Natural gradient descent has a remarkable property that in the small learning rate limit, it displays an invariance with respect to network reparameterizations, leading to robust training behavior even for highly covariant network parameterizations. We show that optimization algorithms with this property can be viewed as discrete approximations of natural transformations from the functor determining an optimizer's state space from the diffeomorphism group if its configuration manifold, to the functor determining that state space's tangent bundle from this group. Algorithms with this property enjoy greater efficiency when used to train poorly parameterized networks, as the network evolution they generate is approximately invariant to network reparameterizations. More specifically, the flow generated by these algorithms in the limit as the learning rate vanishes is invariant under smooth reparameterizations, the respective flows of the parameters being determined by equivariant maps. By casting this property a natural transformation, we allow for generalizations beyond equivariance with respect to group actions; this framework can account for non-invertible maps such as projections, creating a framework for the direct comparison of training behavior across non-isomorphic network architectures, and the formal examination of limiting behavior as network size increases by considering inverse limits of these projections, should they exist. We introduce a simple method of introducing this naturality more generally and examine a number of popular machine learning training algorithms, finding that most are unnatural.

What do Taylor Swift, Andrew Tate and Robert Oppenheimer all have in common? They were the most searched articles on Wikipedia this year. The platform shared a fascinating report revealing the topics most interested people in English-speaking countries. Collectively, we racked up more than 84 billion views on Wikipedia this year. The site's page for ChatGPT was the top article, with more than 49 million views, following its breakout year that sparked curiosity and concern worldwide. Curiosity and concern also played a part in the second most viewed Wikipedia article of the year: 'Deaths in 2023' ' which HAD over 42 million views.

Intent-aware session recommendation (ISR) is pivotal in discerning user intents within sessions for precise predictions. Traditional approaches, however, face limitations due to their presumption of a uniform number of intents across all sessions. This assumption overlooks the dynamic nature of user sessions, where the number and type of intentions can significantly vary. In addition, these methods typically operate in latent spaces, thus hinder the model's transparency.Addressing these challenges, we introduce a novel ISR approach, utilizing the advanced reasoning capabilities of large language models (LLMs). First, this approach begins by generating an initial prompt that guides LLMs to predict the next item in a session, based on the varied intents manifested in user sessions. Then, to refine this process, we introduce an innovative prompt optimization mechanism that iteratively self-reflects and adjusts prompts. Furthermore, our prompt selection module, built upon the LLMs' broad adaptability, swiftly selects the most optimized prompts across diverse domains. This new paradigm empowers LLMs to discern diverse user intents at a semantic level, leading to more accurate and interpretable session recommendations. Our extensive experiments on three real-world datasets demonstrate the effectiveness of our method, marking a significant advancement in ISR systems.

The healthcare industry generates enormous amounts of complex clinical data that make the prediction of disease detection a complicated process. In medical informatics, making effective and efficient decisions is very important. Data Mining (DM) techniques are mainly used to identify and extract hidden patterns and interesting knowledge to diagnose and predict diseases in medical datasets. Nowadays, heart disease is considered one of the most important problems in the healthcare field. Therefore, early diagnosis leads to a reduction in deaths. DM techniques have proven highly effective for predicting and diagnosing heart diseases. This work utilizes the classification algorithms with a medical dataset of heart disease; namely, J48, Random Forest, and Na\"ive Bayes to discover the accuracy of their performance. We also examine the impact of the feature selection method. A comparative and analysis study was performed to determine the best technique using Waikato Environment for Knowledge Analysis (Weka) software, version 3.8.6. The performance of the utilized algorithms was evaluated using standard metrics such as accuracy, sensitivity and specificity. The importance of using classification techniques for heart disease diagnosis has been highlighted. We also reduced the number of attributes in the dataset, which showed a significant improvement in prediction accuracy. The results indicate that the best algorithm for predicting heart disease was Random Forest with an accuracy of 99.24%.

Most Simultaneous localisation and mapping (SLAM) systems have traditionally assumed a static world, which does not align with real-world scenarios. To enable robots to safely navigate and plan in dynamic environments, it is essential to employ representations capable of handling moving objects. Dynamic SLAM is an emerging field in SLAM research as it improves the overall system accuracy while providing additional estimation of object motions. State-of-the-art literature informs two main formulations for Dynamic SLAM, representing dynamic object points in either the world or object coordinate frame. While expressing object points in a local reference frame may seem intuitive, it may not necessarily lead to the most accurate and robust solutions. This paper conducts and presents a thorough analysis of various Dynamic SLAM formulations, identifying the best approach to address the problem. To this end, we introduce a front-end agnostic framework using GTSAM that can be used to evaluate various Dynamic SLAM formulations.

Graph Neural Networks (GNN) have recently gained popularity in the forecasting domain due to their ability to model complex spatial and temporal patterns in tasks such as traffic forecasting and region-based demand forecasting. Most of these methods require a predefined graph as input, whereas in real-life multivariate time series problems, a well-predefined dependency graph rarely exists. This requirement makes it harder for GNNs to be utilised widely for multivariate forecasting problems in other domains such as retail or energy. In this paper, we propose a hybrid approach combining neural networks and statistical structure learning models to self-learn the dependencies and construct a dynamically changing dependency graph from multivariate data aiming to enable the use of GNNs for multivariate forecasting even when a well-defined graph does not exist. The statistical structure modeling in conjunction with neural networks provides a well-principled and efficient approach by bringing in causal semantics to determine dependencies among the series. Finally, we demonstrate significantly improved performance using our proposed approach on real-world benchmark datasets without a pre-defined dependency graph.

Zipf (1935) posited that wordforms are optimized to minimize utterances' communicative costs. Under the assumption that cost is given by an utterance's length, he supported this claim by showing that words' lengths are inversely correlated with their frequencies. Communicative cost, however, can be operationalized in different ways. Piantadosi et al. (2011) claim that cost should be measured as the distance between an utterance's information rate and channel capacity, which we dub the channel capacity hypothesis (CCH) here. Following this logic, they then proposed that a word's length should be proportional to the expected value of its surprisal (negative log-probability in context). In this work, we show that Piantadosi et al.'s derivation does not minimize CCH's cost, but rather a lower bound, which we term CCH-lower. We propose a novel derivation, suggesting an improved way to minimize CCH's cost. Under this method, we find that a language's word lengths should instead be proportional to the surprisal's expectation plus its variance-to-mean ratio. Experimentally, we compare these three communicative cost functions: Zipf's, CCH-lower , and CCH. Across 13 languages and several experimental settings, we find that length is better predicted by frequency than either of the other hypotheses. In fact, when surprisal's expectation, or expectation plus variance-to-mean ratio, is estimated using better language models, it leads to worse word length predictions. We take these results as evidence that Zipf's longstanding hypothesis holds.

Despite significant advancements in network-based image harmonization techniques, there still exists a domain disparity between typical training pairs and real-world composites encountered during inference. Most existing methods are trained to reverse global edits made on segmented image regions, which fail to accurately capture the lighting inconsistencies between the foreground and background found in composited images. In this work, we introduce a self-supervised illumination harmonization approach formulated in the intrinsic image domain. First, we estimate a simple global lighting model from mid-level vision representations to generate a rough shading for the foreground region. A network then refines this inferred shading to generate a harmonious re-shading that aligns with the background scene. In order to match the color appearance of the foreground and background, we utilize ideas from prior harmonization approaches to perform parameterized image edits in the albedo domain. To validate the effectiveness of our approach, we present results from challenging real-world composites and conduct a user study to objectively measure the enhanced realism achieved compared to state-of-the-art harmonization methods.

We present a framework for constraining the automatic sequential generation of equations to obey the rules of dimensional analysis by construction. Combining this approach with reinforcement learning, we built $\Phi$-SO, a Physical Symbolic Optimization method for recovering analytical functions from physical data leveraging units constraints. Our symbolic regression algorithm achieves state-of-the-art results in contexts in which variables and constants have known physical units, outperforming all other methods on SRBench's Feynman benchmark in the presence of noise (exceeding 0.1%) and showing resilience even in the presence of significant (10%) levels of noise.

Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications including environmental monitoring and crop-yield prediction. Satellite images are significantly different from natural images - they can be multi-spectral, irregularly sampled across time - and existing diffusion models trained on images from the Web do not support them. Furthermore, remote sensing data is inherently spatio-temporal, requiring conditional generation tasks not supported by traditional methods based on captions or images. In this paper, we present DiffusionSat, to date the largest generative foundation model trained on a collection of publicly available large, high-resolution remote sensing datasets. As text-based captions are sparsely available for satellite images, we incorporate the associated metadata such as geolocation as conditioning information. Our method produces realistic samples and can be used to solve multiple generative tasks including temporal generation, superresolution given multi-spectral inputs and in-painting. Our method outperforms previous state-of-the-art methods for satellite image generation and is the first large-scale generative foundation model for satellite imagery. Diffusion models have achieved state of the art results in image generation (Sohl-Dickstein et al., 2015; Ho et al., 2020; Dhariwal & Nichol, 2021; Kingma et al., 2021; Song & Ermon, 2019; 2020). Large scale models such as Stable Diffusion Rombach et al. (2022) (SD) have been trained on Internet-scale image-text datasets to generate high-resolution images from user-provided captions.