In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to understanding why deep networks generalize well. One of the key elements of super-converge…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Super Learning”
A new method improves super learner validation efficiency.
problem Improving the efficiency of super learner validation.
method Bootstrap Bias Corrected Cross Validation applied to Super Learning.
result Bootstrap Bias Corrected Cross Validation proved efficient and cost-effective.
Study shows zero-shot super-resolution in neural operators is impossible in many cases.
problem Understanding the theoretical limits of zero-shot super-resolution in neural operators.
method Systematic theoretical study including information-theoretic and generalization bounds analysis.
result Zero-shot super-resolution is information-theoretically impossible in many settings.
Develops a new density ratio estimator for causal inference.
problem Estimation of density ratio functions in statistics.
method Super learning approach with a novel loss function.
result Empirical validation of the density ratio super learner's performance.
We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin classifier in 1D. For general learners, we provide a …
Super-OT combines GANs and optimal transport for lineage tracing.
problem Lineage tracing in single-cell RNA-seq data.
method Supervised learning framework with GANs for optimal transport.
result Super-OT outperforms Waddington-OT in predicting cell differentiation outcomes.
Study super cluster algebras from super Plücker and Ptolemy relations.
problem Developing super cluster algebra structure in super Grassmannians.
method Analyzing super Plücker and Ptolemy relations, developing super cluster structure.
result New simple form of super Plücker relations for $\Gr_{r|1}(n|1)$.
Graph machine learning and Super-App data improve credit risk prediction for financial inclusion.
problem Improving credit risk prediction for financial inclusion.
method Two graph-based experiments using centrality, behavior, and transactionality features.
result Graph features enhance credit risk models, leading to more inclusive financial systems.
Deep learning has become very popular for tasks such as predictive modeling and pattern recognition in handling big data. Deep learning is a powerful machine learning method that extracts lower level features and feeds them forward for the next layer to identify higher level features that improve performance. However, …
Super-AND improves unsupervised embedding learning with 89.2% accuracy on CIFAR-10.
problem Extracting good representations from data without labels.
method Super-AND uses unique losses to gather similar samples and maintain features.
result Super-AND achieves 89.2% accuracy on CIFAR-10 image classification.
Super twisted productsmath.DG
The paper defines and analyzes curvature tensors on super twisted product spaces.
problem Investigating curvature tensors on super twisted product spaces.
method Defined -curvature tensor, computed curvature tensors and Ricci tensors, and studied curvature flatness.
result Mixed Ricci-flat super twisted product semi-Riemannian manifolds can be expressed as super warped product manifolds.
With the usual definition of a super Hilbert space and a super unitary representation, it is easy to show that there are lots of super Lie groups for which the left-regular representation is not super unitary. I will argue that weakening the definition of a super Hilbert space (by allowing the super scalar product to b…
We establish a higher generalization of super L-infinity-algebraic T-duality of super WZW-terms for super p-branes. In particular, we demonstrate spherical T-duality of super M5-branes propagating on exceptional-geometric 11d super spacetime.
Unified super-symmetry and higher fluxes using super-Lie-infinity algebras.
problem Unified extended super-symmetry and higher flux densities.
method Using super-Lie-infinity algebras and their extensions and cyclifications.
result Derivation of topological T-duality laws from super-Lie-infinity structure.
Researchers create holographic super-embeddings for M5 and M2 branes.
problem No concrete examples of super-embeddings for M5 and M2 branes existed.
method Constructed explicit holographic super-embeddings of probe M5 and M2 branes into their super-AdS backgrounds.
result Explicit holographic super-embeddings of M5 and M2 branes were successfully constructed.
Super learner with Huber loss improves cost prediction and causal effect estimation in healthcare expenditure data.
problem Challenges in modeling healthcare expenditure distributions with standard super learning methods.
method Proposes a super learner using Huber loss, a robust loss function that down-weights outliers.
result Demonstrates appreciable finite-sample gains in cost prediction and causal effect estimation.
Recent years have witnessed growing interest in machine learning-based models and techniques for low-dose X-ray CT (LDCT) imaging tasks. The methods can typically be categorized into supervised learning methods and unsupervised or model-based learning methods. Supervised learning methods have recently shown success in …
Develops Riemannian geometry for noncommutative super surfaces.
problem No specific problem stated; focuses on mathematical development.
method Introduces metric and connections on noncommutative super surfaces, showing compatibility and zero torsion under certain conditions.
result Noncommutative super surfaces have a well-defined Riemannian geometry with properties analogous to classical Riemannian geometry.
Defines super stable maps and proves quotient superorbifolds for genus zero.
problem Defines stable supercurves and super stable maps of genus zero.
method Uses labeled trees and slice theorem for super Lie groups.
result Proves moduli space of stable supercurves and super stable maps are quotient superorbifolds.
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.
Riemann surfaces are two-dimensional manifolds with a conformal class of metrics. It is well known that the harmonic action functional and harmonic maps are tools to study the moduli space of Riemann surfaces. Super Riemann surfaces are an analogue of Riemann surfaces in the world of super geometry. After a short intro…
New deep learning method improves 4D Flow MRI super-resolution under domain shift.
problem Domain shift in low-resolution 4D Flow MRI data.
method Distributional deep learning framework for domain generalization.
result Framework significantly outperforms traditional methods in real data applications.
New theorem disproves Angle Defect for super triangles.
problem Angle Defect Theorem for N=1 super hyperbolic geometry.
method Action of OSp(1|2) on real super Minkowski space and brute-force computation.
result Disproves Angle Defect Theorem and provides novel additive function.
The underlying even manifold of a super Riemann surface is a Riemann surface with a spinor valued differential form called gravitino. Consequently infinitesimal deformations of super Riemann surfaces are certain infinitesimal deformations of the Riemann surface and the gravitino. Furthermore the action functional of no…
The paper studies special warped products with a specific connection on super Riemannian manifolds.
problem Investigating curvature and Ricci tensors on super warped product spaces with a semi-symmetric non-metric connection.
method Defined a semi-symmetric non-metric connection, computed curvature and Ricci tensors, and introduced and analyzed two types of super warped product spaces.
result Conditions for two super warped product spaces with a semi-symmetric non-metric connection to be Einstein spaces are provided.
Few-shot graph classification on graphs with limited labeled examples.
problem Limited labeled data for graph classification.
method Graph spectral measures to cluster graphs into super-classes, then use GNNs.
result Improved classification performance on few-shot graph classification tasks.
HighRes-net enhances satellite imagery by fusing multiple low-res views.
problem Super-resolving satellite imagery for reliable monitoring of human impact.
method End-to-end deep learning approach for multi-frame super-resolution.
result HighRes-net outperformed in European Space Agency's MFSR competition.
Super tau-covers extend bihamiltonian hierarchies' symmetries.
problem Extending symmetries of bihamiltonian hierarchies.
method Constructing super tau-covers for bihamiltonian integrable hierarchies.
result Symmetries of bihamiltonian hierarchies extended to super tau-covers.
We derive the canonical forms of super Riemannian metrics and the local isometry groups of such metrics. For certain super metrics we also compute the simply connected covering groups of the local isometry groups and interpret these as local spin groups of the super metric. Using a generalization of a Theorem of Rogers…
A super Lie group is a group whose operations are mappings in the sense of Rogers. Thus the underlying supermanifold possesses an atlas whose transition functions are functions. Moreover the images of our charts are open subsets of a graded infinite-dimensional Banach space since our space of …
GANs can learn hierarchical distributions in real-world images efficiently.
problem Understanding and efficiently learning complex, real-world distributions with GANs.
method Formally studying how GANs can learn hierarchically generated distributions close to real-life image distributions using SGDA.
result Training GANs via SGDA can efficiently learn distributions with a 'forward super-resolution' structure, both in sample and time complexities.
Background and objective: Stacking is an ensemble machine learning method that averages predictions from multiple other algorithms, such as generalized linear models and regression trees. An implementation of stacking, called super learning, has been developed as a general approach to supervised learning and has seen f…
Super Learner combines dynamic predictions from various models to improve survival estimates.
problem Challenges in obtaining optimal survival estimates for liver failure risk.
method Super Learner framework combining machine learning and statistical procedures.
result Super Learner outperformed individual models in primary biliary cholangitis application.
The study uses unsupervised machine learning to identify top European football teams.
problem Selecting teams for the new European football Super League.
method Used Laplacian eigenmaps clustering on performance data.
result Successfully identified four clusters of teams based on performance metrics.
Let be a super Riemann surface with holomorphic distribution and a symplectic manifold with compatible almost complex structure . We call a map a super -holomorphic curve if its differential maps the almost complex structure on to . Such a super -holomorp…
The paper develops a theory of -superrings and their superschemes.
problem Developing a theory for -superrings and superschemes.
method Proving an equivalence between categories of fair affine -superschemes and fair -superrings.
result A key equivalence between fair affine -superschemes and fair -superrings.
Characterizes super-replication prices in a financial market model.
problem Characterizing prices in a financial market model.
method Characterizes prices as the supremum of mono-prior super-replication prices through extreme priors and martingale measures.
result Super-replication prices are the supremum of mono-prior super-replication prices.
Scheme resolves super-brane topology via equivariant structures.
problem Topological issues in super-brane dynamics.
method Geometric scheme for Green-Schwarz cocycles, equivariant structures.
result Equivariant structures resolve super-brane topology.
Defines super projective modules and explores their properties.
problem Exploring the geometric-algebraic link in super geometry.
method Defined and explored super projective modules over supersmooth functions.
result Module of vector fields over a supersphere is a super projective module.
This article provides a brief discussion of the functional of super Riemann surfaces from the point of view of classical (i.e. not "super-) differential geometry. The discussion is based on symmetry considerations and aims to clarify the "borderline" between classical and super differential geometry with respect to the…
Matrix formulas for super Teichmüller spaces generalize previous work and yield super λ-lengths.
problem Calculating super λ-lengths on bordered surfaces with marked points.
method Using holonomy matrices of elements in the supergroup OSp(1|2) to compute super λ-lengths in decorated super Teichmüller spaces.
result Matrix formulas for arcs on bordered surfaces yield super λ-lengths in Penner-Zeitlin's decorated super Teichmüller space.
3d Super Hyperbolic Geometrymath.GT
Extends Wigner's representation to study super hyperbolic geometry.
problem Understanding geometry in super hyperbolic three-space.
method Extended Wigner's representation of the Lorentz group to OSp_C(1|2) and applied to Minkowski (3,1|4)-dimensional super space.
result Proof of divergence of the volume of a typical ideal tetrahedron in super hyperbolic three-space.
Extends differential geometry concepts to manifolds with super tangent bundles.
problem No specific problem stated; extending differential geometry to super tangent bundles.
method Introduces super tangent bundle and extends differential geometry concepts.
result Basic notions of differential geometry extended to manifolds with super tangent bundles.
Daily streamflow forecasting through data-driven approaches is traditionally performed using a single machine learning algorithm. Existing applications are mostly restricted to examination of few case studies, not allowing accurate assessment of the predictive performance of the algorithms involved. Here we propose sup…
Paper constructs super integrable systems on color Lie algebra.
problem Super integrable systems on color Lie algebra.
method Using non-isospectral problems with matrices from color Lie algebra , constructing (1+1)- and (2+1)-dimensional systems.
result Super integrable systems and their Hamiltonian structures constructed on color Lie algebra .
SLEM: Machine Learning for Path Modeling and Causal Inference with Super Learner Equation Modelingstat.ML
SLEM uses machine learning to improve causal inference from observational data.
problem Improving causal inference from observational data using non-linear relationships.
method Super Learner Equation Modeling integrating machine learning ensembles.
result SLEM provides consistent and unbiased estimates of causal effects.
Note on instabilities in super-time-stepping methods for Heston model.
problem Instabilities in super-time-stepping methods applied to Heston model.
method Exploration of explicit super-time-stepping schemes (RK-Chebyshev, RK-Legendre) for Heston model.
result Relevance of stability remarks beyond super-time-stepping schemes.
We define a super analog of the classical Plücker embedding of the Grassmannian into a projective space. One of the difficulties of the problem is rooted in the fact that super exterior powers are not a simple generalization from the completely even case (this works only for when it is possible to us…