SIMULE learns multiple sparse UGMs from aggregated data, identifying context-specific and shared interactions.
problem Jointly estimating multiple sparse UGMs from aggregated samples across different contexts.
method Constrained L1 minimization approach for multi-UGM learning.
result SIMULE achieves consistent results at rate O(log(Kp)/n_{tot}) and significantly improves over state-of-the-art methods.
Most real life systems have a random component: the multitude of endogenous and exogenous factors influencing them result in stochastic fluctuations of the parameters determining their dynamics. These empirical systems are in many cases subject to noise of multiplicative nature. The special properties of multiplicative…
MCPCA analyzes shared factors across multiple data contexts.
problem No tools to recover shared factors across multiple contexts.
method Developed a theoretical and algorithmic framework (MCPCA).
result Reveals shared axes of variation across subsets of contexts.
JCI unifies causal discovery from multiple contexts.
problem Discover causal relations from observational data.
method Unified causal modeling framework for multiple contexts.
result JCI implementations outperform state-of-the-art algorithms.
Enhances image captioning with novel context combination methods.
problem Improving machine learning for image captioning with structured learning and meaningful interpretation.
method Combines Feature Distribution Composition (FDC), Multiple Role Representation Crossover (MRRC) attention layers, and language decoder.
result Significantly improved image captioning performance (35.3%) and established new standards.
New RNN model fuses sensor data from multiple stations.
problem Modeling distributed sensor networks for future behavior prediction.
method Multi-Encoder-Decoder RNN architecture with attention mechanism.
result Model improves prediction accuracy on real-world sensor datasets.
GOAT learns multiple node representations from graph structure alone.
problem Context-free graph representation learning limits model performance.
method Inspired by gossip and mutual attention, GOAT learns multiple node representations.
result GOAT outperforms 12 SOTA baselines on link prediction and clustering tasks.
Word2vec improved but lacks multi-meaning words; ConEc creates new embeddings.
problem Lack of meaningful embeddings for words with multiple meanings and OOV words.
method Context encoders (ConEc) extend word2vec by multiplying embeddings with context vectors.
result ConEc creates embeddings for OOV words and words with multiple meanings based on local contexts.
Modeling long-range context for multi-function utterances in dialogues.
problem Complex dependencies across dialogue turns in long utterances.
method Adapted Convolutional Recurrent Neural Network (CRNN) to model interactions between utterances.
result Significantly outperforms existing work on CDA recognition on a tech forum dataset.
Algorithm identifies Pareto front using multiple context directions and reuses exploration samples.
problem Identifying a set of arms with undominated mean reward vectors in linear bandits.
method Proposes a new estimator that updates estimates along multiple context directions and reuses exploration samples.
result Optimal sample complexity and logarithmic regret compared to optimal algorithms.
A neural network learns word-referent associations across various contexts.
problem Learning word-referent associations in different contexts.
method A biologically inspired multi-layered architecture that takes images and phonemes as input, builds representations, and adjusts prototypes based on current context.
result The model achieves up to 78% accuracy in ambiguous situations and mimics human learning patterns.
CausalRegNet generates accurate data for gene perturbation experiments, improving CSL methods.
problem Assessing and selecting causal structure learning methods in gene perturbation experiments.
method CausalRegNet, a multiplicative effect structural causal model, generates accurate observational and interventional data.
result CausalRegNet generates more accurate distributions and scales better than current simulation frameworks.
RACDNN improves saliency detection by iteratively refining attention to multiple scales.
problem Saliency detection struggles with objects of varying scales.
method Recurrent attentional convolutional-deconvolution network (RACDNN) using spatial transformer and recurrent units.
result RACDNN outperforms state-of-the-art methods on saliency detection datasets.
Maximizes mutual info across views for better image representations.
problem Improving image representation learning through multiple views.
method Maximizing mutual information between features from multiple views.
result ImageNet accuracy of 68.1% using linear evaluation, significantly outperforming prior methods.
MEDL_CVAE learns complex correlations among multiple entities using rich context.
problem Learning complex correlations among multiple entities with rich context.
method Conditional Variational Auto-Encoder (CVAE) for encoding conditional multivariate distributions.
result MEDL_CVAE captures rich dependency structures and improves joint likelihood.
Persona2vec learns multiple node roles in graphs.
problem Graphs often have nodes with multiple overlapping roles.
method Persona2vec learns multiple node representations based on structural contexts.
result Persona2vec outperforms state-of-the-art models in link prediction.
Positive definite operator-valued kernels generalize the well-known notion of reproducing kernels, and are naturally adapted to multi-output learning situations. This paper addresses the problem of learning a finite linear combination of infinite-dimensional operator-valued kernels which are suitable for extending func…
We present a Bayesian nonparametric framework for multilevel clustering which utilizes group-level context information to simultaneously discover low-dimensional structures of the group contents and partitions groups into clusters. Using the Dirichlet process as the building block, our model constructs a product base-m…
Proves a generalization of a multiplicity one theorem for specific groups.
problem Generalizing a multiplicity one theorem for spherical representations.
method Analyzes τ n τ_n τ n -spherical representations of G = S O ( 2 , 1 ) ∘ G = SO(2,1)^\circ G = S O ( 2 , 1 ) ∘ . result Proves an analogue of the strong multiplicity one theorem.
Monte-Carlo sampling improves histological image classification accuracy.
problem Histological image classification accuracy.
method Sequential Monte-Carlo method for patch sampling.
result Higher generalization performance compared to grid and uniform sampling.
Extends Manin triples to Lie bialgebroids over Lie groupoids.
problem Characterizing Lie bialgebroids via Manin triples.
method Establishing correspondence between Lie bialgebroid groupoids and multiplicative Manin triples.
result New viewpoint on co-quadratic Lie algebroids and Manin triple description of Lie bialgebroid crossed modules.
We present a proof of the Riemannian Penrose inequality with charge in the context of asymptotically flat initial data sets for the Einstein-Maxwell equations, having possibly multiple black holes with no charged matter outside the horizon, and satisfying the relevant dominant energy condition. The proof is based on a …
Enhances neural processes to learn from multiple related datasets.
problem Improving predictions from datasets with shared similarities.
method Developed the in-context in-context learning pseudo-token TNP (ICICL-TNP) to condition on both sets of datapoints and sets of datasets.
result Demonstrated the importance and effectiveness of in-context in-context learning.
Paper develops methods to fairly measure contributions in federated learning.
problem Fairly allocate credits for participants in federated learning.
method Uses deletion method for horizontal FML and Shapley Values for vertical FML.
result Developed techniques to calculate contributions in federated learning.
We reformulate notions from the theory of quasi-Poisson g-manifolds in terms of graded Poisson geometry and graded Poisson-Lie groups and prove that quasi-Poisson g-manifolds integrate to quasi-Hamiltonian g-groupoids. We then interpret this result within the theory of Dirac morphisms and multiplicative Manin pairs, to…
Improves NMT by sampling context from predicted sequence during training.
problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.
LLMs generate answers under incomplete context, and their uncertainty should scale with missing information.
problem Evaluating the quality of LLM answers under incomplete context.
method A controlled framework with varying context availability, and two uncertainty measures (sampling-based confidence and response entropy) evaluated on SQuAD.
result Response entropy increases with context removal and explains more variance in accuracy than confidence, suggesting it is a more responsive uncertainty measure.
Paper learns identity-sensitive word embeddings from text corpora.
problem Lack of context-aware word embeddings.
method Constructs a heterogeneous network of words and identities, then embeds into a low-dimensional space.
result Identity-sensitive word embeddings capture different meanings of words.
asp2vec learns dynamic node aspect distributions for better network embedding.
problem Lack of multi-aspect node representations in network embedding.
method Dynamic aspect assignment via Gumbel-Softmax and aspect regularization.
result Improved network embedding quality through dynamic aspect modeling.
In this work, we consider Corporate Governance (CG) ties among companies from a multiple network perspective. Such a structure naturally arises from the close interrelation between the Shareholding Network (SH) and the Board of Directors network (BD). In order to capture the simultaneous effects of both networks on CG,…
Reinforcement Learning improves personalized dialogue systems.
problem Personalized dialogue systems that generalize across users.
method Two RL-based approaches: single learner with user context features, and learner per context segmentation.
result RL methods outperform handcrafted systems in financial product recommendation.
Proposes a topological framework to study modular invariants and related concepts.
problem Exploring modular invariants and related concepts in topological quantum field theory.
method Topological paradigm in alterfold topological quantum field theory.
result Establishes a novel integral identity for modular invariance across multiple Morita contexts.
Optimal algorithm for contextual bandits with unknown context distributions.
problem Designing efficient algorithms for contextual bandits with unknown context distributions.
method Cross-learning setting, novel technique for coordinating multiple epochs.
result Nearly tight regret bound of O ~ ( T K ) \widetilde{O}(\sqrt{TK}) O ( T K ) for learning to bid in first-price auctions and sleeping bandits. Analyzes how word meaning is captured by co-occurrence features.
problem Understanding the theoretical basis of word representation by co-occurrences.
method Theoretical analysis of word representation methods using co-occurrences.
result Using multiple context features improves word prediction scores.
InstaGAN tackles image-to-image translation for images with multiple instances and significant shape changes.
problem Challenging cases, especially images with multiple target instances and significant shape changes.
method Instance-aware GAN (InstaGAN) that incorporates instance information and context preserving loss.
result Improves multi-instance transfiguration while maintaining permutation invariance of instances.
LLMs perform well in financial sentiment analysis without fine-tuning.
problem Challenges in financial terminology, emotions, and ambiguous expressions.
method In-context learning methods for financial document-sentiment pairs.
result LLMs can generalize in-context demonstrations to new financial documents.
Simple greedy algorithms can excel in multi-objective bandits with multiple good arms.
problem Optimizing multiple objectives in bandits is traditionally harder.
method Introduced greedy algorithms that exploit multiple good arms for multiple objectives.
result Simple greedy algorithms achieve strong performance in multi-objective bandits.
The study finds multiple closed Reeb orbits on specific contact forms.
problem Finding geometrically distinct closed Reeb orbits on prequantization bundles.
method Analyzes contact forms on prequantization bundles with specific index requirements.
result Establishes multiplicity results for closed Reeb orbits under certain conditions.
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.
CoDA adapts dynamics models to new physical systems by conditioning on context.
problem Generalizing to new physical systems with shared dynamics but different contexts.
method Context-informed dynamics adaptation (CoDA) using multiple environments and a hypernetwork.
result State-of-the-art generalization results on nonlinear dynamics.
DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.
problem Pathologies in standard policy gradients, leading to poor updates and over-allocation of gradient budget.
method Introduces Delightful Policy Gradient (DG) that gates each term with a sigmoid of advantage and surprisal.
result DG provably improves directional accuracy in a single context and shifts the expected gradient closer to the oracle across multiple contexts.
Multi-head attention outperforms single-head in in-context linear regression tasks.
problem Comparing performance of transformer with single-/multi-head attention in in-context learning.
method Theoretical analysis of performance of transformers with different attention mechanisms in linear regression tasks.
result Multi-head attention with a substantial embedding dimension outperforms single-head attention in in-context linear regression tasks.
Symmetries of bundle gerbes modeled using multiplicative vector fields.
problem Infinitesimal symmetries of bundle gerbes.
method Modeling symmetries with multiplicative vector fields on Lie groupoids.
result Connection-preserving multiplicative vector fields inherit a Lie 2-algebra structure.
Optimal model selection for forecasting large collections of short time series using latent space.
problem Challenges in choosing among multiple forecasting methods for large, high-dimensional time series with limited data.
method Combining low-rank temporal matrix factorization with optimal model selection using cross-validation.
result Forecasting latent factors leads to significant performance gains compared to direct uni-variate model application.
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.
New Lie 2-algebra structure for multiplicative forms on quasi-Poisson groupoids.
problem Understanding Lie 2-algebra structures on geometric stacks.
method Construction of graded weak Lie 2-algebras from multiplicative forms and differential forms.
result Established a morphism between Lie 2-algebras and weak Lie 2-algebras of multiplicative forms.
Max-rank improves multiple testing in conformal prediction.
problem Simultaneous testing of multiple hypotheses in scientific inquiries.
method Introduces max-rank, a novel correction for positive dependencies in simultaneous testing.
result Max-rank efficiently controls family-wise error rate and improves predictive uncertainty estimates.
Predicting emotional state from narratives using contextual information.
problem Predicting valence from personal narratives using contextual information.
method Investigated multiple machine learning techniques to model narratives, focusing on textual information.
result Models capture inter-individual differences, leading to more accurate predictions of emotional state.