New constructions in Legendrian embeddings space yield novel invariants.
problem Understanding higher-order homotopy in Legendrian embeddings.
method Introduced parametric satellite and connected-sum constructions.
result Constructed new infinite families of Legendrian embeddings.
News embeddings improve volatility forecasts.
problem Improving volatility forecasting accuracy.
method Transformed news text into embeddings, evaluated standalone and combined with benchmarks.
result News contains useful predictive information, especially for stock-related content.
New proof shows no Hölder embeddings into Heisenberg group.
problem Non-existence of Hölder embeddings into Heisenberg group.
method Developed a new elementary proof method.
result Generalization of Gromov's theorem proven.
Predict stock movement with news headlines using BERT embeddings.
problem Predicting stock price movement after financial news.
method Fine-Tuned Contextualized-Embedding Recurrent Neural Network (FT-CE-RNN) using BERT.
result Obtains state-of-the-art results on stock movement prediction task.
In this paper new general modewise Johnson-Lindenstrauss (JL) subspace embeddings are proposed that are both considerably faster to generate and easier to store than traditional JL embeddings when working with extremely large vectors and/or tensors. Corresponding embedding results are then proven for two different type…
A new framework for knowledge graph embedding using sheaves.
problem Learning representations for entities and relations in knowledge graphs.
method Using cellular sheaves to describe knowledge graph embeddings with consistency constraints.
result A generalized framework for reasoning about knowledge graph embedding models.
We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific embeddings, to improve their combined expressive power. Our approach relies on two key c…
Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies. However, such learning techniques are data demanding and work poorly on new ads w…
A new method combines multiple node embeddings using tensor decomposition.
problem Generating accurate node embeddings for complex networks.
method TenSemble2Vec: combines multiple embeddings via tensor decomposition.
result Improves node embeddings by leveraging complementary information from different methods.
This paper predicts stock prices using LLMs and news embeddings.
problem Predicting stock prices with high accuracy and relevance.
method Integrates LLMs with stock name embeddings and attention mechanisms for news filtering.
result Reduces MAE by 7.11% compared to baseline.
New constraints on embedded spheres and projective planes in 4-manifolds from Seiberg-Witten theory.
problem Constraints on configurations of embedded spheres and real projective planes in 4-manifolds.
method Equivariant Seiberg-Witten invariants and gluing formula for relative Seiberg-Witten invariants.
result Existence of certain configurations of surfaces leads to 4-manifolds of non-simple type.
DiSeNE generates interpretable node embeddings without supervision.
problem Lack of interpretability in unsupervised node embeddings.
method Disentangled representation learning with novel objective functions and metrics.
result DiSeNE produces interpretable node embeddings aligned with graph structure.
New algorithm for RL using mean embeddings of return distributions.
problem Improving reinforcement learning algorithms for dynamic programming.
method Mean embeddings of return distributions, novel algorithms for RL.
result Asymptotic convergence and improved performance in deep RL.
New symplectic barriers found in ball embeddings.
problem Existence of symplectic embeddings with intersections.
method Proving obligatory intersections with symplectic planes.
result Existence of symplectic barriers in ball embeddings.
Given Poincare spaces M and X, we study the possibility of compressing embeddings of M x I in X x I down to embeddings of M in X. This results in a new approach to embedding in the metastable range both in the smooth and Poincare duality categories.
The article introduces a new set of Polish word embeddings, built using KGR10 corpus, which contains more than 4 billion words. These embeddings are evaluated in the problem of recognition of temporal expressions (timexes) for the Polish language. We described the process of KGR10 corpus creation and a new approach to …
New embeddings for manifolds using heat kernels.
problem Constructing canonical conformal embeddings for manifolds.
method Employing heat kernel embedding from Bérard-Besson-Gallot'94 to find canonical conformal embeddings.
result Intrinsic construction of canonical conformal embeddings with dimensions growing exponentially with t. New test for conditional independence using kernel embeddings.
problem Testing conditional independence in high-dimensional settings.
method Analytic kernel embeddings, asymptotic distribution.
result New test outperforms existing methods in high-dimensional settings.
A new method simplifies HLLE for better robustness.
problem Improving robustness of Hessian locally linear embedding.
method Replacing Hessian with arbitrary weights and modifying manifold dimension.
result Achieved a new LLE-type method called tangential LLE.
New balls smoothly fit in CP² but not symplectically.
problem Embedding Stein rational homology balls in CP².
method Constructing a family of smooth but not symplectic embeddings.
result Existence of a doubly infinite family of such embeddings.
3028 obstructions found for embedding without knots.
problem Finding obstructions for knotless embedding.
method Surveying recent work, updating obstructions, and proposing new questions.
result New obstructions with μ=6 and insights into connectivity.
The paper uses news headlines to predict stock prices using embeddings.
problem Predicting stock prices using news headlines.
method Using OpenAI-based text embedding models and PCA to create vector encodings of news headlines, then training machine learning models on financial data.
result Headline data embeddings improve stock price prediction by at least 40%.
Neural model learns company embeddings from data and news.
problem Subjective industry classification schemes in finance.
method Multimodal neural model training company embeddings.
result Objective company representations capture nuanced relationships.
New model uses financial news to predict stock returns.
problem Predicting stock returns based on financial news.
method Derive company embedding vectors from news, select basis assets, and use statistical methods.
result NEUS model outperforms Fama-French 5-factor model.
New tool: relative Hopf invariant for Poincaré surgery.
problem Non-simply connected Poincaré surgery.
method Relative Hopf invariant in equivariant setting.
result Established Poincaré embedding results in relative setting.
New symplectic embedding obstructions found for polydisks into half-integer ellipsoids.
problem Obstructing symplectic embeddings of polydisks into half-integer ellipsoids.
method Combinatorial criterion developed by Hutchings to obstruct symplectic embeddings.
result Optimal inclusion conditions for symplectic embeddings of polydisks into half-integer ellipsoids.
Notes on embedding criteria for smooth manifolds.
problem Conditions for embedding smooth manifolds into Euclidean space.
method Linking recent results to classical criteria and K-theory.
result Recent results connect to classical embedding criteria.
New algorithm B++&C improves hierarchical clustering on large deep embedding datasets.
problem Scaling up hierarchical clustering to massive datasets of deep embeddings.
method Proposes B++&C algorithm for practical hierarchical clustering, introduces B2SAT&C for theoretical approximation.
result Achieves 5%/20% improvement on MW/CKMM objectives compared to classic methods.
New subgroups of mapping class groups constructed for infinite-type surfaces.
problem Constructing new subgroups of mapping class groups for infinite-type surfaces.
method Utilization of special homeomorphisms called shift maps and multipush maps.
result Countably (and uncountably in certain cases) many non-conjugate embeddings of subgroups into mapping class groups.
WEGL embeds graphs in a vector space for faster machine learning.
problem Efficiently embedding graphs for machine learning tasks.
method Wasserstein distance for node embedding similarity, Monge maps for graph representation.
result State-of-the-art classification performance with superior computational efficiency.
New method interprets deep embeddings for diabetes patient clustering.
problem Interpreting deep embeddings for disease progression.
method Patient clustering approach using deep embeddings.
result Clinically meaningful insights into diabetes progression patterns.
We generalise theorems of Khodorovskiy and Park-Park-Shin, and give new topological proofs of those theorems, using embedded surfaces in the 4-ball and branched double covers. These theorems exhibit smooth codimension-zero embeddings of certain rational homology balls bounded by lens spaces.
Optimal subspace embedding with near-optimal sparsity for high-dimensional data.
problem Efficiently preserving norms of vectors in high-dimensional subspaces.
method Near-optimal sparsity oblivious subspace embedding with decoupling argument and cumulant method.
result Achieved near-optimal sparsity of O~(1/ε) non-zeros per column. Survey on embedding 3-manifolds in definite 4-manifolds, focusing on Donaldson's theorem.
problem Understanding embeddings of 3-manifolds in definite 4-manifolds.
method Utilizes Donaldson's diagonalization theorem and combinatorics of integral lattices.
result New result on embedding amphichiral lens spaces in negative-definite manifolds.
Word embeddings are a popular approach to unsupervised learning of word relationships that are widely used in natural language processing. In this article, we present a new set of embeddings for medical concepts learned using an extremely large collection of multimodal medical data. Leaning on recent theoretical insigh…
Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets they do not take full advantage of the extra data due to their linear nature, and typically underfit. We propose a new class of models which …
Knowledge graph is a popular format for representing knowledge, with many applications to semantic search engines, question-answering systems, and recommender systems. Real-world knowledge graphs are usually incomplete, so knowledge graph embedding methods, such as Canonical decomposition/Parallel factorization (CP), D…
New sampling methods improve node embedding efficiency.
problem Efficiency and scalability in node embedding methods.
method Sampling approaches to node embedding, modeling eigenvectors and feature vectors.
result Improved computational efficiency and scalability.
A new clustering method improves recovery guarantees by re-embedding data.
problem Improving recovery guarantees in clustering algorithms.
method Chaining four techniques: leapfrog distances, multidimensional scaling, spectral methods, and sum-of-norms clustering.
result Re-embedding data improves recovery guarantees of clustering.
New symplectic caps and embeddings found in complex projective plane.
problem Embeddings of homology balls in complex projective plane.
method Handlebody construction of symplectic caps and embeddings.
result First examples of symplectic handlebody decompositions of a closed symplectic 4-manifold.
New formulas for minimal surfaces with specific end conditions.
problem Existence and explicit formulas for minimal surfaces with embedded planar ends.
method Provided new explicit formulas for genus 0 minimal surfaces in R^3 with 2k+1 embedded planar ends.
result Existence and explicit formulas for minimal surfaces with 2k+1 embedded planar ends for all k ≥ 4.
Enhanced word embedding creates new consumer-friendly health terms.
problem Laymen's health terms are often jargon and hard to understand.
method Developed an enhanced GloVe word embedding technique to generate new consumer-friendly terms.
result New CHV terms generated from consumer-generated text.
A new approach selects tuning parameters for embedding methods.
problem Difficulty in selecting tuning parameters for embedding methods.
method Minimize a stress notion to supervise tuning parameter selection.
result Uncover a new bias--variance tradeoff phenomenon.
New method learns state embeddings from demonstrations for improved reinforcement learning.
problem Difficult relationship between observed state and useful policy actions in dynamic problems.
method Variational framework for learning state embeddings that optimize trajectory linearity.
result Learning embedding spaces improves policy gradient reinforcement learning performance.
Proposes QQE for transforming and embedding data distributions.
problem Transforming and embedding data distributions for better representation or visualization.
method Quantile-Quantile Embedding (QQE) using quantile-quantile plot concept.
result QQE allows for better discrimination of classes in some cases.
We develop a new approach to the classical problem on isotopy classification of embeddings of manifolds into Euclidean spaces. This approach involves studying of a new embedding invariant, of almost-embeddings and of smoothing, as well as explicit constructions of embeddings. Using this approach we obtain complete conc…
Characterizes graphs with leveled embeddings and introduces new graph invariants.
problem Understanding the properties of leveled embeddings in spatial graphs.
method Characterization of graphs with leveled embeddings, introduction of new invariants.
result Characterization of graphs with low level number and determination of specific invariants for complete graphs and complete bipartite graphs.
New families of embeddings in 4-manifolds, topologically trivial but smoothly non-trivial.
problem Constructing non-trivial smooth embeddings of 3-manifolds in 4-manifolds.
method Parameterized families of embeddings, using high-dimensional spheres.
result Embeddings of homology spheres and any 3-manifold in blown-up K3 surfaces.