Transformer learns to estimate negative binomial parameters efficiently.
problem Parameter estimation for over-dispersed count data in large screens.
method Pre-trained transformer trained on synthetic data generation to invert parameter to count transformation.
result Method of moments provides faster, more efficient, and better-calibrated estimates.
Bayesian active learning tackles nuisance parameters, leading to bias and dilemmas.
problem Bayesian active learning with nuisance parameters leads to bias and dilemmas.
method Characterizes and mitigates negative interference by accurately estimating nuisance parameters.
result The extent of negative interference can be extremely large, and accurate estimation of nuisance parameters is critical.
The study investigates the impact of negative examples in contrastive learning.
problem Understanding how the number of negative examples affects downstream performance in contrastive learning.
method Theoretical analysis and empirical evaluation of NLP and vision tasks.
result The optimal number of negative examples should scale with the number of underlying concepts in the data.
Constructs metrics with negative constant scalar curvature.
problem Negative constant scalar curvature metrics.
method One-parameter family of complete metrics.
result Verifies positive energy conjecture for these metrics.
Solves Fu-Yau equation for negative slope parameters in arbitrary dimensions.
problem Solving the Fu-Yau equation for negative slope parameters in arbitrary dimensions.
method Solves the Fu-Yau equation for negative slope parameters in arbitrary dimensions.
result First non-trivial solutions of the Fu-Yau equation in any dimension strictly greater than 2.
New approach uses negative controls to estimate causal parameters without completeness conditions.
problem Estimating causal parameters when not all confounders are observed.
method Identification strategy based on minimax learning formulations for general function classes.
result Avoids completeness conditions and uniqueness assumptions on bridge functions.
Constructs 7-manifolds with SO(3) invariant non-negative curvature.
problem Finding exotic spheres with non-negative curvature.
method Six-parameter family of highly connected 7-manifolds constructed with invariant metrics.
result All exotic spheres in 7 dimensions have non-negative curvature.
Investigates maps and properties in spaces with negative dimensions and curvature.
problem Existence of transport maps and local-to-global property in spaces with negative dimensions and bounded Ricci curvature.
method Examines metric measure spaces with negative curvature dimensions and applies reduced curvature-dimension conditions.
result Establishes the existence of transport maps and proves the local-to-global property.
Study shows existence of Strominger system solutions is not stable under complex structure deformations.
problem Stability of Strominger system solutions under complex structure deformations.
method Analyzes stability of solutions to the Strominger system in dimensions six, considering both positive and negative slope parameters.
result Existence of solutions to the Strominger system is neither open nor closed under holomorphic deformations of the complex structure.
New magnetic flow rigidity theorem for negative curvatures.
problem Rigidity of magnetic flows under constant periodic orbit lengths.
method Smooth families of diffeomorphisms and magnetic flows.
result Generalization of Guillemin-Kazhdan result to magnetic flows.
New investment strategy outperforms market with high probability.
problem Investment performance under market conditions.
method Negative-parameter portfolio strategy with market weight inversely proportional to wealth.
result Strategy outperforms market with probability one under specific conditions.
Study stability of curvature-dimension condition for negative dimensions.
problem Stability of curvature-dimension condition with negative dimension parameters.
method Introduced CD(K, N)-condition for N < 0, defined distance d_{\mathsf{iKRW}}, proved convergence stability.
result Limit structure of converging metric measure spaces remains CD(K, N) for N < 0.
SANS uses graph structure to find meaningful negatives for entity and relation embeddings.
problem Finding hard negatives for entity and relation embeddings in knowledge graphs.
method Structure Aware Negative Sampling (SANS) that selects negatives from a node's k-hop neighborhood.
result SANS finds semantically meaningful negatives and is competitive with state-of-the-art approaches.
LSQ+ improves quantization of neural nets with Swish activations, achieving state-of-the-art results.
problem Quantization of neural nets with Swish activations, especially negative activations, leads to significant performance loss.
method Introduces learnable scale and offset parameters for asymmetric quantization, and uses MSE-based initialization for quantization parameters.
result Significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations, achieving up to 5.6% gain with W2A2 quantization of EfficientNet-B0.
A novel method relaxes binary constraints to non-negative spheres for multi-matching and clustering.
problem Optimization problems over binary matrices with injectivity constraints.
method Non-negative spherical relaxation followed by conditional power iteration.
result Automatic adjustment of the continuous parameter related to universe size.
The report analyzes Legendre decomposition for tensor data.
problem Finding effective lower dimensional representations of tensors.
method Theoretical analysis of dual parameters and dually flat manifold properties, followed by experimental verification and clustering.
result Parameters on submanifold cannot be directly used as low-rank representations.
Estimates parameters of a rectified Gaussian distribution using ReLU networks.
problem Estimating parameters of a rectified Gaussian distribution from i.i.d. samples.
method Simple algorithm using O(1/ε2) samples and O(d2/ε2) time. result Estimates distribution up to ε in total variation distance. Invertible DenseNets improve model efficiency and performance.
problem Improving model efficiency and performance in neural networks.
method Enforcing invertibility in DenseNets by satisfying the Lipschitz constraint and proposing a learnable concatenation.
result i-DenseNets outperform Residual Flows in negative log-likelihood on various datasets.
Study on geometry of Dirichlet distributions using Fisher-Rao metric.
problem Understanding the geometry of Dirichlet distributions.
method Analysis of Fisher-Rao metric on Dirichlet distribution parameter space.
result Geodesic completeness and negative sectional curvature of the space.
Study finds minimal hypersurface in convex manifolds with non-negative Ricci curvature.
problem Finding minimal hypersurfaces in manifolds with specific curvature properties.
method Min-max method applied to one-parameter families of hypersurfaces.
result The min-max minimal hypersurface is orientable, of index one and multiplicity one.
New DKPP family controls positive and negative dependence in random subsets.
problem Challenges in seamlessly bridging probabilistic models for positive and negative dependence.
method Introduced DKPP family and developed computational methods for probabilistic operations and inference.
result Controllability of positive and negative dependence demonstrated through numerical experiments.
The classic 2pi-Theorem of Gromov and Thurston constructs a negatively curved metric on certain 3-manifolds obtained by Dehn filling. By Geometrization, any such manifold admits a hyperbolic metric. We outline a program using cross curvature flow to construct a smooth one-parameter family of metrics between the "2pi-me…
Agent-based model for wealth distribution with negative wealth.
problem Modeling wealth distribution with negative wealth and validating against empirical data.
method Agent-based model, Fokker-Planck equation, numerical solution, inverse problem solving.
result Agreement with empirical data of an average error less than 0.16% over 27 years.
Improved estimation for imbalanced data using log odds correction and optimal sampling.
problem Parameter estimation with nonuniform negative sampling for imbalanced data.
method Derive asymptotic distribution of IPW estimator, derive optimal sampling probability, propose likelihood-based estimator.
result Improved estimator has the smallest asymptotic variance.
We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the lp-norm of the parameters. We discuss several implications of Lipschitz parametrization. We present an upper bound of the Kullback-Leibler divergence that allows understanding methods that penalize the …
Improved score matching for non-negative data models.
problem Estimating parameters of non-negative probability density functions.
method Generalized score matching method for non-negative data.
result Improved estimation efficiency and theoretical guarantees.
The study addresses negative transfer in multi-output Gaussian processes by proposing latent structures.
problem Negative transfer in multi-output Gaussian processes leading to decreased performance.
method Defining negative transfer, deriving conditions for avoiding it, proposing latent structures.
result Latent structures can avoid negative transfer and scale to large datasets.
We construct new homogeneous Einstein spaces with negative Ricci curvature in two ways: First, we give a method for classifying and constructing a class of rank one Einstein solvmanifolds whose derived algebras are two-step nilpotent. As an application, we describe an explicit continuous family of ten-dimensional Einst…
The study finds infinitely many 7-manifolds with non-negative curvature but not homotopy equivalent to bundles.
problem Constructing and analyzing non-negative curvature 7-manifolds.
method Constructing a family of 7-manifolds with specific properties and computing their linking forms.
result The family contains infinitely many manifolds not homotopy equivalent to S3-bundles over S4. A new objective function for NMF reduces model complexity and improves accuracy.
problem NMF's error-based objective function can lead to overly complex models.
method MDL-NMF uses minimum description length to balance model complexity and accuracy.
result MDL-NMF outperforms traditional NMF on various datasets.
New model explains price dynamics of Bitcoin with psychological factors.
problem Understanding price variations in cryptocurrency markets with psychological factors.
method Extended agent-based model with heterogeneous psychological parameters.
result Model shows diverse dynamics based on psychological correlation.
Improved HGF networks avoid negative precision errors in volatility updates.
problem Negative posterior precision errors in volatility-coupled nodes of HGF networks.
method Introduced a modified quadratic approximation to variational energy.
result Robust update equations across parameter space that track posterior faithfully.
Given for instance a finite volume negatively curved Riemannian manifold M, we give a precise relation between the logarithmic growth rates of the excursions into cusps neighborhoods of the strong unstable leaves of negatively recurrent unit vectors of M and their linear divergence rates under the geodesic flow. As…
Paper proves geodesic ball maximizes second Robin eigenvalue in non-compact symmetric spaces.
problem Maximizing the second Robin eigenvalue in non-compact rank-1 symmetric spaces.
method Quantitative spectral inequality for the second Robin eigenvalue.
result Geodesic ball maximizes the second Robin eigenvalue among domains of the same volume.
Rigidity results for negatively curved manifolds under small metric perturbations.
problem Stability of negatively curved manifolds under small metric perturbations.
method Local and infinitesimal rigidity results for compactly supported deformations of negatively curved metrics.
result Small metric perturbations of negatively curved metrics result in isometric metrics.
Constructs new steady gradient Ricci solitons for higher dimensions.
problem Finding new steady gradient Ricci solitons with non-negative curvature.
method Constructing continuous families of Ricci flows from spherical polyhedra, proving stability.
result Produces new examples of steady gradient Ricci solitons for n≥4. Paper proposes a method to interpret neural networks by decomposing them into simpler tasks.
problem Understanding the complex nonlinear relationships in trained neural networks.
method Non-negative matrix factorization applied to a trained layered neural network.
result Reveals the roles of hidden units in terms of their contribution to each principal task.
The paper constructs foliations of minimal surfaces in negatively curved 3-manifolds.
problem Constructing foliations of minimal surfaces in negatively curved 3-manifolds.
method Deformations of totally geodesic foliations, using Grassmann bundle and negatively curved metrics.
result The foliations of minimal surfaces are deformations of totally geodesic foliations.
Non-negative blind source separation (BSS) has raised interest in various fields of research, as testified by the wide literature on the topic of non-negative matrix factorization (NMF). In this context, it is fundamental that the sources to be estimated present some diversity in order to be efficiently retrieved. Spar…
Paper accelerates SAGA using sampled negative momentum.
problem Directly accelerating SAGA for optimization problems.
method Proposes SSNM for direct acceleration of SAGA.
result Achieves best known oracle complexity for strongly convex problems.
This paper proposes Dropping Networks for improved transfer learning in natural language understanding tasks.
problem Transfer learning between natural language understanding tasks often suffers from negative transfer.
method Combines Dropout and Bagging (Dropping) for improved transferability in neural networks.
result Improves transfer learning performance and comparable results to state-of-the-art using a fraction of target task data.
Efficiently reduces tensor ranks using mean-field approximation.
problem Low-rank approximation of non-negative tensors.
method Mean-field approximation of tensor rank reduction.
result Our algorithm achieves faster and competitive tensor rank reduction.
A new PGA algorithm ensures stable, robust, and noise-immune solutions for non-negative inverse problems.
problem Stable convergence and suboptimal solutions in inverse problems due to negative values and high sensitivity to hyperparameters.
method A novel multiplicative update proximal gradient algorithm (SSO-PGA) that enforces non-negativity and boundedness through a learnable sigmoid-based operator.
result Significantly surpasses traditional PGA and other state-of-the-art algorithms in performance and stability.
Constructs Einstein metrics on manifolds with specific orbits.
problem Finding Einstein metrics on manifolds with given orbits.
method Continuous families of metrics constructed using vector bundles and R4m+4. result Recovery of Spin(7) metrics A8 and B8. ELU algorithm improves on EM for over-specified Gaussian mixtures.
problem Slow convergence of EM in over-specified Gaussian mixtures.
method Developed ELU algorithm for two-component mixtures, combining exponential location update and gradient descent.
result ELU converges to final statistical radius after logarithmic iterations, resolving open question.
A new SBM for non-negative zero-inflated edge weights in networks.
problem Modeling international trading networks with non-negative zero-inflated edge weights.
method Restricted Tweedie distribution and nodal information accounting.
result Efficient two-step algorithm for estimating covariate effects.
Entire minimal graphs in Heisenberg space have negative Gauss curvature.
problem Characterizing entire minimal graphs in Heisenberg space.
method Defining holomorphic quadratic differentials and using them to describe entire graphs.
result Entire minimal graphs in Heisenberg space have negative Gauss curvature.
We compute the analytic expression of the probability distributions F{FTSE100,+} and F{FTSE100,-} of the normalized positive and negative FTSE100 (UK) index daily returns r(t). Furthermore, we define the alpha re-scaled FTSE100 daily index positive returns r(t)^alpha and negative returns (-r(t))^alpha that we call, aft…