A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New method learns state embeddings from demonstrations for improved reinforcement learning.
This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank. In the spirit of diffusion map, we propose an efficient method for learning a low-dimensional state embedding and capturing the process's dynamics. This idea a…
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling e…
The transition amplitudes between coherent states on a coherent state manifold are expressed in terms of the embedding of the coherent state manifold into a projective Hilbert space. Consequences for the dimension of projective Hilbert space and a simple geometric interpretation of Calabi's diastasis follows.
New method uses Cantor embeddings and Wasserstein distances to analyze predictive states in time series data.
Efficient RL in large POMDPs with latent determinism and embeddings.
A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes' …
A novel geometric algebra-based KG embedding framework improves link prediction.
Predictive State Representations (PSRs) are an expressive class of models for controlled stochastic processes. PSRs represent state as a set of predictions of future observable events. Because PSRs are defined entirely in terms of observable data, statistically consistent estimates of PSR parameters can be learned effi…
RECODE uses clustering and embedding to track state visitation counts in RL.
Representation learning methods that transform encoded data (e.g., diagnosis and drug codes) into continuous vector spaces (i.e., vector embeddings) are critical for the application of deep learning in healthcare. Initial work in this area explored the use of variants of the word2vec algorithm to learn embeddings for m…
This work analyzes PPR-based node embeddings and their topological information.
New method improves reinforcement learning generalization.
Paper proves Chow stability implies balanced embedding.
Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to tr…
Models use embeddings and attention for better claim severity prediction.
FREDE efficiently embeds graphs using linear space and guarantees quality.
Transformers encode latent distributions in text, improving performance in out-of-distribution cases.
Embeddings leak sensitive information about input data, which can be recovered or inferred.
A new method estimates multi-dimensional value distributions using Hilbert space embeddings.
Generalizes embedding formalism for CFTs on curved backgrounds.
Embedding words in a vector space has gained a lot of attention in recent years. While state-of-the-art methods provide efficient computation of word similarities via a low-dimensional matrix embedding, their motivation is often left unclear. In this paper, we argue that word embedding can be naturally viewed as a rank…
We propose a simple discrete time semi-supervised graph embedding approach to link prediction in dynamic networks. The learned embedding reflects information from both the temporal and cross-sectional network structures, which is performed by defining the loss function as a weighted sum of the supervised loss from past…
Obtaining continuous representations of structural data such as directed acyclic graphs (DAGs) has gained attention in machine learning and artificial intelligence. However, embedding complex DAGs in which both ancestors and descendants of nodes are exponentially increasing is difficult. Tackling in this problem, we de…
Paper proves impossibility of three desirable properties in node embedding.
This paper learns multi-modal embeddings from text, audio, and video views/modes of data in order to improve upon down-stream sentiment classification. The experimental framework also allows investigation of the relative contributions of the individual views in the final multi-modal embedding. Individual features deriv…
In this paper we introduce score embedding, a neural network based model to learn interpretable vector representations for words. Score embedding is a supervised method that takes advantage of the labeled training data and the neural network architecture to learn interpretable representations for words. Health care has…
Explains Hodge theory and Kodaira embedding theorem for complex manifolds.
Measures time-delay embedding for noisy, sparse data.
Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far apart. We propose a probabilistic method that treats embeddings as random variables. Extending a state-of-the-art deterministic method, Protot…
MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.
Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of t…
Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities. We propose the use of informative priors to create interpretable and domain-informed dime…
New method for embedding large networks without attributes, achieving state-of-the-art performance.
Persona2vec learns multiple node roles in graphs.
Quantum traces embed into quantum tori for surface skein algebras.
Given an integral symplectic manifold, we construct a family of "coherent state" maps into complex projective space. The maps are built from sections of the tensor powers of a hermitian line bundle whose curvature is a multiple of the symplectic form. We show that this family is an almost-complex version of the Kodiara…
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…
In this paper, we propose a Tensor Train Neighborhood Preserving Embedding (TTNPE) to embed multi-dimensional tensor data into low dimensional tensor subspace. Novel approaches to solve the optimization problem in TTNPE are proposed. For this embedding, we evaluate novel trade-off gain among classification, computation…
The study examines Kähler structures on coadjoint orbits of Lie groups using coherent and squeezed states.
A new method combines multiple node embeddings using tensor decomposition.
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. …
Proves h-principle for loose Legendrian embeddings in contact topology.
Contrastive embeddings improve neural architecture search performance.
Proposes FEFM and DeepFEFM for CTR prediction, outperforming state-of-the-art models.
We find the minimal number of links in an embedding of any complete -partite graph on 7 vertices (including , which has at least 21 links). We give either exact values or upper and lower bounds for the minimal number of links for all complete -partite graphs on 8 vertices. We also look at larger complete bip…
Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data. However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks. Hence, it i…
The goal of this note is to prove a compact embedding result for spaces of forward rate curves. As a consequence of this result, we show that any forward rate evolution can be approximated by a sequence of finite dimensional processes in the larger state space.