reflected in the performance space.

An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common solution is for a human expert to define either a penalty in the reward function or a cost to be minimised when reaching unsafe states. However, this is non-trivial, since too small a penalty may lead to agents that reach unsafe states, while too large a penalty increases the time to convergence. Additionally, the difficulty in designing reward or cost functions can increase with the complexity of the problem. Hence, for a given environment with a given set of unsafe states, we are interested in finding the upper bound of rewards at unsafe states whose optimal policies minimise the probability of reaching those unsafe states, irrespective of task rewards. We refer to this exact upper bound as the "Minmax penalty", and show that it can be obtained by taking into account both the controllability and diameter of an environment. We provide a simple practical model-free algorithm for an agent to learn this Minmax penalty while learning the task policy, and demonstrate that using it leads to agents that learn safe policies in high-dimensional continuous control environments.

The accurate estimation of the mutual information is a crucial task in various applications, including machine learning, communications, and biology, since it enables the understanding of complex systems. High-dimensional data render the task extremely challenging due to the amount of data to be processed and the presence of convoluted patterns. Neural estimators based on variational lower bounds of the mutual information have gained attention in recent years but they are prone to either high bias or high variance as a consequence of the partition function. We propose a novel class of discriminative mutual information estimators based on the variational representation of the $f$-divergence. We investigate the impact of the permutation function used to obtain the marginal training samples and present a novel architectural solution based on derangements. The proposed estimator is flexible as it exhibits an excellent bias/variance trade-off. Experiments on reference scenarios demonstrate that our approach outperforms state-of-the-art neural estimators both in terms of accuracy and complexity.