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.

168,742 papers · 148 categories

Trend · papers per month

12.5%25.0%37.5%50.0% · Sep 199319922001200920172026
48 results for latent symmetry

The study examines the stretch factors of outer automorphisms and their latent symmetry.

problem Understanding stretch factors of outer automorphisms in free groups.
method Analyzes the latent symmetry of graphs and uses it to bound stretch factors.
result A precise notion of latent symmetry provides a lower bound on the number of folds required.

Bayesian Empirical Bayes extends EB to complex structures using probabilistic symmetry.

problem Improving simultaneous inference in complex settings like arrays and graphs.
method Generalized empirical Bayes approach based on probabilistic symmetry.
result BEB outperforms existing methods in denoising arrays and spatial data.

SymPE breaks symmetries in equivariant networks, improving performance across various tasks.

problem Equivariant networks cannot break symmetries, leading to poor performance in tasks with symmetrical inputs.
method Novel equivariant conditional distributions and randomized canonicalization.
result SymPE significantly improves performance of group-equivariant and graph neural networks.

New method uses cycle consistency to enforce invariance in latent space.

problem Learning meaningful and independent factors of variation in datasets.
method Two separate latent subspaces, cycle consistency constraints, deep information bottleneck.
result Identifies more meaningful factors leading to sparser and interpretable models.

The manifold hypothesis states that many kinds of high-dimensional data are concentrated near a low-dimensional manifold. If the topology of this data manifold is non-trivial, a continuous encoder network cannot embed it in a one-to-one manner without creating holes of low density in the latent space. This is at odds w…

2018-07-12abs ↗pdf ↗

StrTransformer recovers sources without labels by optimizing latent matrices and enforcing structural constraints.

problem Unsupervised blind source recovery in signal processing.
method Source-wise structured Transformer framework with latent source matrix optimization, structural regularization, and branch-specific weights.
result StrTransformer learns distinct temporal-scale structures and recovers source-aligned latent trajectories.

Polytopic Matrix Factorization models data as latent vectors from a polytope, maximizing determinant for identifiability.

problem Data decomposition with semi-structured latent vectors and polytope constraints.
method Model input data as latent vectors from a polytope, using determinant maximization for identifiability.
result Identifiability condition for polytopes with specific symmetry restrictions.

Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for m…

2019-03-18abs ↗pdf ↗

Unified approach to causal representation learning using invariance principles.

problem Identifying latent causal variables from high-dimensional observations.
method Guiding identification of causal variables with invariance principles rather than causal hierarchies.
result Unified method that mixes causal and non-causal assumptions improves treatment effect estimation.

In this work, we move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to model entities and relations for knowledge graph embeddings. More specifically, quaternion embeddings, hypercomplex-valued embeddings with three imaginary components, are utilized to …

2019-04-23abs ↗pdf ↗

Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two separate deep representations: an invariant representation that encodes the informat…

2019-02-08abs ↗pdf ↗

MIM learns useful representations with high mutual information.

problem Learning useful representations for downstream tasks.
method Symmetric Jensen-Shannon divergence and mutual information regularizer in an encoder/decoder framework.
result MIM learns high mutual information representations without posterior collapse.

We consider a binary sequence generated by thresholding a hidden continuous sequence. The hidden variables are assumed to have a compound symmetry covariance structure with a single parameter characterizing the common correlation. We study the parameter estimation problem under such one-parameter models. We demonstrate…

2017-12-27abs ↗pdf ↗

Studying a softmax-attention model, we show that the learned query converges to the latent signal subspace spanned by the informative direction.

problem Understanding the theoretical principles of attention mechanisms in large-scale token collections.
method Deriving a population objective and analyzing the limiting ordinary differential equation of the learning dynamics.
result The learned query asymptotically recovers the latent signal up to the intrinsic sign ambiguity.

The paper analyzes symmetries of Vaidya-Bonner geodesics.

problem Investigating invariance properties of Vaidya-Bonner geodesics.
method Classification of Lie point symmetries and Noether symmetries, determination of optimal system of subalgebras.
result Determination of optimal system of subalgebras for Vaidya-Bonner geodesics.

A new method uses algebraic insights to create approximately equivariant networks without complex architectures.

problem Designing equivariant neural networks with complex architectures and high computational cost.
method Imposes the group's regular representation as an inductive bias via an auxiliary loss, adding no learnable parameters.
result Matches or outperforms specialized models in several cases, even for infinite groups.

Method improves deep learning models for datasets with mixed approximate symmetries.

problem Improving deep learning models for datasets with mixed approximate symmetries.
method Regularizer-based approach to build models for datasets with mixed approximate symmetries.
result Our method achieves better accuracy than prior approaches while discovering the approximate symmetry levels correctly.

Symmetry in loss functions constrains model parameters, leading to specific learning outcomes.

problem Understanding and leveraging symmetries in neural networks to improve learning outcomes.
method Analyzing the impact of loss function symmetries on model parameters and learning behavior.
result Mirror-reflection symmetries in loss functions lead to constraints on model parameters, influencing learning outcomes.

Approximate symmetries of geodesic equations on 2-spheres are studied. These are the symmetries of the perturbed geodesic equations which represent approximate path of a particle rather than exact path. After giving the exact symmetries of the geodesic equations, two different approaches to study the approximate symmet…

2010-05-09abs ↗pdf ↗

New framework discovers non-affine continuous symmetries in neural networks.

problem Lack of efficient methods for detecting non-affine continuous symmetries in neural networks.
method Computational framework for discovering infinitesimal generators of multi-parameter group actions.
result Framework can discover non-affine continuous symmetries in neural networks.

This paper introduces a new approach to finding knots and links with hidden symmetries using "hidden extensions", a class of hidden symmetries defined here. We exhibit a family of tangle complements in the ball whose boundaries have symmetries with hidden extensions, then we further extend these to hidden symmetries of…

2015-01-04abs ↗pdf ↗

Symmetry of neural network densities can be determined from correlation functions.

problem Determining symmetries of neural network densities without knowing the density itself.
method Symmetry-via-duality approach using invariance properties of correlation functions.
result Symmetries of neural network densities can be determined via dual computations of correlation functions.

Clarifies relation between Pfaffian fibrations and relative algebroids.

problem Understanding geometric structures and symmetries in PDEs.
method Introduces and analyzes Pfaffian fibrations and relative algebroids, clarifying their relationship.
result Every Pfaffian fibration induces a relative algebroid, and their prolongations and local solutions coincide.