Research
On-device research index

arXiv research

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.

169,291 papers · 148 categories

Trend · papers per month

87173260346 · Jun 202019922001200920182026
48 results for ID representation

Paper proposes embedding framework to efficiently represent IDs in e-commerce.

problem Efficient representation of IDs with consideration of relationships among different types of IDs.
method Embedding based framework using item ID sequences and structural connections.
result Effective representation and transfer of IDs across different scenarios in e-commerce.

New research shows common ID estimators in neural representations are inaccurate.

problem Inaccurate estimation of intrinsic dimensions in neural representations.
method Theoretical and empirical investigation of ID estimators in neural representations.
result Common ID estimators do not accurately reflect the true underlying ID of neural representations.

Study reveals differences in medical image models' hidden representation refinement.

problem Understanding how intrinsic dimensionality changes in neural network hidden representations across different domains.
method Analysis of 11 natural and medical image datasets using 6 network architectures.
result Medical image models refine hidden representations earlier, suggesting differences in feature abstraction.

Deep networks learn low-dimensional yet complex data representations.

problem Understanding the intrinsic dimensionality of deep neural network representations.
method Analysis of intrinsic dimensionality across multiple layers of trained networks.
result The intrinsic dimensionality of data representations in deep networks is significantly lower than the number of units in each layer.

This study analyzes VAEs using ID and II, revealing a transition in behaviour and distinct training phases.

problem Understanding the hidden representations and training phases of VAEs.
method Analysis using Intrinsic Dimension (ID) and Information Imbalance (II).
result VAEs exhibit a transition in behaviour and distinct training phases when the bottleneck size exceeds the Intrinsic Dimension of the data.

P-OCS detects OOD samples in a low-dimensional subspace, outperforming existing methods.

problem Efficient OOD detection for deep learning models in open-world environments.
method P-OCS operates in the orthogonal complement of the principal subspace, applying a single projected perturbation.
result P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining.

Researchers analyze the geometric and statistical properties of transformer model representations.

problem Understanding the semantic structure of large transformer models across various data types.
method Characterization of geometric and statistical properties through analysis of intrinsic dimension and neighbor composition.
result The semantic information of the dataset is better expressed at the end of the first peak in transformer models.

Compositional Network Embedding learns node embeddings from node features.

problem Cold-start problem and lack of robustness to noise in existing network embedding methods.
method Generative framework that combines node attribute embeddings through a graph-based loss.
result Effectiveness and generalization of compositional network embeddings, especially on unseen nodes.

Meta-Embedding improves CTR predictions for new ads, addressing cold-start and warm-up issues.

problem Improving CTR predictions for new ads with little logging data.
method Meta-learning approach to generate initial embeddings for new ad IDs.
result Meta-Embedding significantly improves CTR predictions for various models, including lightweight and deep learning.

Calibrated ensembles improve both ID and OOD accuracy in distribution shift.

problem Desired balance between in-distribution and out-of-distribution accuracy.
method Ensemble standard and robust models, calibrating on ID data only.
result ID-calibrated ensembles outperform state-of-the-art methods on multiple datasets.

Improved OOD detection across various shifts using multi-encoder fusion of RDMs.

problem Out-of-distribution detection across multiple types of distribution shifts.
method Statistical identification of encoder sensitivity, EncMin2L fusion, and Tippett minimum combination.
result Achieves AUROC ≥ 0.94 across four shift types, outperforming state-of-the-art detectors.

We first analyze the integrated density of states (IDS) of periodic Schrödinger operators on an amenable covering manifold. A criterion for the continuity of the IDS at a prescribed energy is given along with examples of operators with both continuous and discontinuous IDS'. Subsequently, alloy-type perturbations of th…

2007-05-08abs ↗pdf ↗

ASTPN improves video-based person re-identification by jointly attending to spatial and temporal features.

problem Video-based person re-identification in surveillance and HCI.
method Joint Spatial and Temporal Attention Pooling Network (ASTPN).
result ASTPN outperforms state-of-the-art methods on multiple datasets.

The Jones-Witten theory gives rise to representations of the (extended) mapping class group of any closed surface Y indexed by a semi-simple Lie group G and a level k. In the case G=SU(2) these representations (denoted V_A(Y)) have a particularly simple description in terms of the Kauffman skein modules with parameter …

2002-09-12abs ↗pdf ↗

IDS improves sparse linear bandits by balancing information and regret.

problem Sparse linear bandits in high-dimensional decision-making.
method Information-directed sampling (IDS) with Bayesian regret bounds and empirical Bayesian sparse posterior sampling.
result IDS nearly matches existing lower bounds and significantly reduces regret.

DeepHGNN detects program identity changes using system behaviors.

problem Detecting program identity changes to prevent malware.
method Attentional heterogeneous graph neural network (DeepHGNN) for graph classification.
result DeepHGNN effectively identifies program identities across various metrics.

ProSub uses angles in feature space to classify data as in- or out-of-distribution.

problem Open-set semi-supervised learning with unknown classes.
method Probabilistic approach based on angles in feature space, estimating conditional distributions of scores.
result ProSub achieves state-of-the-art performance on benchmark problems.

New bounds on IDS for RL show how to balance computation and learning efficiency.

problem Understanding and optimizing information-directed sampling (IDS) for reinforcement learning.
method Developed novel information-theoretic tools to bound information ratio and cumulative information gain.
result Derived prior-free Bayesian regret bounds for IDS in tabular finite-horizon MDPs and improved computational efficiency.

Generates realistic person images for re-id, overcoming pose variations.

problem Lack of cross-view paired training data and pose variations in person re-identification.
method Pose-normalization GAN (PN-GAN) for generating images conditioned on pose.
result Synthesized images enable learning invariant features free of pose variations.

Study complex reflections in infinite Coxeter tetrahedron moduli space.

problem Characterize representations of Coxeter group in complex hyperbolic space.
method Type-preserving representations of Coxeter group GG to PU(3,1)PU(3,1), parameterized by θθ.
result Discrete and faithful representations for θ[5π6,π]θ \in [\frac{5π}{6}, π]. First nontrivial moduli space in complex hyperbolic space.

Beta-SOD detects and corrects noisy object re-identification using cosine similarity and Beta mixtures.

problem Noisy object re-identification in image datasets.
method Reframed Re-ID as a similarity task, using Siamese networks and Beta mixture models.
result Superior performance in noisy conditions compared to state-of-the-art methods.

Let qq be a 2N2Nth root of unity where NN is odd. Let Uq(sl2)U_q(sl_2) denote the quantum group with large center corresponding to the lie algebra sl2sl_2 with generators E,F,KE,F,K, and K1K^{-1}. A semicyclic representation of Uq(sl2)U_q(sl_2) is an NN-dimensional irreducible representation $ρ:U_q(sl_2)\rightarrow M_N(\mathbb{C}…

2016-07-07abs ↗pdf ↗

New IDS algorithm refines parameter norm bounds for better bandit performance.

problem Frequentist IDS requires tight norm bounds, which are often unavailable in practice.
method Iteratively refines a high-probability upper bound on true parameter norm using data.
result Regret bounds independent of assumed parameter norm, outperforming state-of-the-art algorithms.

Knoto-ID studies the entanglement of open protein chains without closing them.

problem Analyzing the entanglement of open protein chains without altering their geometry.
method Using knotoids, a generalization of knot theory for open curves, to evaluate entanglement without closing the curve.
result Knoto-ID can analyze both global and local topologies of protein chains, identifying non-trivial folds.

This work introduces a protocol to automatically select the correct range of scales for meaningful Intrinsic Dimension estimation.

problem The Intrinsic Dimension (ID) varies with scale in real-world datasets, leading to erroneous results.
method The protocol selects the correct range of scales by ensuring constant density of data points.
result The method provides a robust and scale-adaptive approach to estimating meaningful Intrinsic Dimension.

LoD improves model safety by integrating unlabeled wild data, reducing OOD misclassification.

problem Improving model safety and reliability using unlabeled wild data containing both in-distribution and out-of-distribution samples.
method Intentionally label-noisifying unlabeled wild data to enable joint learning of labeled ID and OOD data, distinguishing losses between ID and OOD samples.
result LoD framework achieves superior OOD detection without requiring thresholds, improving model safety.

New method estimates intrinsic dimensionality in undersampled data.

problem Challenges in estimating intrinsic dimensionality in high-dimensional, undersampled data.
method Uses tangent space properties and full correlation integral for accurate estimation.
result Capable of estimating ID in extremely undersampled regimes and curved manifolds.

In this paper, we study the risk bounds for samples independently drawn from an infinitely divisible (ID) distribution. In particular, based on a martingale method, we develop two deviation inequalities for a sequence of random variables of an ID distribution with zero Gaussian component. By applying the deviation ineq…

2012-02-14abs ↗pdf ↗

A Bloom filter approach combined with Transformer models improves accuracy for machine learning tasks on opaque IDs.

problem Improving accuracy for machine learning tasks on opaque IDs with large vocabulary sizes.
method Applying hash functions to map opaque IDs to multiple hash tokens, similar to a Bloom filter, and using a multi-layer Transformer to process these digests.
result Models outperform those without hashing and sampled softmax, achieving high accuracy with a smaller computational budget.

Study on deep learning IDS resistance against adversarial attacks.

problem Vulnerabilities in deep learning-based IDS against adversarial attacks.
method Apply min-max optimization to train IDS against adversarial samples.
result Adversarial attack methods can be used in continuous domains and boost IDS robustness.