Hiererachical clustering, that is computing a recursive partitioning of a dataset to obtain clusters at increasingly finer granularity is a fundamental problem in data analysis. Although hierarchical clustering has mostly been studied through procedures such as linkage algorithms, or top-down heuristics, rather than as optimization problems, Dasgupta [9] recently proposed an objective function for hierarchical clustering and initiated a line of work developing algorithms that explicitly optimize an objective (see also [7, 22, 8]). In this paper, we consider a fairly general random graph model for hierarchical clustering, called the hierarchical stochastic block model (HSBM), and show that in certain regimes the SVD approach of McSherry [18] combined with specific linkage methods results in a clustering that give an Op1q approximation to Dasgupta's cost function. Finally, we report empirical evaluation on synthetic and real-world data showing that our proposed SVD-based method does indeed achieve a better cost than other widely-used heurstics and also results in a better classification accuracy when the underlying problem was that of multi-class classification.

Neural Information Processing Systems http://nips.cc/

Recently, linear formulations and convex optimization methods have been proposed to predict diffusion-weighted Magnetic Resonance Imaging (dMRI) data given estimates of brain connections generated using tractography algorithms. The size of the linear models comprising such methods grows with both dMRI data and connectome resolution, and can become very large when applied to modern data. In this paper, we introduce a method to encode dMRI signals and large connectomes, i.e., those that range from hundreds of thousands to millions of fascicles (bundles of neuronal axons), by using a sparse tensor decomposition. We show that this tensor decomposition accurately approximates the Linear Fascicle Evaluation (LiFE) model, one of the recently developed linear models.

Many online platforms act as intermediaries between a seller and a set of buyers. Examples of such settings include online retailers (such as Ebay) selling items on behalf of sellers to buyers, or advertising exchanges (such as AdX) selling pageviews on behalf of publishers to advertisers. In such settings, revenue sharing is a central part of running such a marketplace for the intermediary, and fixedpercentage revenue sharing schemes are often used to split the revenue among the platform and the sellers. In particular, such revenue sharing schemes require the platform to (i) take at most a constant fraction α of the revenue from auctions and (ii) pay the seller at least the seller declared opportunity cost c for each item sold. A straightforward way to satisfy the constraints is to set a reserve price at c/(1 α) for each item, but it is not the optimal solution on maximizing the profit of the intermediary.

We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the Johnson-Lindenstrauss transform and the angular kernel, we show that we can select matrices yielding guaranteed improved performance in accuracy and/or speed compared to earlier methods. We introduce matrices with complex entries which give significant further accuracy improvement. We provide geometric and Markov chain-based perspectives to help understand the benefits, and empirical results which suggest that the approach is helpful in a wider range of applications.

Neural Information Processing Systems http://nips.cc/

With climate change-related extreme events on the rise, high dimensional Earth observation data presents a unique opportunity for forecasting and understanding impacts on ecosystems. This is, however, impeded by the complexity of processing, visualizing, modeling, and explaining this data. To showcase how this challenge can be met, here we train a convolutional long short-term memory-based architecture on the novel DeepExtremeCubes dataset. DeepExtremeCubes includes around 40,000 long-term Sentinel-2 minicubes (January 2016-October 2022) worldwide, along with labeled extreme events, meteorological data, vegetation land cover, and topography map, sampled from locations affected by extreme climate events and surrounding areas. When predicting future reflectances and vegetation impacts through kernel normalized difference vegetation index, the model achieved an R$^2$ score of 0.9055 in the test set. Explainable artificial intelligence was used to analyze the model's predictions during the October 2020 Central South America compound heatwave and drought event. We chose the same area exactly one year before the event as counterfactual, finding that the average temperature and surface pressure are generally the best predictors under normal conditions. In contrast, minimum anomalies of evaporation and surface latent heat flux take the lead during the event. A change of regime is also observed in the attributions before the event, which might help assess how long the event was brewing before happening. The code to replicate all experiments and figures in this paper is publicly available at https://github.com/DeepExtremes/txyXAI

This paper presents a solution to the problem of optimal ground station selection for low-Earth orbiting (LEO) space missions that enables mission operators to precisely design their ground segment performance and costs. Space mission operators are increasingly turning to Ground-Station-as-a-Service (GSaaS) providers to supply the terrestrial communications segment to reduce costs and increase network size. However, this approach leads to a new challenge of selecting the optimal service providers and station locations for a given mission. We consider the problem of ground station selection as an optimization problem and present a general solution framework that allows mission designers to set their overall optimization objective and constrain key mission performance variables such as total data downlink, total mission cost, recurring operational cost, and maximum communications time-gap. We solve the problem using integer programming (IP). To address computational scaling challenges, we introduce a surrogate optimization approach where the optimal station selection is determined based on solving the problem over a reduced time domain. Two different IP formulations are evaluated using randomized selections of LEO satellites of varying constellation sizes. We consider the networks of the commercial GSaaS providers Atlas Space Operations, Amazon Web Services (AWS) Ground Station, Azure Orbital Ground Station, Kongsberg Satellite Services (KSAT), Leaf Space, and Viasat Real-Time Earth. We compare our results against standard operational practices of integrating with one or two primary ground station providers.

Recently, when dealing with high-resolution images, dominant LMMs usually divide them into multiple local images and one global image, which will lead to a large number of visual tokens. In this work, we introduce AVG-LLaVA, an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. This approach not only reduces the number of visual tokens and speeds up inference, but also improves the overall model performance. Specifically, we introduce the following modules based on LLaVA-NeXT: (a) a visual granularity scaler that includes multiple pooling layers to obtain visual tokens with different granularities; (b) a visual granularity router, which includes a Transformer layer, an MLP layer, and a voter layer, used to select the appropriate visual granularity based on the image and instruction. Furthermore, we propose RGLF, a novel training paradigm that aims at aligning the granularity predicted by the router with the preferences of the LMM, without the need for additional manually annotated data. Extensive experiments and analysis show that AVG-LLaVA achieves superior performance across 11 benchmarks, as well as significantly reduces the number of visual tokens and speeds up inference (e.g., an 85.3% reduction in visual tokens and a 2.53$\times$ increase in inference speed on the AI2D benchmark).