Study LASSO for high-dimensional VAR models with weakly dependent innovations.
problem Understanding sparse regularization in high-dimensional VAR models with weakly dependent innovations.
method LASSO estimation for weakly sparse VAR models with heavy tailed innovations, under L1 mixingale condition. result Oracle properties of LASSO estimation in high-dimensional VAR models with weakly dependent innovations.
New proof for weak mixing in polygonal billiards.
problem Proving weak mixing in polygonal billiards.
method Using Baire category and eigenvalue analysis.
result Billiard flow is weakly mixing for non-rational polygons.
Paper describes links of mixed polynomials with specific properties.
problem Understanding the links of mixed polynomials with nice Newton boundaries.
method Analyzes links constructed from sequences of links associated with compact 1-faces of the Newton boundary.
result Links of singularities of inner non-degenerate mixed polynomials can be described using a specific procedure.
New method detects essential tori in mixed singularity links.
problem Detecting essential tori in mixed singularity link complements.
method Analyzing properties of defining mixed polynomials.
result Explicit criteria for essential tori existence.
MixML unifies analysis of weakly consistent parallel learning.
problem Lack of insight into how communication structure affects convergence in parallel learning.
method Proposes MixML framework for analyzing convergence of weakly consistent parallel machine learning.
result Shows dependency of convergence on mixing time tmix.
The study improves error bounds for statistical learning methods using weakly dependent sums.
problem Investigating error bounds for spectral regularization methods.
method Obtained a Bernstein-type inequality for Banach-valued sums under weak dependence and smoothness assumptions.
result Improved error upper bounds for spectral regularization methods trained on τ−mixing processes. Paper tackles robust deep learning from weakly dependent data with unbounded loss and input.
problem Tackles robust deep learning from weakly dependent data with unbounded loss and input.
method Establishes non-asymptotic bounds for expected excess risk under strong mixing and ψ-weak dependence assumptions. result Derives a relationship between bounds and r, and shows convergence rate close to i.i.d. results for r=∞. Deep learning model uses mixed supervision for brain tumor segmentation.
problem Costly manual tumor segmentation data.
method Extends segmentation networks with an image-level classification branch.
result Significant improvement in segmentation performance.
Study on singularities of specific polynomial functions.
problem Characterizing the topology of singularities of mixed functions.
method Introduced inner non-degenerate mixed functions and used Newton boundary to characterize links.
result Links of singularities can be completely characterized under certain conditions.
Bayesian test assesses dependence between mixed data types.
problem Assessing dependence between text, image, and sound data.
method Bayesian kernelised correlation test using Dirichlet process model.
result Demonstrated effectiveness compared to other methods.
The paper calculates Hausdorff dimensions for Teichmüller geodesics and related sets.
problem Calculating Hausdorff dimensions for specific sets of Teichmüller geodesics.
method Analyzing flat surfaces and Teichmüller geodesics to determine dimensions.
result Hausdorff dimensions for specific sets of Teichmüller geodesics are strictly less than 1 and bounded above by 1/2.
Sharp rates found for learning with dependent data, avoiding sample size deflation.
problem Learning with dependent data and square loss.
method Combining weak sub-Gaussian class and mixed tail generic chaining.
result Achieves a rate that only depends on class complexity and second order statistics.
Paper introduces MSA for weakly supervised covariance alignment in MEG signals.
problem Limited labeled signals in target datasets for MEG applications.
method Mixing model Stiefel Adaptation (MSA) leveraging unlabeled data.
result MSA outperforms recent methods in brain-age regression with MEG signals.
Deep neural nets learn from weakly dependent processes.
problem Learning from ψ-weakly dependent processes. method Deep neural networks for ψ-weakly dependent processes. result Established consistency of empirical risk minimization algorithm and generalization bound.
Research on mixed polynomials, extending non-degeneracy concepts to complex variables.
problem Extending non-degeneracy concepts to mixed polynomials in complex variables.
method Generalization of Mondal's partial non-degeneracy to mixed polynomials, introducing new concepts and proving properties.
result Strong partial non-degeneracy implies isolated singularities, and mixed polynomials that are strongly inner non-degenerate satisfy the strong Milnor condition.
Sparse-penalized deep neural networks improve performance in weakly dependent processes.
problem Nonparametric regression and classification under weak dependence.
method Sparse-penalized deep neural networks with oracle inequalities and convergence rates established.
result The proposed estimators outperform non-penalized ones in simulations.
The paper bounds the excess risk of deep neural networks for weakly dependent processes.
problem Learning with weakly dependent data using deep neural networks.
method Approximation of smooth functions by deep neural networks and a bound on excess risk.
result The excess risk bound for deep learning under weak dependence is close to O(n−1/2) for sufficiently smooth functions. New method uses dendrograms for better mixture model selection and clustering.
problem Selecting the correct number of components in finite mixture models.
method Hierarchical clustering tree derived from overfitted latent mixing measures.
result Consistently selects the true number of mixing components and optimal convergence rate for parameter estimation.
PAPAL algorithm finds mixed Nash equilibria in continuous games.
problem Finding mixed Nash equilibria in non-convex, non-concave games.
method Particle-based Primal-Dual Algorithm (PAPAL) for weakly entropy-regularized min-max optimization.
result PAPAL offers non-asymptotic convergence guarantees for ε-mixed Nash equilibrium. The paper proves positivity of third Chern form for certain vector bundles.
problem Proving positivity of third Chern form for Griffiths positive vector bundles.
method Analyzing mixed discriminants and Schur forms.
result Positivity of third Chern form for Griffiths positive vector bundles.
New method improves sampling from logconcave distributions truncated on polytopes.
problem Sampling from logconcave distributions with polytope constraints.
method Regularized Dikin walks, using Lewis weights.
result Improved mixing time guarantees for various distributions and polytopes.
MALA improves sampling from log-concave densities with faster mixing times.
problem Sampling from strongly log-concave densities efficiently.
method Discretization of Langevin diffusion with accept-reject step.
result MALA requires O(κdlog(1/δ)) steps for TV error δ. Optimizes learning policies in MDPs with weakly communicating structure.
problem Learning optimal policies in weakly communicating MDPs with generative model.
method Span-based approach, reducing to discounted MDPs for analysis.
result First minimax optimal sample complexity bound for weakly communicating MDPs.
We present a new notion of probabilistic duality for random variables involving mixture distributions. Using this notion, we show how to implement a highly-parallelizable Gibbs sampler for weakly coupled discrete pairwise graphical models with strictly positive factors that requires almost no preprocessing and is easy …
New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD.
problem Analyzing mixing times and privacy in projected Langevin algorithm and noisy SGD.
method New bounds derived using PABI framework and optimization problems.
result New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD, showing dependency on gradient regularity.
The paper develops a new min-max theory for minimal disks with free boundary.
problem Constructing minimal disks with free boundary in Riemannian manifolds.
method Develops a min-max theory using harmonic replacement and energy convexity.
result Established an effective version of partial Morse theory for minimal disks with free boundary.
Study nonparametric estimator for Markov chain transition matrices in offline setting.
problem Estimating transition matrices of finite controlled Markov chains from logged data.
method Developed sample complexity bounds and conditions for minimaxity.
result Achieving certain statistical risk requires balancing mixing properties and sample size.
Weakly Einstein Kähler surfaces are characterized and classified.
problem Characterizing and classifying weakly Einstein Kähler surfaces.
method Several conditions and constructions to characterize and classify weakly Einstein Kähler surfaces.
result Classification of weakly Einstein Kähler surfaces with specific properties and construction of new examples.
The study examines weakly Einstein Lie groups and proves non-existence for certain types.
problem Characterizing and proving the non-existence of weakly Einstein Lie groups.
method Analyzing left-invariant metrics on Lie groups and using algebraic properties.
result No weakly Einstein non-abelian 2-step nilpotent Lie groups exist.
Classifies weakly Einstein submanifolds in space forms satisfying specific equalities.
problem Characterizing submanifolds in space forms with certain geometric properties.
method Classification based on Chen's equality and semisymmetric conditions.
result Classification of weakly Einstein submanifolds in space forms.
U-turn chains improve sampling from complex distributions.
problem Sampling from high-dimensional learned distributions.
method Iterative forward-backward diffusion steps with Metropolis-Hastings correction.
result Minimal U-turn dynamics exhibit phase transitions and layer-ordering inversion.
The study explores weakly p-Kähler hyperbolic manifolds.
problem Generalization and application of weakly p-Kähler hyperbolic manifolds. method Investigation of generalizations and applications.
result Exploration of weakly p-Kähler hyperbolic manifolds. Study weakly weighted Einstein-Finsler metrics, showing specific curvature properties and characterizing them.
problem Characterizing weakly weighted Einstein-Finsler metrics.
method Showed isotropic S-curvature under certain conditions. Characterized via navigation expressions and α and β. result Weakly weighted Einstein-Kropina metrics have isotropic S-curvature and can be completely characterized.
The paper provides examples of keen weakly reducible bridge spheres for links in b-bridge position.
problem Characterizing and finding examples of keen weakly reducible bridge spheres.
method Analyzing bridge spheres and their properties in terms of compressing disks and width complex.
result Infinitely many examples of keen weakly reducible bridge spheres for links in b-bridge position.
The study examines weakly Einstein metrics on specific types of manifolds.
problem Investigating weakly Einstein metrics on Sasakian and contact metric manifolds.
method Analyzing scalar curvature constraints and proving manifold properties.
result Classification and properties of weakly Einstein contact metric manifolds.
The paper proves positivity of characteristic forms for certain vector bundles.
problem Characterizing positivity conditions for vector bundles.
method Operator theory, pushforward identities, and differential forms.
result Schur polynomials in Chern forms of Nakano and Griffiths positive vector bundles are positive as differential forms.
Minimal displacement set in weakly systolic complexes is systolic and embeds isometrically.
problem Structure of minimal displacement set in weakly systolic complexes.
method Investigation of minimal displacement set properties and embeddings.
result Minimal displacement set is systolic and embeds isometrically into the complex.
The paper classifies weakly Einstein critical metrics on compact manifolds with boundary.
problem Identifying weakly Einstein critical metrics on compact manifolds with boundary.
method Complete classification for 3D and 4D cases with nonnegative scalar curvature; similar result for higher dimensions with Weyl tensor constraint.
result Complete classification of weakly Einstein critical metrics on compact manifolds with boundary.
Study on extended weakly symmetric spaces, classifying and providing an example.
problem Understanding geometric properties of extended weakly symmetric spaces.
method Classification and presentation of a non-trivial example.
result Existence of extended weakly symmetric spaces established.
Discusses existence of specific types of symmetric manifolds.
problem Existence of weakly cyclic Z-symmetric manifolds. method Analyzes defining conditions and provides examples.
result Provides proper examples of weakly cyclic Z-symmetric manifolds. Curvature estimates and sheeting theorems for weakly stable CMC hypersurfaces established.
problem Establishing curvature estimates and sheeting theorems for weakly stable CMC hypersurfaces.
method Pointwise curvature estimate and sheeting theorem for weakly stable CMC hypersurfaces.
result Effective version of the compactness theorem for weakly stable CMC hypersurfaces.
Study properties of Kenmotsu manifolds with a specific connection.
problem Properties of Kenmotsu manifolds with a semi-symmetric non-metric connection.
method Analysis of generalized recurrent, Ricci-recurrent, weakly symmetric, and weakly Ricci-symmetric properties.
result New findings on properties of Kenmotsu manifolds under semi-symmetric non-metric connection.
There is a well developed theory of weakly symmetric Riemannian manifolds. Here it is shown that several results in the Riemannian case are also valid for weakly symmetric pseudo-Riemannian manifolds, but some require additional hypotheses. The topics discussed are homogeneity, geodesic completeness, the geodesic orbit…
The paper finds many infinite-dimensional weakly reflective PF submanifolds in Hilbert spaces.
problem Minimal submanifolds in Hilbert spaces with reflective properties.
method Introduced weakly reflective PF submanifolds into Hilbert spaces and showed their existence.
result Existence of infinite-dimensional weakly reflective PF submanifolds in Hilbert spaces.
Study differentially private methods for learning Hawkes processes.
problem Lack of thorough analysis on sample complexity for learning Hawkes processes parameters and releasing differentially private versions.
method Developed non-private and differentially private estimators for Hawkes processes parameters.
result Obtained sample complexity results for both private and non-private settings.
Self-supervised attention model improves weakly labeled audio event classification.
problem Efficiently classify audio events with minimal labeled data.
method Develops a self-supervised attention model for weakly labeled audio clips.
result Self-supervised attention model performs comparably to strongly supervised model trained with strong labels.
Classifies weakly Einstein hypersurfaces in spaces of constant curvature.
problem Identifying weakly Einstein hypersurfaces in spaces of constant curvature.
method Complete classification through tensor analysis and geometric properties.
result Hypersurfaces are either products of spaces of constant curvature or rotation hypersurfaces.
Paper proposes a framework to improve weakly supervised learning performance.
problem Weakly supervised data often lead to poor performance due to unreliable labels.
method Guides label quality optimization using a small validation set.
result Framework achieves impressive performance gains with minimal validation data.