Elastic-InfoGAN learns object identity in class-imbalanced data.
problem Learning disentangled representations in class-imbalanced data.
method Invariance to identity-preserving transformations to learn object identity.
result Effectiveness in disentangling object identity in imbalanced datasets.
We evaluate the impact of probabilistically-constructed digital identity data collected from Sep. to Dec. 2017 (approx.), in the context of Lookalike-targeted campaigns. The backbone of this study is a large set of probabilistically-constructed "identities", represented as small bags of cookies and mobile ad identifier…
Improved local SGD analysis for identical and heterogeneous data.
problem Analyzing local SGD performance in identical and heterogeneous data regimes.
method Developed a new variance measure specific to local SGD and improved existing theory.
result Tightened stepsize and number of local iterations for optimal performance.
Undirected graphs are often used to describe high dimensional distributions. Under sparsity conditions, the graph can be estimated using ℓ1 penalization methods. However, current methods assume that the data are independent and identically distributed. If the distribution, and hence the graph, evolves over time t…
The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such services, the sharing of such inherently personal data, including speech data, raises obvious security and privacy concerns. In particular, …
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
New method learns identity-preserving transformations on data manifolds without labels.
problem Learning identity-preserving transformations on natural variations without supervision.
method Introduces a learning strategy that does not require transformation labels and learns local regions for operators.
result Trains on MNIST and Fashion MNIST, and CelebA, learning transformations without labels.
Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different co…
Study ridge regression for non-identically distributed data with varying variances.
problem Investigate high-dimensional regression with non-identical data variance.
method Propose a random effect model and use tools from random matrix theory.
result Highlight the double descent phenomenon in high-dimensional regression for certain variance profiles.
Bayesian weight priors improve neural network learning of identity relations.
problem Neural networks struggle to learn abstract and systematic relations, especially identity relations.
method Extended RBP approach using Bayesian weight priors as a regularization term.
result Bayesian weight priors lead to perfect generalization for identity relations and do not hinder standard neural network learning.
In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete id…
This paper discovers new identities linking geodesic and orthogeodesic lengths on hyperbolic surfaces.
problem Understanding relationships between geodesic and orthogeodesic lengths on hyperbolic surfaces.
method Investigates a broad family of identities involving lengths of all closed geodesics and orthogeodesics.
result Introduces new identities that include lengths of all closed geodesics, contrasting with previous identities.
Unsupervised mesh disentanglement separates identity and pose.
problem Geometric disentanglement for 3D deformable models.
method CFAN-VAE architecture using conformal factor and normal features.
result CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement.
Establishes a correspondence between two mathematical identities.
problem None explicitly stated; focuses on identity correspondence.
method Establishes correspondence between Pestov and Weitzenböck identities.
result Established correspondence between Pestov and Weitzenböck identities.
This work examines how non-identical data distributions affect Federated Learning performance.
problem The impact of non-identical data distributions on Federated Learning performance.
method Synthesized datasets with varying degrees of data distribution similarity, evaluated Federated Averaging algorithm performance, proposed server momentum mitigation.
result Performance of Federated Learning degrades as data distributions differ more, and a mitigation strategy improves accuracy.
VRL-SGD reduces communication complexity in non-identical data settings.
problem Training machine learning models with non-identical data distribution.
method VRL-SGD, which eliminates gradient variance dependency and achieves linear speedup with lower communication complexity.
result VRL-SGD reduces communication complexity from $O(T^{ rac{3}{4}} N^{ rac{3}{4}})$ to $O(T^{ rac{1}{2}} N^{ rac{3}{2}})$.
SiD distills pretrained diffusion models into a fast one-step generator.
problem Efficiently distilling pretrained diffusion models into a fast generator.
method Reformulates forward diffusion processes as semi-implicit distributions and uses three score-related identities to create a loss mechanism.
result Achieves high FID performance and significantly reduces generation time.
Novel framework for data sharing and coordinated exploration in concurrent RL with non-identical environments.
problem Learning more data-efficient and better policies in concurrent RL with non-identical environments.
method Proposes a novel algorithmic framework that leverages causal inference via ANM-MM to extract model parameters and a new data sharing scheme based on similarity measures.
result Demonstrates superior learning speeds on various tasks and effectiveness of diverse action selection.
Quandle homology was defined from rack homology as the quotient by a subcomplex corresponding to the idempotency, for invariance under the type I Reidemeister move. Similar subcomplexes have been considered for various identities of racks and moves on diagrams. We observe common aspects of these identities and subcompl…
New method estimates animal density using acoustic data, accounting for unknown call identities.
problem Estimating animal density or call density from acoustic data with unknown call identities.
method Monte Carlo Expectation-Maximization (MCEM) method to resolve unknown call identities.
result Estimates are within 15% of expert-constructed estimates and incorporate uncertainty about call identities.
The paper derives curvature identities for 5D and 6D Einstein manifolds.
problem Deriving curvature identities for specific dimensions of Einstein manifolds.
method Using Patterson's curvature identities and the Chern-Gauss-Bonnet Theorem, the paper provides explicit formulae for 5D and 6D Einstein manifolds.
result The curvature identities for 5D and 6D Einstein manifolds are confirmed to be consistent with previous work.
Global Pestov identity proved on frame bundle and related fibrations.
problem Global Pestov identity on frame bundles and fibrations.
method Global Pestov identity on frame bundles and fibrations.
result Global Pestov identity on frame bundles and fibrations.
RLINK uses deep reinforcement learning to improve user identity linkage across social networks.
problem Recognizing the same user across different social networks.
method Converts user identity linkage into a sequence decision problem and uses deep reinforcement learning to optimize the linkage strategy.
result Achieves better performance than state-of-the-art methods in experiments on various datasets.
Proves Bochner's identity on graphs using a new auxiliary graph.
problem Extending Bochner's identity to graph theory.
method Introduces a complete tangent graph to prove the identity.
result Validates Bochner's identity on graphs.
Doodles link to commutator identities in a 2-sphere.
problem Understanding commutator identities in free groups via doodles.
method Analyzing doodles with proper noose systems and establishing bijections.
result A bijection between doodles and commutator identities.
This paper tackles computational bottlenecks in federated learning on mobile devices.
problem Computationally heterogeneous mobile devices hinder federated learning efficiency.
method Proposes efficient algorithms to schedule mobile devices based on data heterogeneity.
result Achieves up to 100x speedup and 7% accuracy gain in federated learning.
The paper studies harmonic identity maps on Riemannian manifolds.
problem Understanding harmonicity of identity maps on Riemannian manifolds.
method Constructing new examples and defining a symmetric tensor field.
result New examples of identity harmonic maps are constructed.
Paper detects common subtrees with identical labels in trees.
problem Finding common subtrees with identical label distribution in tree data.
method Developed an algorithm for tree isomorphism and a new compression scheme for trees.
result The method efficiently finds and compresses common subtrees with identical labels.
We investigate the problems of identity and closeness testing over a discrete population from random samples. Our goal is to develop efficient testers while guaranteeing Differential Privacy to the individuals of the population. We describe an approach that yields sample-efficient differentially private testers for the…
Identity-link IRT improves TVD-MI scores without curvature violations.
problem Preserving additivity in TVD-MI scores for efficient LLM evaluation.
method Derives clipped-linear model from Gini entropy maximization, using identity link.
result Identity-link yields lower curvature violations (median curl 0.080-0.150) compared to probit/logit.
The importance of Einstein's geometrization philosophy, as an alternative to the least action principle, in constructing general relativity (GR), is illuminated. The role of differential identities in this philosophy is clarified. The use of Bianchi identity to write the field equations of GR is shown. Another similar …
We use computer algebra to demonstrate the existence of a multilinear polynomial identity of degree 8 satisfied by the bilinear operation in every Lie-Yamaguti algebra. This identity is a consequence of the defining identities for Lie-Yamaguti algebras, but is not a consequence of anticommutativity. We give an explicit…
The paper proves a Basmajian identity for non-Archimedean local fields.
problem Proving Basmajian's identity over non-Archimedean local fields.
method Projective Anosov representations and Berkovich hyperbolic geometry.
result A signed finite sum series identity for Basmajian's identity.
The paper analyzes ridge regression with random features for non-identically distributed data.
problem Analyzing ridge regression performance for data with heterogeneous variance profiles.
method Combining linear-plus-chaos approximation and operator-valued free probability.
result Derives asymptotic equivalents for training and test risks under non-identically distributed data.
In our previous paper (Axiomatic Differential Geometry II-3) we have discussed the general Jacobi identity, from which the Jacobi identity of vector fields follows readily. In this paper we derive Jacobi-like identities of tangent-vector-valued forms from the general Jacobi identity.
Discover new identities linking hypersurface mean curvatures.
problem Understanding mean curvatures of hypersurfaces in Riemannian manifolds.
method Developed three most general Minkowski or Hsiung-Minkowski identities.
result Classical Minkowski identity is natural to all Riemannian manifolds.
Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
problem Slow iterative refinement process of diffusion-based text-to-image models.
method Guided Score identity Distillation with Long and Short Classifier-Free Guidance.
result Achieves state-of-the-art FID performance with competitive CLIP score.
We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the …
Graded identities for hyperbolic surfaces with cusps and cone points.
problem Understanding dilogarithm identities on hyperbolic surfaces.
method Establishing graded versions of Bridgeman's dilogarithm identity.
result Applications to the study of orthogeodesics.
We give a curvature identity derived from the generalized Gauss-Bonnet formula for 4-dimensional compact oriented Riemannian manifolds. We prove that the curvature identity holds on any 4-dimensional Riemannian manifold which is not necessarily compact. We also provide some applications of the identity.
New energy identity found for biharmonic maps into spheres.
problem Establishing energy identity for biharmonic maps in supercritical dimensions.
method Adapting Lin-Rivière's strategy for sphere-valued maps.
result Energy identity for stationary biharmonic maps into spheres in supercritical dimensions n≥5. New identities link Frobenius elements to Jones-Wenzl projectors at roots of unity.
problem Understanding relationships between Frobenius elements and Jones-Wenzl projectors at roots of unity.
method Obtained skein identities relating Frobenius elements to Jones-Wenzl projectors in the Kauffman bracket skein module.
result Skein identities provide new proofs of the existence of the Chebyshev-Frobenius homomorphism.
The paper proves curvature identities for symplectic connections.
problem Curvature tensor identities on symplectic connections.
method Invariant theory of the symplectic group, analogous to Riemannian or Kahler geometry.
result Describes the first space of p-covariant curvature identities.
In this paper, we obtain a Cartan type identity for curvature-adapted isoparametric hypersurfaces in symmetric spaces of compact type or non-compact type. This identity is a generalization of Cartan-D'Atri's identity for curvature-adapted(=amenable) isoparametric hypersurfaces in rank one symmetric spaces. Furthermore,…
The study finds new infinite dilogarithm identities related to number sequences and continued fractions.
problem Finding new infinite dilogarithm identities.
method Demonstrating families of identities associated with specific number sequences and continued fractions.
result New infinite dilogarithm identities related to Fibonacci, Lucas numbers, convergents of even period continued fractions, and recurrence relations.
Just as the Jacobi identity of vector fields is a natural consequence of the general Jacobi identity of microcubes in synthetic differential geometry, it is to be shown in this paper that the graded Jacobi identity of the Frolicher-Nijenhuis bracket is also a natural consequence of the general Jacobi identity.
Study on functional ellipsoids to decompose the identity.
problem Decompose the identity for functional ellipsoids.
method Construct a decomposition similar to Fritz John's theorem.
result Developed a new approach to functional ellipsoids.
The paper proves identities for hyperconvex Anosov representations and their applications to Cantor sets.
problem Establishing identities for hyperconvex Anosov representations.
method Analyzing holomorphic families of Cantor non-conformal repellers and studying series identities.
result The series is absolutely summable if and only if the Hausdorff dimension of the Cantor set is less than 1.