This paper proposes a problem-independent GRASP metaheuristic using the random-key optimizer (RKO) paradigm. GRASP (greedy randomized adaptive search procedure) is a metaheuristic for combinatorial optimization that repeatedly applies a semi-greedy construction procedure followed by a local search procedure. The best solution found over all iterations is returned as the solution of the GRASP. Continuous GRASP (C-GRASP) is an extension of GRASP for continuous optimization in the unit hypercube. A random-key optimizer (RKO) uses a vector of random keys to encode a solution to a combinatorial optimization problem. It uses a decoder to evaluate a solution encoded by the vector of random keys. A random-key GRASP is a C-GRASP where points in the unit hypercube are evaluated employing a decoder. We describe random key GRASP consisting of a problem-independent component and a problem-dependent decoder. As a proof of concept, the random-key GRASP is tested on five NP-hard combinatorial optimization problems: traveling salesman problem, tree of hubs location problem, Steiner triple covering problem, node capacitated graph partitioning problem, and job sequencing and tool switching problem.

In the evolving landscape of deep learning, selecting the best pre-trained models from a growing number of choices is a challenge. Transferability scorers propose alleviating this scenario, but their recent proliferation, ironically, poses the challenge of their own assessment. In this work, we propose both robust benchmark guidelines for transferability scorers, and a well-founded technique to combine multiple scorers, which we show consistently improves their results. We extensively evaluate 13 scorers from literature across 11 datasets, comprising generalist, fine-grained, and medical imaging datasets. We show that few scorers match the predictive performance of the simple raw metric of models on ImageNet, and that all predictors suffer on medical datasets. Our results highlight the potential of combining different information sources for reliably predicting transferability across varied domains.

Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e., sensitivity to design settings such as example selection, order, and prompt formatting. Previous studies have addressed LLM bias through external adjustment of model outputs, but the internal mechanisms that lead to such bias remain unexplored. Our work delves into these mechanisms, particularly investigating how feedforward neural networks (FFNs) and attention heads result in the bias of LLMs. By Interpreting the contribution of individual FFN vectors and attention heads, we identify the biased LLM components that skew LLMs' prediction toward specific labels. To mitigate these biases, we introduce UniBias, an inference-only method that effectively identifies and eliminates biased FFN vectors and attention heads. Extensive experiments across 12 NLP datasets demonstrate that UniBias significantly enhances ICL performance and alleviates prompt brittleness of LLMs.

We present new results to model and understand the role of encoder-decoder design in machine learning (ML) from an information-theoretic angle. We use two main information concepts, information sufficiency (IS) and mutual information loss (MIL), to represent predictive structures in machine learning. Our first main result provides a functional expression that characterizes the class of probabilistic models consistent with an IS encoder-decoder latent predictive structure. This result formally justifies the encoder-decoder forward stages many modern ML architectures adopt to learn latent (compressed) representations for classification. To illustrate IS as a realistic and relevant model assumption, we revisit some known ML concepts and present some interesting new examples: invariant, robust, sparse, and digital models. Furthermore, our IS characterization allows us to tackle the fundamental question of how much performance (predictive expressiveness) could be lost, using the cross entropy risk, when a given encoder-decoder architecture is adopted in a learning setting. Here, our second main result shows that a mutual information loss quantifies the lack of expressiveness attributed to the choice of a (biased) encoder-decoder ML design. Finally, we address the problem of universal cross-entropy learning with an encoder-decoder design where necessary and sufficiency conditions are established to meet this requirement. In all these results, Shannon's information measures offer new interpretations and explanations for representation learning.

Adapting to the changing climate requires accurate local climate information, a computationally challenging problem. Recent studies have used Generative Adversarial Networks (GANs), a type of deep learning, to learn complex distributions and downscale climate variables efficiently. Capturing variability while downscaling is crucial for estimating uncertainty and characterising extreme events - critical information for climate adaptation. Since downscaling is an undetermined problem, many fine-scale states are physically consistent with the coarse-resolution state. To quantify this ill-posed problem, downscaling techniques should be stochastic, able to sample realisations from a high-resolution distribution conditioned on low-resolution input. Previous stochastic downscaling attempts have found substantial underdispersion, with models failing to represent the full distribution. We propose approaches to improve the stochastic calibration of GANs in three ways: a) injecting noise inside the network, b) adjusting the training process to explicitly account for the stochasticity, and c) using a probabilistic loss metric. We tested our models first on a synthetic dataset with known distributional properties, and then on a realistic downscaling scenario, predicting high-resolution wind components from low-resolution climate covariates. Injecting noise, on its own, substantially improved the quality of conditional and full distributions in tests with synthetic data, but performed less well for wind field downscaling, where models remained underdispersed. For wind downscaling, we found that adjusting the training method and including the probabilistic loss improved calibration. The best model, with all three changes, showed much improved skill at capturing the full variability of the high-resolution distribution and thus at characterising extremes.

Non-negative matrix factorization with the generalized Kullback-Leibler divergence (NMF) and latent Dirichlet allocation (LDA) are two popular approaches for dimensionality reduction of non-negative data. Here, we show that NMF with $\ell_1$ normalization constraints on the columns of both matrices of the decomposition and a Dirichlet prior on the columns of one matrix is equivalent to LDA. To show this, we demonstrate that explicitly accounting for the scaling ambiguity of NMF by adding $\ell_1$ normalization constraints to the optimization problem allows a joint update of both matrices in the widely used multiplicative updates (MU) algorithm. When both of the matrices are normalized, the joint MU algorithm leads to probabilistic latent semantic analysis (PLSA), which is LDA without a Dirichlet prior. Our approach of deriving joint updates for NMF also reveals that a Lasso penalty on one matrix together with an $\ell_1$ normalization constraint on the other matrix is insufficient to induce any sparsity.

This paper introduced a clustered estimator of the Network Information Criterion (NICc) to approximate leave-one-cluster-out cross-validated deviance, which can be used as an alternative to cluster-based cross-validation when modeling clustered data. Stone proved that Akaike Information Criterion (AIC) is an asymptotic equivalence to leave-one-observation-out cross-validation if the parametric model is true. Ripley pointed out that the Network Information Criterion (NIC) derived in Stone's proof, is a better approximation to leave-one-observation-out cross-validation when the model is not true. For clustered data, we derived a clustered estimator of NIC, referred to as NICc, by substituting the Fisher information matrix in NIC with its estimator that adjusts for clustering. This adjustment imposes a larger penalty in NICc than the unclustered estimator of NIC when modeling clustered data, thereby preventing overfitting more effectively. In a simulation study and an empirical example, we used linear and logistic regression to model clustered data with Gaussian or binomial response, respectively. We showed that NICc is a better approximation to leave-one-cluster-out deviance and prevents overfitting more effectively than AIC and Bayesian Information Criterion (BIC). NICc leads to more accurate model selection, as determined by cluster-based cross-validation, compared to AIC and BIC.

In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the predictive model. Although performativity is generally problematic because it manifests as distribution shifts, we develop algorithmic fairness practices that leverage performativity to achieve stronger group fairness guarantees in social classification problems (compared to what is achievable in non-performative settings). In particular, we leverage the policymaker's ability to steer the population to remedy inequities in the long term. A crucial benefit of this approach is that it is possible to resolve the incompatibilities between conflicting group fairness definitions.

Humans have an innate drive to seek out causality. Whether fuelled by curiosity or specific goals, we constantly question why things happen, how they are interconnected, and many other related phenomena. To develop AI agents capable of addressing this natural human quest for causality, we urgently need a comprehensive dataset of natural causal questions. Unfortunately, existing datasets either contain only artificially-crafted questions that do not reflect real AI usage scenarios or have limited coverage of questions from specific sources. To address this gap, we present CausalQuest, a dataset of 13,500 naturally occurring questions sourced from social networks, search engines, and AI assistants. We formalize the definition of causal questions and establish a taxonomy for finer-grained classification. Through a combined effort of human annotators and large language models (LLMs), we carefully label the dataset. We find that 42% of the questions humans ask are indeed causal, with the majority seeking to understand the causes behind given effects. Using this dataset, we train efficient classifiers (up to 2.85B parameters) for the binary task of identifying causal questions, achieving high performance with F1 scores of up to 0.877. We conclude with a rich set of future research directions that can build upon our data and models.

Red Arrows pay tribute to Spitfire crash pilot 2 hours agoEleanor Maslin,BBC NewsShareMODSqn Ldr Mark Long was described as a "passionate aviator" in a tribute by the RAF The Red Arrows have shared their "heartfelt condolences" after the death of a pilot when his Spitfire crashed into a Lincolnshire field. Emergency crews were called shortly before 13:20 BST on 25 May to the site near RAF Coningsby where Sqn Ldr Mark Long crashed. Red Arrows team leader Sqn Ldr Jon Bond said he and fellow pilots were supporting Sqn Ldr Long's family "as much as we can". The display team is getting ready to start its 60th anniversary season after returning from winter training in Greece on Saturday.Sqn Ldr Jon Bond said "things can change quickly" when flying The RAF said a "comprehensive investigation" was now under way to determine the cause of the Spitfire crash. Speaking to BBC Radio Lincolnshire, Sqn Ldr Bond said: "Awful news to come back to on Saturday. "Our absolute heartfelt condolences go to Mark's family, all at the BBMF (Battle of Britain Memorial Flight) and all at RAF Coningsby.