Countries rarely enter unrelated products, but those that do grow faster.
problem Understanding the benefits of entering unrelated products for economic growth.
method Identifying periods of unrelated product entry through analysis of 93 countries' exports from 1965 to 2014.
result Countries entering more unrelated products experience a small but significant increase in future economic growth.
Study shows volume and genus unrelated for hyperbolic fibred knots.
problem Volume and genus of hyperbolic fibred knots are unrelated.
method Analyzes hyperbolic fibred knots in three-sphere.
result Volume and genus are unrelated for hyperbolic fibred knots.
New product structures encode superintegrable Hamiltonian systems in Euclidean spaces.
problem Encoding superintegrable Hamiltonian systems using product structures.
method Introducing commutative and associative product structures on Euclidean spaces of dimension at least three, satisfying specific conditions.
result All abundant superintegrable Hamiltonian systems on Euclidean space of dimension at least three arise from these product structures.
Unified product embeddings improve cross-task performance in e-commerce.
problem Training product embeddings in isolation limits cross-task performance.
method Combining text, clickstream, and image data using denoising auto-encoders, BPR, and Siamese neural networks.
result Unified product embeddings uniformly outperform isolated embeddings across three e-commerce tasks.
Which song will Smith listen to next? Which restaurant will Alice go to tomorrow? Which product will John click next? These applications have in common the prediction of user trajectories that are in a constant state of flux over a hidden network (e.g. website links, geographic location). What users are doing now may b…
Study on fibered knots in 3-manifolds, proving unrelated volume and genus.
problem Unrelated volume and genus in hyperbolic fibered knots.
method Proof of unrelated volume and genus for hyperbolic fibered knots in 3-manifolds.
result Proved that volume and genus are unrelated for hyperbolic fibered knots.
New model improves inference on asset market durations.
problem Statistical artifacts in trade aggregation.
method Flexible stochastic duration model with uncertainty in related trades.
result Conditional hazard function varies less than previous studies.
Develops a contrastive framework for data-efficient multimodal learning.
problem Expensive training of multimodal generative models requiring related multimodal data.
method Contrastive framework for multimodal learning, distinguishing related from unrelated data.
result Data-efficient multimodal learning on challenging datasets for various VAE models.
Deep CNN detects mind wandering from EEG data.
problem Detecting mind wandering to reorient attention.
method Channel-wise deep convolutional neural network (CNN) model.
result 91.78% accuracy in detecting mind wandering.
Training on mixed distributions improves test performance even when components are unrelated.
problem Improving test performance with mismatched training and test distributions.
method Analyzing mixture distributions with different training and test proportions.
result Distribution shift can be beneficial, improving test performance even when components are unrelated.
Model compares news articles and videos using neural networks and machine-learned activation functions.
problem Comparing heterogeneous entities like news articles and videos.
method Artificial neural networks with trainable weighted structural components and machine-learned activation functions.
result Achieved up to 59.2% accuracy in matching videos to news articles.
In this paper we show that two seemingly unrelated problems in economics, the hypothesis of integrability and the hypothesis of additive separability are linked by the absence of curvature of connections on webs naturally associated with each problem.
Detects crime series using RBM embeddings from crime narratives.
problem Detecting related crime series from crime records.
method Unsupervised learning of latent feature embeddings using Gaussian-Bernoulli RBM.
result Related cases are closer in feature space, unrelated cases are far apart.
Quasi-orthonormal encoding reduces high dimensionality for categorical data.
problem High dimensionality and low sample size issues in categorical data encoding.
method Quasi-orthonormal encoding (QOE) for categorical data.
result QOE reduces dimensionality and improves machine learning performance.
We present an axiomatic modification of quaternionic quantum mechanics with a possible-worlds semantics capable of predicting essential "nonquantum" features of an observable universe model - the dimensionality and topology of spacetime, the existence, the signature and a specific form of a metric on it, and certain na…
Reviews six finance topics, including 'radical complexity'.
problem None explicitly stated, focuses on research directions.
method Informal review and discussion of open questions.
result No specific key result mentioned, focuses on research directions.
New method for rolling bodies on inclined planes, with applications to rescue operations.
problem Constructing solid bodies rolling along curves on inclined planes.
method Rigorous existence theorems and connections to maritime rescue operations.
result Comprehensive existence theorems for rolling bodies on inclined planes.
Hybrid BFP-FP improves DNN training accuracy with 8.5x higher throughput.
problem Limited dynamic range of fixed-point arithmetic for DNN training convergence.
method Introducing HBFP, a hybrid BFP-FP approach.
result HBFP matches floating point's accuracy while delivering up to 8.5x higher throughput.
TQFT signatures linked to trace fields of knots.
problem Relationship between TQFT signatures and knot trace fields.
method Analysis of Frobenius algebras and TQFTs at specific roots.
result TQFT signatures equal to trace fields of two-bridge knots.
Maximal metric spheres found, related to Sobolev-to-Lipschitz property.
problem Finding maximal metric spheres.
method Characterizing maximal spheres by Sobolev-to-Lipschitz property.
result Maximal spheres uniquely characterized by Sobolev-to-Lipschitz property.
Study proposes a new method for better price prediction using machine learning and metaheuristics.
problem Challenges in predicting prices due to correlated variables and computational efficiency.
method Introduces a novel decision fusion approach combining Elastic Net and MOPSO for variable selection and prediction.
result The proposed method outperforms traditional approaches in terms of accuracy and efficiency.
Modern statistical methods find the most common value in data.
problem Finding the most common value in data.
method Modern statistical methods applied to mode estimation.
result Traditional approaches to mode estimation are explored and modern methods are applied to new fields.
We introduce a new class of quantum enhancements we call biquandle brackets, which are customized skein invariants for biquandle colored links.Quantum enhancements of biquandle counting invariants form a class of knot and link invariants that includes biquandle cocycle invariants and skein invariants such as the HOMFLY…
DERWENT learns paths for distant transfer learning via deep random walk.
problem Transfer learning between distant domains is challenging.
method DERWENT uses deep random walk to explicitly learn paths between source and target domains.
result DERWENT achieves state-of-the-art performance on benchmark datasets.
Accurate goodness-of-fit tests for the extreme tails of empirical distributions is a very important issue, relevant in many contexts, including geophysics, insurance, and finance. We have derived exact asymptotic results for a generalization of the large-sample Kolmogorov-Smirnov test, well suited to testing these extr…
Deep learning and set theory improve prediction accuracy regardless of data relevance.
problem Improving prediction accuracy with limited relevant training data.
method Deep learning and set theory applied to large labeled training data.
result Exceptional prediction results achieved with irrelevant training data.
We show how binary classification methods developed to work on i.i.d. data can be used for solving statistical problems that are seemingly unrelated to classification and concern highly-dependent time series. Specifically, the problems of time-series clustering, homogeneity testing and the three-sample problem are addr…
DeGAN enriches data from related domains for future learning tasks.
problem Lack of relevant data for future learning tasks like Model Compression and Incremental Learning.
method Data-Enriching GAN (DeGAN) framework to retrieve representative samples from a trained classifier.
result State-of-the-art performance for Data-free Knowledge Distillation and Incremental Learning on benchmark datasets.
Efficient algorithm for robust recovery in stochastic block models.
problem Robust recovery in stochastic block models.
method Convex optimization framework, addressing optimization landscape challenges.
result Achieves robust recovery without a price of robustness.
Boosts barely robust learners to be more adversarially robust.
problem Learning predictors robust to small perturbations on a small fraction of data.
method Oracle-efficient algorithm for robustness with larger perturbation set.
result Qualitative and quantitative equivalence between strongly robust and barely robust learning.
Many complex systems exhibit extreme events far more often than expected for a normal distribution. This work examines how self-similar bursts of activity across several orders of magnitude can emerge from first principles in systems that adapt to information. Surprising connections are found between two apparently unr…
Neural recordings are nonstationary time series, i.e. their properties typically change over time. Identifying specific changes, e.g. those induced by a learning task, can shed light on the underlying neural processes. However, such changes of interest are often masked by strong unrelated changes, which can be of physi…
New approach discovers active learning strategies for various domains.
problem Finding efficient active learning strategies across different data types.
method Formalized annotation as a Markov decision process, designed universal state and action spaces, introduced a reward function, and used reinforcement learning to find optimal strategies.
result Learned strategies consistently outperform existing methods on multiple unrelated domains.
GRASP removes spurious correlations in fine-tuned models, improving task performance and reducing bias.
problem Fine-tuned models can latch onto spurious correlations, leading to bias and reduced generalization.
method GRASP identifies and removes spurious correlations from model weights without removing latent factors.
result GRASP significantly reduces bias and improves task performance in various fine-tuning tasks.
We consider how the problem of determining normal forms for a specific class of nonholonomic systems leads to various interesting and concrete bridges between two apparently unrelated themes. Various ideas that traditionally pertain to the field of algebraic geometry emerge here organically in an attempt to elucidate t…
Study finds stocks with higher cyber risk scores outperform others, indicating a market-wide cyber risk premium.
problem Identifying and quantifying firms' cyber risks and their impact on stock performance.
method Machine learning algorithm to analyze disclosures and a dedicated cyber corpus.
result High cyber risk stocks significantly outperform others, indicating a market-wide cyber risk premium.
Counterexamples show deconfounder fails to control multi-cause confounding.
problem Deconfounding method fails to handle multi-cause confounding.
method Incorrectly inferring independence and joint independence from conditional independence.
result Two simple counterexamples demonstrate deconfounder's failure.
We discuss in this article a property of action of groups by isometries called "well displacing". An action is said to be well displacing, if the displacement function is equivalent to the the displacement function for the action on the Cayley graph. We relate this property with the fact that orbit maps are quasi-isome…
Novel framework for quantifying data distribution values.
problem Quantifying the value of data distributions from samples.
method Generalized Bayesian Inference with loss from transferability measures.
result Unified solution for various practical problems.
The sequence (xn)n∈N=(2,5,15,51,187,…) given by the rule xn=(2n+1)(2n−1+1)/3 appears in several seemingly unrelated areas of mathematics. For example, xn is the density of a language of words of length n with four different letters. It is also the cardinality of the quotient of $(\math…
Investment strategies derived from commodity futures curves exploit dynamics in price movements.
problem Modeling and predicting the term structure of commodity futures prices.
method Employed the Nelson-Siegel framework to model term structure, and developed investment strategies based on changes in slope and curvature parameters.
result Significant profits generated from systematic strategies based on the change in slope, unrelated to risk factors and robust to transaction costs.
Two case studies reveal hidden biases and confounders in machine learning models of biomedical data.
problem Hidden biases and confounders in machine learning models of biomedical data.
method Two case studies examining biases and confounders in machine learning models of biomedical data.
result Prediction models performed well but hidden biases and confounders were revealed.
Bayesian correlated component analysis identifies brain process similarities across multiple stimulus views.
problem Investigating brain process similarity in responses to multiple views of a stimulus.
method Hierarchical probabilistic model that evaluates universality of spatial networks across multi-view data.
result Bayesian correlated component analysis evaluates favorably against other algorithms and identifies variability in spatial representations.
We establish a connection between two previously unrelated topics: a particular discrete version of conformal geometry for triangulated surfaces, and the geometry of ideal polyhedra in hyperbolic three-space. Two triangulated surfaces are considered discretely conformally equivalent if the edge lengths are related by s…
Unified theory linking node embeddings and graph representations.
problem Clarifying the relationship between node embeddings and graph representations.
method Using invariant theory, the paper establishes a theoretical framework bridging node embeddings and structural graph representations.
result Proves equivalence between node embeddings and structural graph representations, showing they are interchangeable for various tasks.
JD.com uses a new CNN model to improve ad click prediction.
problem Improving CTR prediction for ads with visual content.
method Proposes Category-specific CNN (CSCNN) to incorporate category knowledge early in the feature extraction process.
result CSCNN outperforms existing methods in CTR prediction.
Classifies generalized cusps in real projective manifolds.
problem Classifying geometric structures on cusps in real projective manifolds.
method Using affine groups and Bieberbach groups to classify cusps.
result Finite Busemann measure condition for cusp classification.
We show that many Lorentzian manifolds of dimension >2 do not admit a spacelike codimension-one foliation, and that almost every manifold of dimension >2 which admits a Lorentzian metric at all admits one which satisfies the dominant energy condition and the timelike convergence condition. These two seemingly unrelated…