New bounds for Dirac eigenvalue involving boundary capacity.
problem Eigenvalue bounds for Dirac operator on hypersurfaces.
method Estimates for Dirac operator on boundaries of compact manifolds.
result Lower bounds for first eigenvalue involving boundary capacity.
New algorithm for shareable arms with load-dependent rewards in stochastic bandits.
problem Learning optimal play strategy with shareable finite-capacity arms in stochastic bandits.
method Developed a capacity estimator and online learning algorithm for MP-MAB with shareable arms.
result Regret upper bound matches the lower bound, validating the algorithm's performance.
Modeling alignment as resource-limited cognitive processes, researchers derive performance bounds.
problem Systematic deviations in feedback-based alignment of large language models.
method Modeling alignment as a two-stage cascade UoHoY given S, with cognitive and total capacities. result Capacity-coupled Alignment Performance Interval derived from Fano and PAC-Bayes bounds.
Upper bounds for Lagrangian capacities of Liouville domains
problem Lagrangian capacity of Liouville domains
method Using S1-equivariant techniques result Extremal Lagrangian torus on the boundary of ellipsoid
Sharp estimates for p-capacity on manifolds with Ricci curvature bounds.
problem Estimating p-capacity on manifolds with Ricci curvature constraints.
method Sharp comparison inequalities, warped-product model ends, and scale-invariant quantities.
result Characterization of equality cases and optimal ranges for normalization parameters.
Sharp upper bounds derived for capacities in hyperbolic and Euclidean spaces.
problem Finding upper limits for the capacity of compact sets in hyperbolic and Euclidean spaces.
method Inverse mean curvature flow, unit-speed normal flow, weak inverse mean curvature flow, inverse anisotropic mean curvature flow.
result Various sharp upper bounds for the p-capacity of compact sets in hyperbolic and Euclidean spaces are derived. Study online learning with delays and capacity constraints, achieving optimal regret bounds.
problem Online learning with delays and capacity constraints.
method Novel scheduling and preemptive techniques, matching upper and lower bounds.
result Achieves optimal regret bounds across all capacity levels.
Study excess capacity in neural networks using Rademacher complexity.
problem Understanding how much capacity deep networks have beyond what's needed for classification.
method Unified Rademacher complexity bounds for function composition and convolutional layers, considering Lipschitz constants and initialization norms.
result There is substantial excess capacity per task, and capacity can be kept similar across different tasks.
Study relates symplectic homology capacity to periodic orbits in Liouville domains.
problem Relating symplectic homology capacity to periodic orbits in Liouville domains.
method Uses positive symplectic homology and Hofer-Zehnder capacity to establish bounds and existence of periodic points.
result Non-zero positive symplectic homology implies finite upper bound for Hofer-Zehnder capacity relative to skeleton and Hamiltonian diffeomorphisms.
New algorithm bounds regret in mediator feedback bandit problems.
problem Mediator feedback bandit game with policy sets.
method Adopting EXP4 algorithm, new regret bounds based on policy set capacity.
result Nearly-matching lower bounds for policy set families.
In this paper we address the following question, given a face representation, how many identities can it resolve? In other words, what is the capacity of the face representation? A scientific basis for estimating the capacity of a given face representation will not only benefit the evaluation and comparison of differen…
Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.
problem Understanding memory and forecasting capabilities in networks with dependent inputs.
method Formulated bounds for memory and forecasting capacities in terms of network size and input properties.
result Proved that memory capacity for linear recurrent networks with independent inputs is given by the rank of the controllability matrix.
Sharp bounds for anisotropic p-capacity of Euclidean compact sets derived using flow methods.
problem Sharp bounds for anisotropic p-capacity of Euclidean compact sets.
method Inverse anisotropic mean curvature flow (IAMCF) and anisotropic Hawking mass.
result Upper bounds for anisotropic p-capacity derived using flow methods.
Using a new method we give elementary estimates for the capacity of non-contractible annuli on cylinders and provide examples, where these inequalities are sharp. Here the lower bound depends only on the area of the annulus. In the case of constant curvature this lower bound is obtained with the help of a symmetrizatio…
Study proves inequalities for mass-capacity on curved spaces.
problem Proving nonnegativity and positive lower bounds of mass on curved spaces.
method Applying mass-capacity inequalities from \cite{M22} to manifolds with nonnegative scalar curvature.
result Sufficient conditions for nonnegativity and positive lower bounds of mass.
Improved neural network capacity analysis using simplified RDT.
problem Analyzing the memorization capabilities of sign perceptron neural networks.
method Developed a simplified, partially lifted Random Duality Theory (fl RDT) approach.
result Concrete capacity bounds universally improve over previous best known ones.
Improved mass-capacity bounds for specific 3D manifolds.
problem Sharp mass-capacity inequality and upper bounds for 3D asymptotically flat manifolds.
method Monotonicity formulas associated with a harmonic potential.
result Improved bounds on ADM mass and capacity in terms of boundary area.
Learning capacity measures model complexity, correlating with test loss and sample size.
problem Understanding model complexity and its relation to test performance.
method Formal correspondence between thermodynamics and inference; learning capacity as a measure of effective dimensionality.
result Learning capacity correlates with test loss and is a small fraction of model parameters.
Estimates for p-capacities on symmetric manifolds.
problem Estimating relative p-capacities on symmetric manifolds. method Rotationally symmetric manifolds and novel volumetric estimates.
result Sharp weak (p,q)-embeddings and precise lower bounds of principal p-frequencies. A note proves the binary perceptron's capacity is less than 0.847.
problem Determining the capacity of the binary perceptron.
method Conditional first moment method combined with known results on the spherical perceptron.
result Proves the binary perceptron's capacity is less than 0.847.
Despite existing work on ensuring generalization of neural networks in terms of scale sensitive complexity measures, such as norms, margin and sharpness, these complexity measures do not offer an explanation of why neural networks generalize better with over-parametrization. In this work we suggest a novel complexity m…
New bounds on neural network capacity for treelike sign perceptrons using RDT.
problem Determining the capacity of treelike sign perceptrons neural networks.
method Random Duality Theory (RDT) to establish upper bounds.
result Mathematically rigorous bounds on network capacity for any number of neurons.
BestChanID identifies the channel with maximal capacity using training sequences.
problem Identifying the channel with maximal capacity among several discrete memoryless channels.
method Formulated as a multi-armed bandit problem, proposed a capacity estimator, and developed gap-elimination algorithms.
result Guaranteed to output the DMC with the largest capacity with a desired confidence.
Differential privacy, a notion of algorithmic stability, is a gold standard for measuring the additional risk an algorithm's output poses to the privacy of a single record in the dataset. Differential privacy is defined as the distance between the output distribution of an algorithm on neighboring datasets that differ …
New analysis tightens memory capacity of Hopfield models using spherical codes.
problem Optimizing memory capacity in modern Hopfield models and Kernelized Hopfield Models.
method Connecting Hopfield models to spherical codes in information theory, establishing an optimal capacity bound and a sub-linear algorithm.
result First tight and optimal asymptotic memory capacity for modern Hopfield models, matching known lower bounds.
The paper defines capacities for minimal graphs over manifolds and proves the half-space property.
problem Characterizing minimal graphs and their properties over manifolds.
method Defining capacities using relative volume, studying solutions of bounded variation, and analyzing boundary behavior.
result Proves the half-space property for M-parabolic manifolds. WGANs improve probability distribution approximation with depth and width trade-offs.
problem Approximating complex probability distributions accurately.
method Wasserstein GANs with GroupSort discriminators, quantified generalization bound.
result High-capacity discriminators are crucial for WGANs' performance.
New analysis shows capacity of treelike neural networks with various activations.
problem Analyzing the capacity of treelike neural networks with diverse activations.
method Utilized Random Duality Theory and its partially lifted version to handle various activations.
result The capacity of treelike neural networks decreases for large network width but converges to a constant value.
Study shows mass-capacity inequality for specific geometric manifolds.
problem Establishing mass-capacity inequality for certain geometric manifolds.
method Using conformally flat manifolds with nonnegative scalar curvature.
result Equality implies harmonically conformal to a specific subset of Euclidean space.
The study uses symplectic capacities to bound the systole on the sphere.
problem Bounding the systole on the sphere using symplectic capacities.
method Using symplectic capacities and properties of fiberwise balanced hypersurfaces.
result Upper bounds on the systole in terms of geometric data and β. Adding noise controls capacity of function compositions.
problem Large capacity of function compositions with bounded capacity classes.
method Adding Gaussian noise to the output of F before composing with H. result Noise effectively controls the capacity of H∘F, offering a general recipe for modular design. We study the volume of extrinsic balls and the capacity of extrinsic annuli in minimal submanifolds which are properly immersed with controlled radial sectional curvatures into an ambient manifold with a pole. The key results are concerned with the comparison of those volumes and capacities with the corresponding entit…
New measure FTC quantifies how much a ReLU network can fine-tune.
problem Analyzing memorization capacity in fine-tuned neural networks.
method Defined Fine-Tuning Capacity (FTC) for additive fine-tuning of ReLU networks.
result Upper and lower bounds on FTC for 2 and 3-layer ReLU networks.
A long standing open problem in the theory of neural networks is the development of quantitative methods to estimate and compare the capabilities of different architectures. Here we define the capacity of an architecture by the binary logarithm of the number of functions it can compute, as the synaptic weights are vari…
Study proposes local effective dimension to measure model capacity and generalization error.
problem Capturing the generalization power of machine learning models.
method Proposes local effective dimension as a capacity measure.
result Local effective dimension bounds the generalization error and correlates well with it.
Through using the semidiameter (in connection to: the mean radius and surface radius) of a convex closed hypersurface in Rn≥2 as an sharp upper bound of the variational (1,n)∋p-capacity radius, this paper settles a restriction/variant of S.-T. Yau's \cite[Problem 59]{Yau} from the surface area to t…
New complexity measure helps in agnostic reinforcement learning with or without access to MDP dynamics.
problem Understanding the number of rounds needed to learn an ε-suboptimal policy in unknown MDPs.
method Introducing spanning capacity as a new complexity measure and developing POPLER algorithm.
result There is a separation between generative and online access models for agnostic learnability.
An action selector associates, in a suitable way, to each compactly supported Hamiltonian on a symplectic manifold an action value of the Hamiltonian. Action selectors are known to exist for a broad class of symplectic manifolds. We show how the existence of an action selector leads to sharp energy capacity inequalitie…
Two potential bottlenecks on the expressiveness of recurrent neural networks (RNNs) are their ability to store information about the task in their parameters, and to store information about the input history in their units. We show experimentally that all common RNN architectures achieve nearly the same per-task and pe…
Capacity-Constrained Online Convex Optimization with Delayed Feedback
problem Online learning with delayed feedback under a hard capacity constraint
method Reduction to a delayed and weighted OCO problem using a scheduler
result First regret guarantees for capacity-constrained OCO under convex and strongly convex losses
The paper extends IPC framework to stationary physical systems and validates it with a photonic system.
problem Characterizing the computational capabilities of stationary physical systems in a principled, data-efficient way.
method Extended IPC framework, established fundamental results, derived asymptotic bias, introduced data-efficient estimation methods.
result IPC strongly correlates with machine-learning performance and provides a reliable estimate of system dimensionality.
Study the relative volume function on AH manifolds and its applications.
problem Characterize the height of geodesic defining functions and capacity of balls.
method Define and analyze the relative volume function, proving its boundedness and regularity.
result Uniformly bounded relative volume function at infinity, bound dependent only on dimension.
The paper connects mass, harmonic functions, and capacity in asymptotically flat 3-manifolds.
problem Connections among ADM mass, harmonic functions, and capacity in asymptotically flat 3-manifolds.
method New formulae for ADM mass via harmonic functions, monotone quantities, and geometric inequalities.
result The mass-to-capacity ratio is bounded below by 1 - sqrt(normalized Willmore functional of the boundary).
Given a surface in an asymptotically flat 3-manifold with nonnegative scalar curvature, we derive an upper bound for the capacity of the surface in terms of the area of the surface and the Willmore functional of the surface. The capacity of a surface is defined to be the energy of the harmonic function which equals 0 o…
Dropout controls model capacity in deep learning and matrix completion.
problem Controlling model capacity in deep learning and matrix completion problems.
method Investigates dropout's effect on model capacity and Rademacher complexity.
result Dropout induces a regularizer that controls model capacity in expectation.
We use drifted Brownian motion in warped product model spaces as comparison constructions to show p-hyperbolicity of a large class of submanifolds for p≥2. The condition for p-hyperbolicity is expressed in terms of upper support functions for the radial sectional curvatures of the ambient space and for the rad…
Scattering networks maximize separation on low-dimensional data.
problem Maximizing separation capacity on low-dimensional datasets.
method Characterize and bound separation capacity for feature extractors, then apply to scattering networks with specific criteria.
result Design criteria for scattering networks to maximize separation on low-dimensional data.
Nonlinear RNNs' memory capacity varies widely, making it impractical.
problem The usefulness of memory capacity as a metric for linear RNNs is questioned.
method Analysis of random nonlinear RNNs with varying input scales.
result Memory capacity of nonlinear RNNs is arbitrary and impractical.