Proposes a constraint for deep clustering to handle both simple and complex topologies.
problem Limited prior knowledge for deep clustering methods to perform well on complex topologies.
method Introduces a constraint using symmetric InfoNCE to enhance deep clustering performance.
result The constraint improves deep clustering methods' performance on both simple and complex topologies.
SC-InfoNCE improves InfoNCE for feature clustering in contrastive learning.
problem Lack of theoretical understanding of InfoNCE's feature clustering mechanism.
method Introduced a transition probability matrix to model data augmentation dynamics and optimize feature similarity.
result SC-InfoNCE achieves strong performance across diverse domains, aligning feature similarity with downstream data.
InfoNCE objective is equivalent to ELBO in RPM, linking to self-supervised learning.
problem Improving self-supervised learning methods by connecting them to variational inference.
method Recognizing RPM and showing InfoNCE as a simplified lower bound on MI, equal to ELBO in infinite sample limit.
result The actual InfoNCE objective is equal to the ELBO (up to a constant) in the infinite sample limit.
Paper refines InfoNCE for accurate mutual information estimation.
problem Indirect connection of InfoNCE to mutual information estimation.
method Introduces InfoNCE-anchor with an auxiliary anchor class for consistent density ratio estimation.
result InfoNCE-anchor yields a plug-in MI estimator with significantly reduced bias.
Improved similarity search in embeddings using InfoNCE loss.
problem Improving similarity search in embedding models trained by contrastive learning.
method Introduced a new continuity bound for InfoNCE loss via Gâteaux differentiation, preserving the averaging effect of negative samples.
result Demonstrated that the averaging effect of k negative samples in InfoNCE loss carries over to stabilisation of generalisation error as k grows. The paper analyzes the InfoNCE loss under different temperature schedules using Langevin dynamics.
problem Understanding the dynamics of InfoNCE loss under fixed versus annealed temperature schedules.
method Modeling embedding evolution under Langevin dynamics on a compact Riemannian manifold, with theoretical guarantees for convergence.
result Slow logarithmic inverse-temperature schedules ensure convergence to globally optimal representations, while faster schedules risk suboptimal minima.
WEINCE improves contrastive learning by correcting softmax biases.
problem Softmax in InfoNCE can lead to misaligned statistical assumptions in contrastive learning.
method WEINCE uses anchor-wise online batch statistics to blend softmax logits with an endpoint shortfall correction.
result WEINCE yields consistent improvements in frozen-feature evaluation across five vision benchmarks.
A new contrastive learning objective, FlatNCE, fixes resource demands in small-batch training.
problem Resource demands in contrastive learning schemes, especially with small-batch training.
method FlatNCE is a novel contrastive objective that no longer explicitly aims for a discriminative classification goal.
result FlatNCE enables immediate performance boost independent of subject-matter engineering efforts.
Paper proposes a new loss function for conditional models using soft targets.
problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.
New method AnInfoNCE uncovers latent factors in contrastive learning with practical variability.
problem Theoretical assumptions of contrastive learning loss overlook practical variability in positive pairs.
method AnInfoNCE, a generalization of InfoNCE, models anisotropic variability to uncover latent factors.
result AnInfoNCE increases recovery of latent factors in CIFAR10 and ImageNet, albeit at the cost of accuracy.
New method improves transfer and robustness of supervised contrastive learning.
problem Class collapse in supervised contrastive learning leads to poor representation quality.
method Adding a weighted class-conditional InfoNCE loss and a class-conditional autoencoder.
result Improves transfer and robustness on 5 standard datasets and 3 worst-group robustness datasets.
New method improves self-supervised representation learning using probabilistic modeling and Monte Carlo integration.
problem Improving self-supervised representation learning for multimodal data.
method Discriminative probabilistic modeling with multiple importance sampling (MIS) for robust Monte Carlo integration.
result Proposes a novel non-parametric method for approximating conditional probability densities through convex optimization.
cMIM improves representation learning without positive-pair augmentations.
problem Learning robust representations for diverse tasks.
method Contrastive Mutual Information Machine (cMIM) framework.
result cMIM outperforms MIM and InfoNCE on classification and regression tasks.
This paper broadens contrastive learning for disentangled representations without strict data distribution assumptions.
problem Learning disentangled representations from data with specific assumptions.
method Extends theoretical guarantees for disentanglement to a broader family of contrastive methods, relaxing data distribution assumptions.
result Identifiability of true latents for four contrastive losses proved without common independence assumptions.
We propose a novel deep learning method for local self-supervised representation learning that does not require labels nor end-to-end backpropagation but exploits the natural order in data instead. Inspired by the observation that biological neural networks appear to learn without backpropagating a global error signal,…
A new contrastive MI estimator improves efficiency and tightness.
problem Efficient and tight mutual information estimation.
method Contrastive Fenchel-Legendre optimization.
result The FLO estimator is tight and converges under stochastic gradient descent.
VCL adds uncertainty to contrastive learning models.
problem Lack of uncertainty quantification in contrastive learning methods.
method VCL uses a decoder-free framework that maximizes ELBO with InfoNCE loss and KL divergence.
result VCL provides meaningful uncertainty estimates and matches deterministic baselines in accuracy.
New measure quantifies contrastive self-supervised learning's generalization ability.
problem Limited theoretical understanding of contrastive self-supervised learning's generalization.
method Defined (σ,δ)-measure to mathematically quantify data augmentation and provide an upper bound for downstream classification error. result Generalization ability is related to alignment of positive samples, divergence of class centers, and concentration of augmented data.
Contrastive learning recovers latent distributions for ambiguous inputs, including aleatoric uncertainty.
problem Real-world observations often have inherent ambiguities, making the true posterior probabilistic with heteroscedastic uncertainty.
method Extended InfoNCE objective and encoders to predict latent distributions, proving they recover the correct posteriors, including aleatoric uncertainty.
result Contrastive learning encoders can recover the correct posteriors of data-generating processes, including aleatoric uncertainty, up to a rotation of the latent space.
New method improves model robustness to biased data.
problem Learning unbiased models from biased datasets.
method Developed epsilon-SupInfoNCE and FairKL losses.
result Improved performance on biased datasets.
New mutual information framework improves contrastive learning for vision tasks.
problem Maximizing mutual information for better unsupervised learning representations.
method Reformulated mutual information as a lower bound, introducing new negative sampling strategies.
result Improved representations outperform previous methods in various vision tasks.
Framework explains how dual deep networks learn features from unlabeled data.
problem Understanding self-supervised learning with dual deep networks.
method Theoretical framework and hierarchical latent tree model.
result Deep ReLU networks learn latent variables through contrastive SSL.
Maximizes image representation dependence for self-supervised learning.
problem Learning meaningful image representations from unlabeled data.
method Maximizes Hilbert-Schmidt Independence Criterion (HSIC) between image transformations and identity.
result Matches state-of-the-art performance on ImageNet and other vision tasks.
Improved 3D MRI classification using contrastive learning with continuous proxy metadata.
problem Insufficient labelled data for 3D medical image classification.
method Proposed a new loss function (y-Aware InfoNCE) to leverage continuous proxy metadata in contrastive learning.
result 3D CNN model pre-trained on 10^4 multi-site healthy brain MRI scans outperforms fully-supervised methods.
This work improves independence tests for high-dimensional data.
problem Detecting subtle dependencies between high-dimensional random variables with complex distributions.
method Develops two approaches to learn powerful independence tests using variational mutual information and HSIC.
result Optimized HSIC tests generally outperform other approaches on detecting structured dependence.
The paper classifies symmetric triads with multiplicities and their applications.
problem Classifying symmetric triads with multiplicities and their applications.
method Developed the theory of symmetric triads with multiplicities, classified abstract triads, and determined corresponding triads for commutative compact triads.
result Classified symmetric triads with multiplicities and their applications.
We find all Ricci semi-symmetric as well as all conformally semi-symmetric spacetimes. Neither of these properties implies the other. We verify that only conformally flat spacetimes can be Ricci semi-symmetric without being conformally semi-symmetric and show that only vacuum spacetimes and spacetimes with just a Λ-t…
We establish a new symmetrization procedure for the isoperimetric problem in symmetric spaces of noncompact type. This symmetrization generalizes the well known Steiner symmetrization in euclidean space. In contrast to the classical construction the symmetrized domain is obtained by solving a nonlinear elliptic equatio…
Study on totally symmetric sets with group applications.
problem Understanding totally symmetric sets and their group applications.
method Survey of existing theory and applications to various groups.
result Exploration of totally symmetric sets in multiple group contexts.
In this article, we summarize the results on symmetric conformal geometries. We review the results following from the general theory of symmetric parabolic geometries and prove several new results for symmetric conformal geometries. In particular, we show that each symmetric conformal geometry is either locally flat or…
The object of the present paper is to study locally φ-symmetric LP-Sasakian manifolds admitting semi-symmetric metric connection and obtain a necessary and sufficient condition for a locally φ-symmetric LP-Sasakian manifold with respect to semi-symmetric metric connection to be locally φ-symmetric LP-Sasakian man…
In this note, we discuss symmetric brackets on skew-symmetric algebroids associated with a metric structure. Given a pseudo-Riemannian metric structure, we describe symmetric brackets induced by connections with totally skew-symmetric torsion in the language of Lie derivatives and differentials of functions. In particu…
Symmetric Poisson structures linked to geodesic foliations and Jordan algebras.
problem Understanding geometric structures related to geodesic foliations and dynamics.
method Introducing symmetric Poisson structures, proving correspondences with geodesic foliations and Jordan algebras.
result Symmetric Poisson structures correspond to totally geodesic foliations and Jacobi-Jordan algebras.
Complete classification of quaternionic skew-Hermitian symmetric spaces found.
problem Classifying quaternionic skew-Hermitian symmetric spaces.
method Proving the existence of a torsion-free mSO∗(2n)mSp(1)-structure and showing that any homogeneous space is symmetric. result A complete classification of quaternionic skew-Hermitian symmetric spaces for arbitrary n>1. Symmetric quandles provide new insights into link colorings.
problem Understanding link colorings using quandles.
method Construction of symmetric quandles and isomorphism of their cohomology groups.
result Homology groups of quandles are isomorphic to those of their symmetric doubles.
Study para-Sasakian φ-symmetric spaces using Boothby-Wang fibration.
problem Characterize para-Sasakian φ-symmetric spaces.
method Use Boothby-Wang fibration to construct and provide examples.
result Explicit construction and example of para-Sasakian φ-symmetric spaces.
Formulae for non-symmetric connections derived from covariant derivatives.
problem Deriving commutation formulae for non-symmetric affine connections.
method Covariant derivatives of tensors with respect to symmetric and non-symmetric affine connections.
result Formulae for non-symmetric connections derived from covariant derivatives.
New (co)homology theory for symmetric quandles developed.
problem Developing strong invariants for symmetric quandles.
method Introducing symmetric quandle modules and Beck modules, extending module theory, and constructing generalized (co)homology.
result Established an explicit isomorphism between symmetric quandle cohomology and group cohomology.
Paper introduces capillary Schwarz symmetrization in half-space.
problem Capillary problems in half-space.
method Introduces a special anisotropic gauge to transform capillary symmetrization to convex symmetrization.
result Capillary Schwarz symmetrization in half-space established.
New proof for symmetric spaces with rectangular lattices.
problem Characterizing symmetric spaces with rectangular unit lattices.
method Explicit construction of isometric embeddings and analysis of root systems.
result Symmetric spaces with rectangular unit lattices are symmetric R-spaces.
In this paper, we introduce the notion of a left-symmetric bialgebroid as a geometric generalization of a left-symmetric bialgebra and construct a left-symmetric bialgebroid from a pseudo-Hessian manifold. We also introduce the notion of a Manin triple for left-symmetric algebroids, which is equivalent to a left-symmet…
We construct and identify star representations canonically associated with holonomy reducible simple symplectic symmetric spaces. This leads the a non-commutative geometric realization of the correspondence between causal symmetric spaces of Cayley type and Hermitian symmetric spaces of tube type.
Develops symmetric Cartan calculus linking to Patterson-Walker metric.
problem No specific problem stated; focuses on developing a new calculus.
method Symmetric Cartan calculus, using torsion-free affine connections.
result Symmetric Cartan calculus is a complete analogue of classical Cartan calculus.
The study characterizes and verifies equivariant embeddings of symmetric Kählerian manifolds.
problem Characterizing and verifying equivariant embeddings of symmetric Kählerian manifolds.
method Investigation motivated by Cartan and Wallach's theorem on symmetric spaces, focusing on CPn and parallel plurimean curvature. result If an equivariant embedding has parallel plurimean curvature, it is the extrinsically symmetric one.
Defines semi-symmetric metric connection on super warped products.
problem Computing curvature and Ricci tensors on super warped products.
method Introduced semi-symmetric metric connection and conditions for Einstein spaces.
result Conditions for super warped product spaces to be Einstein with semi-symmetric metric connection.
Since the work of Henri Cartan finite dimensional Riemannian symmetric spaces are an important subject of mathematical interest. They are related in a natural way to semisimple Lie groups. In this work we introduce and study their infinite dimensional generalization: Affine Kac-Moody symmetric spaces. Affine Kac-Moody …
Classifies totally geodesic submanifolds in symmetric spaces.
problem Classifying submanifolds in symmetric spaces.
method Classification of totally geodesic submanifolds in products of rank one symmetric spaces.
result Infinitely many examples of irreducible totally geodesic submanifolds in Hermitian symmetric spaces.
This paper aims to provide a better understanding of a symmetric loss. First, we emphasize that using a symmetric loss is advantageous in the balanced error rate (BER) minimization and area under the receiver operating characteristic curve (AUC) maximization from corrupted labels. Second, we prove general theoretical p…