Sharp bounds found for minimal surface solutions.
problem Finding bounds for minimal surface solutions.
method Analyzing minimal surface equation with specific boundary conditions.
result Sharp bounds established for solutions over certain domains.
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “sharpness minimization”
Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalizationcs.LG
Sharpness minimization algorithms don't solely improve generalization.
problem Why do overparameterized neural networks generalize?
method Theoretical and empirical investigation of two-layer ReLU networks.
result Sharpness minimization algorithms do not always lead to better generalization.
Sharp upper bound found for stable minimal surfaces.
problem Bounding the diameter of stable minimal surfaces.
method Analyzing three-dimensional Riemannian manifolds with specific curvature conditions.
result Sharp upper bound for the diameter of stable minimal surfaces.
DGSAM improves domain generalization by minimizing individual sharpness.
problem Improving domain generalization models that perform well on unseen target domains.
method Shifts DG paradigm toward minimizing individual sharpness across source domains.
result DGSAM reduces performance variance across domains with less computational overhead.
A Sharp Isoperimetric Property of the Renormalized Area of a Minimal Surface in Hyperbolic Spacemath.DG
Minimal surfaces in hyperbolic space have a sharp area bound.
problem Bounding the renormalized area of minimal surfaces.
method Proving an inequality using conformal length of ideal boundary.
result Sharp isoperimetric property of renormalized area.
Sharp-MAML improves MAML by reducing saddle points in few-shot learning.
problem Challenges in optimizing MAML due to complex loss landscape.
method Sharpness-aware minimization applied to MAML.
result Sharp-MAML and its variant outperform plain MAML on few-shot learning tasks.
LSAM optimizes deep learning training with improved efficiency.
problem Inefficiency in distributed large-batch training with Sharpness-Aware Minimization (SAM).
method Integrates SAM's adversarial steps with an asynchronous distributed sampling strategy.
result Higher final accuracy compared to data-parallel SAM.
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscs.LG
ASAM improves deep neural network generalization by adapting sharpness to scale.
problem Fixed-radius sharpness measure is sensitive to parameter scaling, weakening its connection to generalization.
method Introduces adaptive sharpness, a scale-invariant measure, and proposes ASAM for deep learning.
result ASAM significantly improves model generalization performance across various datasets.
Sharp proof of sub-Riemannian length-minimizing curves being at least
problem Smoothness of sub-Riemannian length-minimizing curves
method Study of a class of sub-Riemannian structures, proving regularity
result Theorem 1.1 in [6] is sharp
Sharp area estimates for minimal submanifolds in curved spaces.
problem Estimating the area of minimal submanifolds passing through a specific point.
method Proving sharp area estimates in hyperbolic and spherical spaces.
result Sharp area estimates analogous to Euclidean settings.
Minimizing the free energymath.AP
Sharp stability in Almgren problem solved in any dimension.
problem Quantitative stability in the radial isotropic Almgren problem.
method Developed a theory for estimating the sharp modulus under minimal assumptions.
result Sharp in any dimension, solving the critical mass problem.
SAM improves neural network generalization by penalizing sharpness, clarifying its exact notion and mechanism.
problem Improving deep neural network generalization for various settings.
method Sharpness-Aware Minimization (SAM) technique that penalizes a notion of sharpness of the model.
result SAM regularizes the third notion of sharpness, most likely preferred for practical performance.
Sharp upper bound for minimal graph area in unit ball established.
problem Determining the exact upper limit for the area of minimal graphs intersecting a unit ball.
method Constructing a sequence of minimal graphs via solutions to a Dirichlet problem.
result The areas of constructed minimal graphs tend to the upper bound of .
Study energy-minimizing maps in projective spaces, proving sharp bounds.
problem Finding optimal mappings in projective spaces.
method Proving lower bounds and characterizing energy-minimizing maps.
result Sharp lower bounds and characterization of energy-minimizing maps.
Noise in linear networks minimizes sharpness and leads to shrinkage-thresholding.
problem Minimizing sharpness in diagonal linear networks.
method Stochastic sharpness-aware minimization (SAM) with isotropic noise.
result Noise forces shrinkage-thresholding of true parameters.
Deep linear networks minimize sharpness, avoiding large eigenvalues.
problem Understanding optimization dynamics in deep linear networks for regression.
method Analyzing sharpness (largest eigenvalue of Hessian) of minimizers and gradient flow solutions.
result Gradient flow implicitly regularizes towards flat minima, with sharpness bounded by a constant.
We prove the two theorems of the title, settling two long standing questions in the local theory of singular minimal hypersurfaces. The sharpness of either result is with respect to its hypothesis on the size of the allowable singular sets. The proofs of both theorems rely heavily on the author's recent regularity and …
Sharp bounds on ERM's minimal error in regression.
problem Understanding ERM's performance in regression tasks.
method Sharp lower bounds for ERM in random and fixed design settings.
result ERM's performance depends on the global or local complexity of the model.
New insights into network generalization show learning rate affects both norm and sharpness.
problem Understanding the generalization of overparameterized networks.
method Empirical analysis and theoretical proof of the trade-off between norm and sharpness.
result Learning rate influences both norm and sharpness, neither alone minimizes generalization error.
We classify local minimizers of among all conformally flat metrics in the Euclidean -ball, , for which the boundary has unit volume, subject to an ellipticity assumption. We also classify local minimizers of the analogous functional in the critical dimension . If minimiz…
New algorithm avoids spurious sharpness minimization for NLP models.
problem SAM fails in NLP, leading to performance degradation.
method Developed Functional-SAM, which modifies logit statistics instead of function geometry.
result Functional-SAM and combined methods outperform AdamW and SAM in NLP tasks.
Monge SAM: Robust Reparameterization-Invariant Sharpness-Aware Minimization Based on Loss Geometrycs.LG
Monge SAM improves deep learning by making sharpness-aware minimization invariant to reparametrizations.
problem Non-invariance of sharpness-aware minimization (SAM) to reparametrizations.
method Introduces Monge SAM, a reparametrization-invariant version of SAM using a Riemannian metric.
result Monge SAM enhances robustness and generalization compared to previous methods.
In this note, we prove the sharp Davies-Gaffney-Grigor'yan lemma for minimal heat kernels on graphs.
Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferabilitycs.LG
SAM minimizes loss sharpness, improving adversarial transferability.
problem Improving adversarial transferability of deep neural networks.
method Evaluating surrogate models trained with seven minimizers, focusing on loss sharpness and flat neighborhoods.
result SAM minimizes loss sharpness, leading to better adversarial transferability.
Overparameterization enhances SAM's effectiveness in minimizing sharpness.
problem Improving generalization in deep neural networks.
method Analysis of Sharpness-Aware Minimization (SAM) under varying degrees of overparameterization.
result Overparameterization significantly improves SAM's performance, particularly in noisy and sparse settings.
Sharp curvature bounds for minimal graphs over unit disk.
problem Proving sharp curvature bounds for minimal graphs.
method Analyzing minimal graphs over unit disk, using Heinz constant and Hopf constant.
result Improved estimate for curvature of minimal graphs and sharp inequality.
We prove a Sobolev inequality which holds on submanifolds in Euclidean space of arbitrary dimension and codimension. This inequality is sharp if the codimension is at most 2. As a special case, we obtain a sharp isoperimetric inequality for minimal submanifolds in Euclidean space of codimension at most 2.
Improves model generalization by minimizing loss sharpness.
problem Overparameterized models often fail to generalize well despite low training loss.
method Sharpness-Aware Minimization (SAM) minimizes both loss value and sharpness.
result SAM improves model generalization across various datasets and models.
Sharp lower bound found for area of vector fields on spherical annuli.
problem Finding the minimum area of unit vector fields on spherical annuli.
method Established a sharp lower bound through mathematical analysis.
result Sharp lower bound for the area of unit vector fields on spherical annuli.
Sharp lower bounds for modular invariants and Dehn twist coefficients in genus 2 and 3.
problem Finding sharp lower bounds for modular invariants and Dehn twist coefficients.
method Analyzing the relation between fractional Dehn twists and modular invariants, classifying pseudo-periodic maps, and proving rigidity properties.
result Sharp lower bounds for modular invariants and Dehn twist coefficients in genus 2 and 3.
DASH improves ensemble generalizability by encouraging diverse, flat loss landscapes.
problem Improving generalization and robustness of deep ensembles.
method DASH promotes diversity and flatness in deep ensembles by encouraging base learners to move towards low-loss regions of minimal sharpness.
result DASH improves ensemble generalizability, as demonstrated by extensive empirical evidence.
Minimal surfaces in a ball have limited area.
problem Bounding the area of genus zero minimal surfaces in a unit ball.
method Proving an area inequality and showing convergence of saturating sequences.
result The area of each nonflat surface is less than its radial projection, with sharp asymptotic bounds.
Researchers found the first and second eigenvalues are Courant-sharp on a Möbius strip.
problem Determining Courant-sharp eigenvalues on a Möbius strip.
method Analyzing the eigenvalues and nodal patterns of the Möbius strip.
result Only the first and second eigenvalues are Courant-sharp on the Möbius strip.
Sharp Liouville theorem for minimal graphs on manifolds with nonnegative Ricci curvature.
problem Characterizing smooth solutions to minimal hypersurface equations on manifolds with nonnegative Ricci curvature.
method Gradient estimate for minimal graphs over with small linear growth of the negative parts of graphic functions via iteration.
result Every smooth solution to minimal hypersurface equation on is a constant provided has sublinear growth for its negative part.
Given a closed Riemannian manifold , we prove the compactness of the space of singular, minimal hypersurfaces in whose volumes are uniformly bounded from above and the -th Jacobi eigenvalue 's are uniformly bounded from below. This generalizes the results of Sharp and Ambrozio-Carl…
The paper proves a Wulff inequality for minimal submanifolds with boundary in Euclidean space.
problem Proving a Wulff inequality for minimal submanifolds with boundary.
method Associating a nonnegative anisotropic weight to the boundary of minimal submanifolds and proving the inequality.
result The Wulff inequality constant is independent of the weights and depends only on and .
Sharp inequalities for curved surfaces and cones.
problem Optimizing areas in nonpositively curved spaces.
method Proving inequalities for disks and triangles in cones.
result Minimal area properties for specific shapes in cones.
This work analyzes statistical properties of SAM, showing it outperforms GD.
problem Improving deep neural network generalization through flatter solutions.
method Directly studies statistical performance of Sharpness-Aware Minimization (SAM).
result SAM has smaller prediction error than Gradient Descent (GD) under certain conditions.
Optimizes sharp curvature inequality on spheres, proving near-minimizers are close to standard metric.
problem Optimizing total -curvature on spheres with positive scalar curvature.
method Analyzes metrics conformal to the standard sphere, uses Sobolev norms to measure closeness.
result Near-minimizers of total -curvature are almost the standard metric (up to Möbius transformations).
Sharp results link DLN gradient flow to basis pursuit optimization and GHA phase transitions.
problem Understanding implicit regularization in Diagonal Linear Networks.
method Sharp convergence bounds and characterization of minimizers.
result Gradient flow of DLNs with tiny initialization approximates minimizers of basis pursuit optimization problem.
Paper solves long-standing Gaussian curvature conjecture for minimal graphs.
problem Gaussian curvature of minimal graphs over the unit disk.
method Complex-analytic methods, conformal harmonic parameterization.
result Sharp estimate for Gaussian curvature at the origin of minimal graphs.
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Schedulermath.OC
New adaptive scheduler improves SAM for better model training.
problem Training machine learning models requires selecting a learning rate, which is often difficult and time-consuming.
method Derive Polyak schedulers tailored to SAM-style updates, proving linear convergence for strongly convex objectives and an O(1/T) rate for convex objectives.
result Polyak schedulers achieve comparable or better performance than tuned SAM baselines, reducing the need for learning-rate tuning.
SAM improves deep learning tasks by promoting balancedness, reducing outlier impact.
problem Improving generalization in deep learning tasks, especially with scale-invariant problems.
method Introduces balancedness as a new concept to depict global behaviors of SAM, focusing on the difference between squared norms of two variables.
result SAM promotes balancedness and is data-responsive, outperforming SGD in outlier scenarios.
Using the weak solution of Inverse mean curvature flow, we prove the sharp Minkowski-type inequality for outward minimizing hypersurfaces in Schwarzschild space.
Sharp curvature estimates for mean curvature flow in spheres.
problem Understanding the behavior of surfaces evolving under mean curvature flow in spheres.
method Proving asymptotically sharp curvature pinching estimates and using them to derive derivative and convexity estimates.
result Partial classification of singularity models and new rigidity results for ancient solutions.
This work connects SAM to variational inference and evaluates its performance.
problem Improving generalization of gradient-based learning by finding flat minima.
method Establishes connections between SAM and Mean-Field Variational Inference (MFVI), and evaluates variational algorithms combining or interpolating between SAM and MFVI.
result SAM-like updates can be used as a drop-in replacement for the reparametrisation trick.
Study finds only first and second eigenvalues are Courant-sharp for flat Klein bottle and cylinders.
problem Determining Courant-sharp eigenvalues for compact flat surfaces.
method Analyzing flat Klein bottle and cylinders, proving only first and second eigenvalues are Courant-sharp.
result Only first and second eigenvalues are Courant-sharp for flat Klein bottle and cylinders.
Label noise SGD converges to a simple model with a single linear feature.
problem Understanding the simplicity bias in neural network training.
method Analyzing the convergence of label noise SGD on two-layer neural networks.
result Label noise SGD converges to a model with a single linear feature.