Dropout increases the generalization of neural networks by expanding the weight space.
problem Understanding and improving the generalization of neural networks.
method Introducing weight expansion and showing that dropout leads to it.
result Dropout increases the generalization of neural networks by expanding the weight space.
Paper generalizes CR Obata theorem to weighted Sasakian manifolds.
problem Deriving eigenvalue estimates for weighted Kohn Laplacian.
method Derived weighted CR Reilly's formula and applied to Sasakian manifolds.
result CR Obata theorem proven for weighted Sasakian manifolds.
Proves positive mass theorem for non-spin weighted manifolds.
problem Proving the positive mass theorem for non-spin weighted manifolds.
method Establishing density theorem and generalizing Geroch conjecture.
result Proves positive weighted mass theorem for non-spin weighted manifolds.
DeepWeightFlow generates diverse neural network weights efficiently.
problem Generating complete neural network weights efficiently and accurately.
method Flow Matching in weight space with Git Re-Basin and TransFusion.
result DeepWeightFlow generates high-accuracy neural networks without fine-tuning.
The paper extends spin geometry to weighted manifolds and defines a new mass for Ricci flow.
problem Generalizing spin geometry to weighted manifolds and defining a new mass.
method Investigates spectral properties of the weighted Dirac operator and defines a new mass.
result Defines a new mass for weighted asymptotically Euclidean manifolds and shows its monotonicity under Ricci flow.
The abstract develops weighted Ricci curvature in Lorentz-Finsler geometry and extends singularity theorems.
problem Extending singularity theorems in weighted Lorentz-Finsler geometry.
method Generalizing Jacobi, Riccati, and Raychaudhuri equations; applying generalized Bishop inequality.
result Weighted Lorentz-Finsler singularity theorems extended.
Estimates causal effects using neural networks for balancing covariates.
problem Estimating causal effects from observational data.
method Neural Balancing Weights (NBW) using α-divergence for density ratio estimation. result Generalized approach for balancing multidimensional data.
A new method to improve deep neural networks using weight rescaling.
problem Overfitting and sensitivity to hyperparameters in weight decay.
method Weight rescaling (WRS) to control weight norm and prevent overfitting.
result WRS outperforms weight decay and other methods in various applications.
Weight Decay induces low-rank weight matrices in neural networks, improving generalization.
problem Improving generalization in neural networks.
method Training ReLU NN with Weight Decay and Stochastic Gradient Descent.
result The weight matrix of a trained NN is approximately rank-two.
New bound for neural networks with full-rank weights, independent of network width.
problem Understanding generalization of neural networks with full-rank weight matrices.
method Using Koopman operators to derive a tighter generalization bound for full-rank weight matrices.
result The bound is tighter than existing norm-based bounds when condition numbers are small.
The paper generalizes K-stability results to singular and weighted settings.
problem Generalizing K-stability to singular and weighted settings.
method Generalization of results in \cite{Li22a} to singular and weighted settings.
result The \(\mathbb{G}\)-uniform weighted K-stability for models implies \(\mathbb{G}\)-coercivity of the weighted Mabuchi functional.
Reverse-weighted portfolios outperform in commodity futures markets.
problem Efficiency of commodity futures markets.
method Permutation-weighted portfolios, rank-based methods.
result Reverse-weighted portfolio outperforms price-weighted portfolio.
Derives integral formulae on weighted manifolds.
problem No specific problem stated; focuses on mathematical derivations.
method Introduces weighted mean sigma-r curvature and uses weighted Newton transformations.
result Derives integral formulae generalizing previous work.
Develops theory of weightings for Lie groupoids and algebroids.
problem Understanding differential geometry of weightings for Lie groupoids and algebroids.
method Extending work on weighted manifolds, defining weighted submanifolds, and developing theories of linear weightings and multiplicative weightings.
result Characterizes infinitesimally multiplicative weightings for Lie algebroids and classifies multiplicative weightings of Lie groupoids.
The paper studies weighted Ricci curvatures and characterizes Randers metrics.
problem Characterizing Randers metrics with weighted Ricci curvatures.
method General weighted Ricci curvatures and characterization of Randers metrics.
result Characterization of Randers metrics with almost isotropic weighted Ricci curvatures.
A new model for detecting overlapping communities in weighted networks.
problem Community detection in overlapping weighted networks with mixed membership and edge weights.
method Mixed membership distribution-free (MMDF) model with an efficient spectral algorithm and fuzzy weighted modularity.
result The MMDF model can estimate community memberships and evaluate community quality for weighted networks.
Pruning large weights improves ANN accuracy without increasing generalization error.
problem Reduction of ANN weights without sacrificing performance and generalization.
method Targeting large weights for pruning in ANNs.
result Pruning large weights leads to higher image classification accuracy and reduced parameter count.
New method generates portfolios using market weights and past data.
problem Creating efficient trading strategies based on market weights.
method Pathwise generation of portfolios using market weights and past data.
result Improved conditions for outperforming the market over time.
Paper generalizes Kreweras triangle using universal sl_2 weight system.
problem Understanding finite order knot invariants.
method Defining a family of polynomials and showing their appearance in the universal sl_2 weight system.
result Polynomials generalize Kreweras triangle, refining normalized median Genocchi numbers.
We consider the tomography problem of recovering a covector field on a simple Riemannian manifold based on its weighted Doppler transformation over a family of curves Γ. This is a generalization of the attenuated Doppler transform. Uniqueness is proven for a generic set of weights and families of curves under a condi…
Improves feature selection in high-dimensional data using LLM-generated weights.
problem Inaccurate LLM-generated weights degrade feature selection performance.
method Integrates LLM-generated weights into prior inclusion probabilities using LLM Sparsity Prior (LSP).
result Improves prediction accuracy and identifies clinically relevant features.
Neural networks generate their own weights using hypernetworks.
problem Generating diverse and non-trivial weights for neural networks.
method Formulate a compromise between accuracy and diversity, using multi-layered perceptrons for mapping.
result Generated weights are diverse and lie on a non-trivial manifold.
New duality found linking neural network weights and activities for better generalization.
problem Understanding and improving neural network generalization.
method Activity-weight duality mapping between neural network layers.
result Generalization loss can be decomposed into geometric factors of sharpness and weight standard deviation.
Optimizes weights for complex test metrics in ML.
problem Complex test metrics and non-identical training/test data.
method Learn weights to optimize test metric on validation set.
result Generalizes to black box and customized test metrics.
Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.
problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.
Diffusion models accurately recover mixture weights from generated samples despite score function insensitivity.
problem Score-based generative models often fail to learn correct relative mode amplitudes (mixture weights) from generated samples.
method Relate diffusion score matching (DSM) loss to mixture weight estimation error, define diffusion score sensitivity index (DSSI), and prove its governing role in mixture weight recovery.
result Generated samples can accurately recover mixture weights from the DSM loss, even when the target score is insensitive to mixture weights.
New method calculates Ricci curvature from distances between weighted volumes.
problem Calculating Ricci curvature for weighted Riemannian manifolds.
method Asymptotic retrieval of generalized Ricci tensor from scaled metric derivatives of Wasserstein 1-distances.
result Limiting coarse curvature of random graphs converges to generalized Ricci tensor.
SGD and weight decay encourage neural networks to learn low-rank weight matrices.
problem The bias of SGD towards low-rank weight matrices in neural networks.
method The study investigates the effect of SGD and weight decay on the rank of weight matrices in neural networks, both theoretically and empirically.
result Training with SGD and weight decay induces a bias towards rank minimization in weight matrices, which becomes more pronounced with smaller batch sizes and stronger weight decay.
AWP improves robustness by flattening weight loss landscape.
problem Improving robustness of deep neural networks against adversarial examples.
method Explicitly regularizes the flatness of weight loss landscape through adversarial weight perturbation.
result AWP forms a double-perturbation mechanism in adversarial training, leading to flatter weight loss landscape.
Corrects distribution shift in target shift scenarios using importance weighting.
problem Analyzes importance weighting for correcting distribution shift under target shift.
method Analyzed importance-weighted kernel ridge regression under target shift.
result Shows that importance weighting corrects the train-test mismatch without altering input-space complexity.
Machine learning approximates Calabi-Yau Hodge numbers from weight systems.
problem Approximating Hodge numbers of Calabi-Yau manifolds from weight systems.
method Neural networks learned Hodge numbers from weight systems, symbolic regression inspired truncation, and machine learning generated new datasets.
result Approximation provides tight lower bounds and dramatically faster computation.
Generative model initializes 2-layer network weights for small datasets.
problem Approximating functions with 2-layer networks using small datasets and gradient-based training.
method Initialize hidden weights with a learned proposal distribution parameterized as a deep generative model. Refine with gradient-based post-processing and regularization.
result Demonstrates effectiveness of the approach with numerical examples.
The study establishes comparison theorems for weighted Finsler manifolds and spacetimes.
problem Analyzing weighted Finsler manifolds and spacetimes with curvature conditions.
method Using weight function and ε-range, the Bonnet-Myers theorem, Laplacian comparison theorem, and Bishop-Gromov volume comparison theorem are formulated. result New comparison theorems for weighted Finsler manifolds and spacetimes are derived, including those for weighted Riemannian manifolds.
Fine-tunes deep neural networks to match theoretical bounds on generalization errors.
problem Improve generalization errors of deep neural networks by constraining weight norms.
method Proposes a two-stage renormalization procedure and a fine-grained SGD algorithm for training DNNs with constrained weights.
result Empirical generalization errors of DNNs are closer to theoretical bounds, improving accuracy.
Proposes volumization for neural networks to control bias-variance tradeoff.
problem Improving generalization and preventing memorization in neural networks.
method Defines a physical volume for weights, interpolating between L2 and L∞ regularization.
result Volumization interpolates between weight decay and clipping, improving generalization.
Generative models learn from biased data using weighted importance.
problem Learning from biased or related data distributions.
method Importance weighting to estimate loss with respect to target distribution.
result Effective in various settings with theoretical guarantees and good performance.
Study of weighted nonlinear flags in symplectic geometry.
problem Understanding the geometry of weighted nonlinear flags.
method Generalizing weighted nonlinear Grassmannians to Frechet manifolds and using them to describe coadjoint orbits.
result Description of coadjoint orbits of Hamiltonian diffeomorphisms using weighted isotropic nonlinear flags.
The CR Obata theorem is extended to weighted Sasakian manifolds.
problem Extending the CR Obata theorem to weighted Sasakian manifolds.
method Deriving the weighted CR Reilly's formula and first eigenvalue estimate for a weighted sub-Laplacian.
result The CR Obata theorem is proven in compact weighted Sasakian manifolds.
Study weightings from singular Lie filtrations.
problem Generalize constructions for singular Lie filtrations.
method Study weightings arising from singular Lie filtrations.
result Generalizes constructions for (regular) Lie filtrations.
Sharp inequality on Siegel domain involving weighted norms and sub-Laplacian.
problem Establishing a Sobolev trace inequality on a specific domain.
method Using weighted norms and fractional powers of sub-Laplacian on Heisenberg group.
result Sharp Sobolev trace inequality on Siegel domain involving weighted norms.
This paper proposes a method to improve few-shot learning by generating multi-level weight-centric features.
problem Improving few-shot learning performance by leveraging both representation power and weight generation capacity.
method A multi-level weight-centric feature learning approach with a weight-centric training strategy and multi-level feature incorporation.
result Significantly outperforms existing methods in low-shot classification benchmarks.
New invariants help solve existence of weighted cscK metrics.
problem Existence of weighted cscK metrics in K-stability.
method Introduced weighted analytic delta invariant and beta invariant.
result Sufficient condition for existence of weighted cscK metrics.
Generative approach speeds hyperparameter tuning for machine learning models.
problem Computational infeasibility of cross-validation and difficulty of fully Bayesian hyper-parameter learning.
method Combines optimization-based approximations and amortization techniques.
result Rapid evaluation of hyper-parameters over grids or ranges, supporting predictive tuning and uncertainty quantification.
Develops a weighting framework to generalize ITRs from source to target populations.
problem Challenges in generalizing ITRs from a source population to a target population with differing characteristics.
method A robust sample weighting framework using a reproducing kernel Hilbert space to balance covariates and improve ITR learning methods.
result Improves ITR estimation for the target population compared to other weighting methods.
A new method uses nearest neighbors for importance weighting.
problem Data covariate shift problems in machine learning.
method Nearest neighbor classification scheme for determining importance weights.
result Demonstrated effectiveness through comparative experiments on various classification tasks.
The paper introduces new Finsler metrics and associated weighted quasi-metrics.
problem Geometric properties of Finsler metrics and quasi-metric spaces.
method Construction of weighted quasi-metrics associated with Finsler metrics.
result Investigation of geometric properties of weighted quasi-metric spaces.
Improved neural networks by averaging late-stage weights.
problem Improving the performance of neural networks.
method Ensemble late-stage weights and average them.
result Augmenting standard models with late-phase weights improves generalization.
Proposes deep weight prior for improving neural network performance.
problem Improving neural network performance with limited training data.
method Defines deep weight prior (DWP) as an implicit distribution and proposes variational inference methods.
result Improves performance of Bayesian neural networks with limited data and accelerates conventional CNN training.