Unbounded output networks improve classification performance.
problem Improving classification accuracy in neural networks.
method Introducing UnBounded output network (UBnet) with unbounded output units and a modified mean-squared error objective.
result UBnets achieve high classification performance on MNIST, CIFAR-10, and CIFAR-100 datasets.
The paper proves neural networks with ReLU and softmax can approximate any function.
problem Approximating functions and class labels in neural networks.
method Extended universal approximator theory to neural networks with ReLU and softmax.
result Neural networks with ReLU and softmax can approximate any function and class labels.
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 ψ ψ -weak dependence assumptions. result Derives a relationship between bounds and r r r , and shows convergence rate close to i.i.d. results for r = ∞ r=\infty r = ∞ . Narrow neural networks have unbounded decision regions.
problem Understanding decision regions of narrow neural networks.
method Analyzing decision regions of neural networks with width ≤ input dimension.
result All connected components of decision regions are unbounded.
Kolmogorov neural networks can represent various types of functions.
problem Representing different types of functions with neural networks.
method Continuous, discontinuous bounded or unbounded activation functions in a two hidden layer model.
result Kolmogorov neural networks can represent continuous, discontinuous bounded and all unbounded multivariate functions.
Sandpile Economics explains how economies can be prone to large crises from small shocks.
problem Capitalist economies' recurrent crises disproportionate to shocks.
method Formal framework interpreting instability as geometric fragility of production networks.
result Curvature of production networks predicts medium-run output dynamics and resilience.
New framework for neural network score estimation in diffusion models.
problem Rigorous guarantees for practical score estimation with neural networks.
method Developed a mathematical framework for score estimation with GD-trained neural networks, addressing optimization and generalization.
result Established minimax-optimal generalization bounds for GD-trained neural networks in diffusion models.
Traditionally, multi-layer neural networks use dot product between the output vector of previous layer and the incoming weight vector as the input to activation function. The result of dot product is unbounded, thus increases the risk of large variance. Large variance of neuron makes the model sensitive to the change o…
New neural network rates for unbounded domains with weighted Sobolev spaces.
problem Improving neural network approximation rates for unbounded domains.
method Embedding results for weighted Fourier-Lebesgue spaces in weighted Sobolev spaces, followed by asymptotic approximation rates.
result Asymptotic approximation rates for shallow neural networks without curse of dimensionality for unbounded domains and Muckenhoupt weights.
New method for manifold fitting under unbounded noise.
problem Noise blurs tangent space estimation, leading to inaccurate manifold recovery.
method Directly estimate tangent spaces at projected points on the manifold, not at sample points.
result Theoretical convergence in high probability for upper bound of manifold distance.
New method for Bayesian neural networks with unbounded weights.
problem Posterior inference for Bayesian neural networks with unbounded weights.
method Conditionally Gaussian representation for efficient posterior inference.
result Interpretable and computationally efficient procedure for posterior inference.
Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.
problem Understanding the impact of noise on the sample complexity of recurrent neural networks.
method Analyzing noisy multi-layered sigmoid recurrent neural networks with independent noise and proving lower bounds.
result Exponential gap in sample complexity between noisy and non-noisy networks, even for small noise values.
We present a new approach to estimating the interdependence of industries in an economy by applying data science solutions. By exploiting interfirm buyer--seller network data, we show that the problem of estimating the interdependence of industries is similar to the problem of uncovering the latent block structure in n…
New analysis shows a gap between Gaussian RKHS and neural networks on unbounded domains.
problem Understanding the function space bias of neural networks compared to Gaussian RKHS.
method Infinite-center asymptotic analysis of neural network Banach space and Gaussian RKHS on unbounded domains.
result Certain functions in Gaussian RKHS have infinite norm in neural network Banach space on unbounded domains.
Robustness to outliers is a central issue in real-world machine learning applications. While replacing a model to a heavy-tailed one (e.g., from Gaussian to Student-t) is a standard approach for robustification, it can only be applied to simple models. In this paper, based on Zellner's optimization and variational form…
Deep neural networks classify unbounded Gaussian mixture data without dimensionality issues.
problem Binary classification of unbounded Gaussian mixture data.
method Deep ReLU neural networks with non-asymptotic upper bounds and convergence rates.
result Deep ReLU networks can classify unbounded Gaussian mixture data without dimensionality constraints.
Framework creates fast, interpretable surrogates for stochastic simulators with unbounded randomness.
problem Creating accurate and fast approximations for stochastic simulators with unbounded randomness.
method Probabilistic surrogate networks that retain structure of reference simulators and enable amortized inference.
result Surrogates accurately model stochastic programs with unbounded random variables and significantly speed up inference.
Theory for deep neural network approximation of score function and its derivatives.
problem Handling data distributions with low-dimensional structure and unbounded support.
method Simultaneous approximation of the score function and its derivatives using deep neural networks.
result Approximation error bounds match literature but relax bounded support requirement.
Neural networks can approximate any L^p functions on R^n.
problem Approximating functions on unbounded domains with neural networks.
method Monotone sigmoid, ReLU, ELU, Softplus, LeakyReLU activation functions.
result Shallow neural networks can arbitrarily well approximate L^p functions on R^n.
New PAC-Bayes training method improves model generalization for unbounded loss.
problem Improving generalization of complex models under unbounded loss.
method Established new PAC-Bayes bound for unbounded loss, jointly training prior and posterior.
result Outperforms existing PAC-Bayes training algorithms and matches ERM accuracy.
The paper tightens bounds on covering numbers for deep ReLU networks.
problem Characterizing the capacity and performance of deep ReLU networks.
method Derives tight lower and upper bounds on metric entropy of ReLU networks.
result Establishes optimality in nonparametric regression via deep networks.
New model classes for function approximation by neural networks defined on domains.
problem Defining novel model classes for function approximation on bounded domains.
method Introducing weighted variation spaces to define new model classes on domains.
result New model classes are strictly larger than classical ones but maintain the same NNA rates.
LLA shows strong performance in Bayesian optimization but has unbounded search space issues.
problem Applying LLA in unbounded search spaces for Bayesian optimization.
method Linearized-Laplace approximation applied to Bayesian optimization problems.
result LLA demonstrates strong performance but also presents unbounded search space challenges.
Two new algorithms improve performance in adversarial bandits with unbounded losses.
problem Adversarial Multi-Armed Bandits with unbounded losses.
method Developed UMAB-NN and UMAB-G for non-negative and general unbounded losses respectively.
result UMAB-NN achieves the first adaptive and scale-free regret bound for non-negative unbounded losses.
Constructs unbounded Kasparov product for sphere embeddings into Euclidean space.
problem Embedding spheres into Euclidean space and their associated Kasparov cycles.
method Constructs unbounded Kasparov cycles, equips with connections, computes unbounded Kasparov product with Dirac operator, identifies index cycles.
result Spectral triple for algebra C ( S n ) C(\mathbb S^n) C ( S n ) differs from round sphere Dirac operator by index cycle. Unbounded convex domains have zero mean curvature on disconnected boundaries.
problem Understanding mean curvature in unbounded convex domains.
method Analyzing mean curvature on disconnected boundary components.
result Mean curvature is zero on disconnected boundary components of unbounded mean convex domains.
The paper proves homotopy equivalences for spaces of unbounded Fredholm operators.
problem Spaces of unbounded Fredholm operators and their properties.
method Analyzing the spaces and proving homotopy equivalences.
result Natural maps between four spaces of unbounded Fredholm operators are homotopy equivalences.
Golden L surface has unbounded bunching of saddle connections
problem Unbounded bunching of saddle connections on translation surfaces
method Translation surface with golden ratio
result Every positive integer K has a ball containing at least K saddle connection periods
This memoir presents a systematic study of the utility maximization problem of an investor in a constrained and unbounded financial market. Building upon the work of Hu et al. (2005) [Ann. Appl. Probab., 15, 1691--1712] in a bounded framework, we extend our analysis to the more challenging unbounded case. Our methodolo…
New inequalities for unbounded functions improve denoising score matching.
problem Statistical error bounds for denoising score matching with unbounded objective functions.
method Derive new concentration inequalities using McDiarmid's inequality and Rademacher complexity bounds.
result Improved statistical error bounds for denoising score matching.
It is shown that the compactly supported identity component of the diffeomorphism group of the 2-dimensional punctured torus T p 2 \mathbb T^2_p T p 2 is an unbounded group. It follows that the fragmentation norm of T p 2 \mathbb T^2_p T p 2 is unbounded.
Study focal surfaces of wave fronts with unbounded curvatures.
problem Characterizing singularities of focal surfaces near non-degenerate singular points.
method Characterizations based on types of singularities and geometrical properties of initial fronts.
result Investigation of Gaussian curvature behavior of focal surfaces.
Study ancient solutions on graphs with unbounded Laplacians, generalizing previous results.
problem Understanding ancient solutions on graphs with unbounded Laplacians.
method Generalizing Colding and Minicozzi's theorem and Hua's result to graphs with unbounded Laplacians.
result The dimension of the space of ancient solutions of polynomial growth is bounded by the dimension of harmonic functions with the same growth.
This paper studies neural networks with bounded norms to avoid the curse of dimensionality.
problem The curse of dimensionality in approximating functions by neural networks.
method Investigates over-parameterized two-layer neural networks with norm constraints in RKHS.
result Improved sample complexity and generalization bounds for neural networks with bounded norms.
New RL policy for unbounded state space with stability guarantee.
problem Traditional RL methods fail for unbounded state space.
method Proposes stability as performance metric, uses Sparse-Sampling-based Monte Carlo Oracle.
result Proposed policy ensures state dynamics remain bounded with high probability.
Study shows unbounded Pontryagin numbers on curved manifolds.
problem Understanding unbounded Pontryagin numbers on curved manifolds.
method Analyzing rational linear combinations of Pontryagin numbers and their relation to the universal elliptic genus.
result Proves existence of unbounded Pontryagin numbers on nonnegatively curved spin manifolds.
Paper tackles online control of linear systems with unbounded noise.
problem Online control of linear systems under unbounded noise with unknown convex cost functions.
method Developed an algorithm achieving i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) high-probability regret under unbounded noise, and established O ( m p o l y ( log T ) ) O({
m poly} (\log T)) O ( m p o l y ( log T )) regret bound for strongly convex costs and sub-Gaussian noise. result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) high-probability regret under unbounded noise, and O ( m p o l y ( log T ) ) O({
m poly} (\log T)) O ( m p o l y ( log T )) regret bound for specific noise and cost conditions. Study solves wealth maximization problem with unbounded mean and volatility.
problem Maximizing terminal wealth with unbounded mean and volatility under Knightian uncertainty.
method Solves utility maximization problem explicitly with Ornstein-Uhlenbeck and GARCH(1) processes.
result First work on unbounded mean and volatility with Knightian uncertainty and nondominated priors.
Constructing VAE Latent Spaces with Prescribed Topology
problem Resolving topological mismatch in VAEs for non-Euclidean data
method A constructive framework for product covering spaces
result Topology-aware latent representations with closed-form KL divergences
AI task delegation faces incentive collapse with unbounded payments as AI accuracy rises.
problem Incentive collapse in AI-assisted task delegation schemes.
method General impossibility result and sentinel-auditing payment mechanism.
result Sentinel-auditing mechanism enforces positive human effort at finite cost, independent of AI accuracy.
UDN adapts depth to data complexity, outperforming standard neural networks.
problem Adapting neural network depth to data complexity.
method Variational inference for infinitely deep neural networks with a novel algorithm.
result UDN outperforms standard neural networks and other infinite-depth approaches.
We show that domains, that allow for convex functions with unbounded gradient at their boundary, are convex.
Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces. To scale up these methods, we extend the celebrated Random Fourier Feature methodology to get an approximation of operator-…
New approach finds solutions to games with unbounded controls.
problem Existence of equilibrium in mean-field games with unbounded controls.
method Weak formulation and new existence/stability results for quadratic-growth generalized McKean-Vlasov BSDEs.
result Existence of equilibrium result for non-Markovian mean-field games with unbounded control space.
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 \mathcal{F} F before composing with H \mathcal{H} H . result Noise effectively controls the capacity of H ∘ F \mathcal{H} \circ \mathcal{F} H ∘ F , offering a general recipe for modular design. The paper provides gradient estimates for Neumann semigroups on manifolds with boundary under unbounded curvature conditions.
problem Gradient estimates for Neumann semigroups on manifolds with boundary under unbounded curvature conditions.
method Establishes Bismut-type formulas and gradient estimates for Feynman--Kac semigroups on Riemannian manifolds with boundary, under geometric conditions formulated in terms of Ricci curvature and second fundamental form.
result Derives pointwise gradient estimates for the Neumann semigroup under variable, possibly unbounded, lower curvature bounds.
Neural networks cannot approximate certain functions in Sobolev spaces, leading to unbounded parameter growth.
problem Non-closedness of sets of neural networks in Sobolev spaces.
method Construction of sequences of neural networks whose realizations converge to functions not realizable by neural networks.
result Sets of realized neural networks are not closed in order- ( m − 1 ) (m-1) ( m − 1 ) Sobolev spaces W m − 1 , p W^{m-1,p} W m − 1 , p for p ∈ [ 1 , ∞ ] p \in [1,\infty] p ∈ [ 1 , ∞ ] . New aggregation strategy handles unbounded losses with regret bounds.
problem Online optimization with unbounded loss functions.
method Follow The Regularized Leader (FTRL) with φ-divergence.
result Worst regret bound for unbounded losses with alternative divergences.