SCHA-VAE generates novel data from limited examples using hierarchical context aggregation.
problem Generating data from a novel distribution with limited examples.
method Hierarchical context aggregation with attention-based point to set-level aggregation.
result Hierarchical approach better captures intrinsic variability in small data.
The paper introduces a tensor-based approach to improve neural models' aggregation of structural context.
problem Sub-optimal use of simple aggregation functions in neural models for structured data.
method Tensor-based formulation and Tucker tensor decomposition to control parameter space size.
result Effective regulation of trade-off between expressivity, computational complexity, and generalisation.
We introduce a new recursive aggregation procedure called Bernstein Online Aggregation (BOA). The exponential weights include an accuracy term and a second order term that is a proxy of the quadratic variation as in Hazan and Kale (2010). This second term stabilizes the procedure that is optimal in different senses. We…
Global Planar Convolution boosts brain tumor segmentation by enhancing context perception.
problem Improving context perception in brain tumor segmentation networks.
method Introduced Global Planar Convolution module to enhance context aggregation in brain tumor segmentation.
result Global Planar Convolution eliminates the need for multiple representation levels in segmentation networks.
New framework handles dynamic contexts in reinforcement learning.
problem Learning in environments where contexts change over time.
method Dynamic Contextual Markov Decision Processes (DCMDPs) with logistic aggregation.
result Upper-confidence-bound style algorithm with regret bounds.
Paper analyzes sparse aggregation in GLMs with Kullback-Leibler risk bounds.
problem Sparse aggregation in GLMs for parameter approximation.
method Exponential weighted aggregation scheme with Kullback-Leibler risk bounds.
result Sharp oracle inequality for Kullback-Leibler risk with leading constant 1 and minimax-optimal rate of aggregation.
The paper uses tensor decompositions to improve neural network models for tree data.
problem Encoding structural knowledge from tree-structured data efficiently.
method Introduces new aggregation functions using Canonical and Tensor-Train decompositions.
result Proposed models outperform traditional methods on tree classification tasks.
Simpler model outperforms state-of-the-art for disaggregating census data.
problem Disaggregating detailed census data into finer-grained, high-resolution mappings.
method Aggregate learning approach using ancillary data for an interpretable model.
result Simple model outperforms state-of-the-art on disaggregation metrics.
The paper examines how small positive dependence can lead to correlated tail risks.
problem Understanding the impact of dependence uncertainty on tail risk measures.
method Introducing a regular dependence measure and analyzing the aggregation of risks.
result Small positive dependence can result in perfectly correlated tail risks.
New algorithm predicts piecewise regular functions online.
problem Online prediction of piecewise regular functions.
method Modified sleeping experts aggregation algorithm.
result Oracle risk bounds for all local regions.
We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions. Our games map the input context to outcomes by first condensing the input into private player types that specify the utilities, weighted interactions…
PNA improves GNNs for graph data with multiple aggregators.
problem Capturing continuous features in graph neural networks.
method Combines multiple aggregators with degree-scalers.
result PNA outperforms existing models on graph theory and real-world tasks.
Paper tightens statistical aggregation results using local complexity.
problem Combining predictors to achieve nearly optimal predictions.
method Replacing global complexity with local complexity, using PAC-Bayes localization.
result Localized versions of classical aggregation bounds proven, improving previous results.
This paper improves federated learning efficiency by auto-tuning secure aggregation parameters.
problem Efficient communication in federated learning with quantized updates.
method Auto-tuning secure aggregation parameters based on random rotation properties.
result Improved communication efficiency in federated learning with secure aggregation.
Identifying context-specific entity networks from aggregated data is an important task, arising often in bioinformatics and neuroimaging. Computationally, this task can be formulated as jointly estimating multiple different, but related, sparse Undirected Graphical Models (UGM) from aggregated samples across several co…
New method accounts for hidden context in preference learning for RLHF models.
problem Incomplete data with hidden context affects RLHF model outcomes.
method Distributional Preference Learning (DPL) methods estimate hidden context distributions.
result DPL methods reduce RLHF vulnerabilities by accounting for hidden context.
U-aggregation combines multiple models without labels for better risk prediction.
problem Challenges in selecting best model for new populations due to limited data and lack of true labels.
method U-aggregation, an unsupervised model aggregation method that integrates pre-trained models without observed labels.
result U-aggregation improves genetic risk prediction of complex traits using publicly available models.
Data aggregation improves HAC for resource-constrained systems.
problem Resource constraints in embedded systems limit HAC's applicability.
method Data aggregation with BETULA algorithm reduces memory and runtime requirements.
result HAC can be applied to large datasets on resource-constrained systems.
Study introduces a new method for multiple parameter regularization in polynomial functional regression.
problem Handling varying regularization parameters in polynomial functional regression.
method Developed a theoretically grounded algorithm for multiple parameter regularization and model aggregation.
result Promising results from evaluations on synthetic and real-world data.
Method learns dynamics from aggregate data without full trajectories.
problem Learning nonlinear dynamics from aggregate data where individual trajectories are not available.
method Combines weak Fokker-Planck Equation description with Wasserstein GAN.
result Successfully learns nonlinear dynamics from aggregate data.
The paper develops a method for forecasting power consumption at various levels of aggregation.
problem Forecasting power consumption at different levels of household aggregation.
method Three-step process: feature generation, aggregation, and projection.
result The method provides theoretical guarantees on prediction error and performs well on real data.
WildWood improves Random Forest predictions using bootstrap out-of-bag samples.
problem Improving Random Forest predictions for supervised learning.
method Uses bootstrap out-of-bag samples to compute improved predictions by aggregating all possible subtrees with exponential weights.
result WildWood produces faster and more competitive predictions compared to other ensemble methods.
Label aggregation makes learning robust to noisy labels.
problem Learning from noisy labels.
method Label aggregation and risk consistency.
result Aggregated labels lead to stronger consistency guarantees.
In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the ℓ1 norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…
AMF is an online random forest algorithm for regression tasks.
problem Online learning for regression tasks with limited data.
method Mondrian Forests combined with Context Tree Weighting for efficient aggregation.
result AMF achieves competitive performance with optimal pruning, suitable for unknown function regularity.
Study tail risk aggregation under dependence uncertainty.
problem Risk aggregation under dependence uncertainty and hidden dependence.
method Introduce hidden dependence, show compatibility with small perturbations, quantify portfolio risk.
result Small deviations in dependence structure can lead to significant risk underestimation.
Improved meta-learning for dynamics using additional structured knowledge.
problem Meta-learning for dynamics with limited raw observations.
method Extended Neural ODE Process model to use privileged information.
result Improved accuracy and calibration on simulated dynamics tasks.
A variety of machine learning models have been proposed to assess the performance of players in professional sports. However, they have only a limited ability to model how player performance depends on the game context. This paper proposes a new approach to capturing game context: we apply Deep Reinforcement Learning (…
This work falls within the context of predicting the value of a real function at some input locations given a limited number of observations of this function. The Kriging interpolation technique (or Gaussian process regression) is often considered to tackle such a problem but the method suffers from its computational b…
In many contexts, we have access to aggregate data, but individual level data is unavailable. For example, medical studies sometimes report only aggregate statistics about disease prevalence because of privacy concerns. Even so, many a time it is desirable, and in fact could be necessary to infer individual level chara…
Study uses echo-sounder buoys to analyze tuna schools' association with dFADs globally.
problem Understanding temporal trends of tuna schools' association to drifting objects.
method Applied Machine Learning to examine binary and regression outputs of tuna schools' colonization and disaggregation times.
result Median colonization and disaggregation times varied by ocean, with Pacific having longest soak and colonization times.
Study optimal stopping for group with diverse discount rates using an attitude function.
problem Optimal stopping for a group with diverse discount rates under an aggregation preference.
method Develop iterative approach using consistent planning for time-consistent equilibria.
result Characterize all time-consistent mild equilibria as fixed points of an operator.
Inferring the correct answers to binary tasks based on multiple noisy answers in an unsupervised manner has emerged as the canonical question for micro-task crowdsourcing or more generally aggregating opinions. In graphon estimation, one is interested in estimating edge intensities or probabilities between nodes using …
Enhances neural processes for better context handling.
problem Real-world context sets are complex, requiring richer prior distributions.
method Introduces a graphical model for a richer prior on latent variables, enabling end-to-end optimization.
result Improves function modeling and test-time robustness with mixture and Student-t assumptions.
Research explores how interconnected systems synchronize and how to control their behavior.
problem Understanding and controlling the behavior of interconnected dynamical systems.
method Mean field games approach applied to controlled coupled oscillators.
result Developed methods to predict and influence emergent phenomena in interconnected systems.
Context-aware CNN improves cancer grading accuracy.
problem Grading colorectal cancer histology images accurately.
method Proposes a context-aware neural network for 1,792x1,792 pixel images.
result Outperforms traditional methods by 3.61%.
We propose scalable methods to execute counting queries in machine learning applications. To achieve memory and computational efficiency, we abstract counting queries and their context such that the counts can be aggregated as a stream. We demonstrate performance and scalability of the resulting approach on random quer…
A simple guide to understanding hierarchical causality in complex systems.
problem Understanding hierarchical causality in complex systems.
method Formalizing hierarchical causality in terms of actors and agents, with three key structures.
result The system requires three additional structures: causation classes, aggregation operators, and discrete event-time maps.
A new method sorts projects using Quicksort and Bradley-Terry model for uncertain long-term benefits.
problem Selecting projects with uncertain long-term benefits.
method Combining Quicksort and Bradley-Terry model for ranking projects based on uncertain long-term benefits.
result Proposed methods outperform existing aggregation methods and can be combined with sampling techniques.
Two approaches integrate qualitative views into portfolio optimization, showing aggregation methods outperform robust optimization.
problem Incorporating qualitative views into portfolio optimization models.
method Robust optimization and order aggregation methods.
result Aggregation methods outperform robust optimization in portfolio performance analysis.
We consider settings in which the distribution of a multivariate random variable is partly ambiguous. We assume the ambiguity lies on the level of the dependence structure, and that the marginal distributions are known. Furthermore, a current best guess for the distribution, called reference measure, is available. We w…
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an extreme diversity space, such as \textit{person-behind-person} and \textit{car-behind…
AdaCAD improves semi-supervised classification by focusing on intra-class nodes.
problem Improving semi-supervised classification by addressing inter-class connections in graphs.
method AdaCAD uses a class-attentive diffusion process to adaptively aggregate nodes based on their class similarity.
result AdaCAD significantly outperforms state-of-the-art methods in semi-supervised classification.
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
Study market efficiency under partial information using SDEs and optimization.
problem Market efficiency under partial information constraints.
method McKean-Vlasov-type SDEs, Wasserstein barycenters, KL divergence, convex optimization, optimal control, nonlinear filtering.
result Convergence of reduced-information market price processes to true price process under increasing information flow.
We demystify attention patterns in multi-head softmax models for linear data.
problem Understanding the training dynamics and emergent patterns in multi-head softmax attention models.
method Extensive empirical experiments and rigorous theoretical analysis.
result Multi-head softmax attention models approximate a debiased gradient descent predictor, outperforming single-head attention and achieving near-Bayesian optimality.
For massive data sets, efficient computation commonly relies on distributed algorithms that store and process subsets of the data on different machines, minimizing communication costs. Our focus is on regression and classification problems involving many features. A variety of distributed algorithms have been proposed …
Improved non-intrusive load monitoring with a novel neural network.
problem Accurately disaggregating household electricity consumption without dedicated meters.
method Developed a scale- and context-aware network with multi-scale features and contextual information.
result Significantly improved accuracy compared to state-of-the-art methods.