Research
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

79157236314 · Jun 202019922001200920172026
48 results for Lipschitz scaling

LiST improves neural network robustness and calibration without manual tuning.

problem Developing robust and calibrated neural networks simultaneously.
method Lipschitz Scaling Training (LiST) that iteratively adjusts the global Lipschitz constant.
result LiST yields an out-of-the-box calibrated network with competitive accuracy and robustness.

In the first part of the paper we show how to relate several dimension theories (asymptotic dimension with Higson property, asymptotic dimension of Gromov, and capacity dimension of Buyalo \cite{Buyalo1}) to Nagata-Assouad dimension. This is done by applying two functors on the Lipschitz category of metric spaces: micr…

2006-01-10abs ↗pdf ↗

Existing depth separation results for constant-depth networks essentially show that certain radial functions in Rd\mathbb{R}^d, which can be easily approximated with depth 33 networks, cannot be approximated by depth 22 networks, even up to constant accuracy, unless their size is exponential in dd. However, the func…

2019-04-15abs ↗pdf ↗

Improved DP SO with large Lipschitz parameters, handling outliers and heavy-tailed data.

problem Differential privacy in stochastic optimization with large Lipschitz parameters.
method Assumes bounded k-th order moments, provides linear-time algorithms for smooth convex and non-smooth convex losses.
result Improved risk bounds scaling with k-th moment, not uniform Lipschitz parameter.

We address reinforcement learning problems with finite state and action spaces where the underlying MDP has some known structure that could be potentially exploited to minimize the exploration rates of suboptimal (state, action) pairs. For any arbitrary structure, we derive problem-specific regret lower bounds satisfie…

2018-06-03abs ↗pdf ↗

This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for…

2017-06-26abs ↗pdf ↗

Study shows shallow ReLU networks struggle with high-dimensional Lipschitz functions.

problem Expressing high-dimensional Lipschitz functions with shallow ReLU networks.
method Established lower bounds on shallow network complexity for polynomial approximation.
result Shallow ReLU networks suffer from the curse of dimensionality for Lipschitz functions.

ELF simplifies normalizing flows, making them more efficient and universal.

problem Computational inefficiency of normalizing flows.
method ELF introduces a simple, one-layer network with closed-form Lipschitz constants, combining the ease of residual flows with the performance of autoregressive flows.
result ELF is a provably universal density approximator, more efficient computationally and parameter-wise.

We consider the notion of dimension in four categories: the category of (unbounded) separable metric spaces and (metrically proper) Lipschitz maps, and the category of (unbounded) separable metric spaces and (metrically proper) uniform maps. A unified treatment is given to the large scale dimension and the small scale …

2006-07-10abs ↗pdf ↗

This paper analyzes convergence of large-scale Transformers with weight decay.

problem Understanding optimization guarantees in large-scale Transformer training.
method Construct mean-field limit, show gradient flow convergence to PDE, demonstrate global minimum consistency.
result Gradient flow reaches global minimum in large-scale Transformers with small weight decay.

Orthogonium offers unified, efficient layers for robust deep learning.

problem Fragmented and computationally demanding implementations of orthogonal and 1-Lipschitz layers.
method Unified, efficient PyTorch library providing orthogonal and 1-Lipschitz layers.
result Reduced overhead and standardized tools for robust experimentation.

Generative models improve for multiscale scientific data with new noise and interpolation techniques.

problem Numerical challenges in generating high-fidelity samples for multiscale scientific data.
method Design of noise distributions and interpolation schedules in function space to ensure Lipschitz regularity and finite noise roughness.
result Scale-adaptive noise and interpolation schedules improve numerical efficiency and fidelity of generated samples.

Colding and Minicozzi have shown that an embedded minimal disk 0ΣBR0\inΣ\subset B_R in $\Real^3$ with large curvature at 0 looks like a helicoid on the scale of RR. Near 0, this can be sharpened: on the scale of A1(0)|A|^{-1}(0), ΣΣ is close, in a Lipschitz sense, to a piece of a helicoid. We use surfaces constructed by C…

2008-05-30abs ↗pdf ↗

Paper proves convergence for private FL on non-Lipschitz convex objectives using normalization instead of clipping.

problem Lack of convergence results for differentially private federated learning with non-Lipschitz objectives.
method Developed a convergence result for private FL on smooth convex objectives without assuming Lipschitzness, using normalization instead of clipping.
result Normalization-based private FL algorithm converges better than clipping-based counterpart on smooth convex functions.

The paper trains neural networks with robustness guarantees using semidefinite constraints.

problem Training neural networks with robustness and stability guarantees.
method Exploiting the banded structure of semidefinite constraints, an efficient and scalable training scheme based on interior point methods is set up.
result The method allows for enforcing Lipschitz constraints in large-scale deep neural networks, as demonstrated in numerical examples.

Hyperbolic space outperforms Euclidean in learning hierarchical data.

problem Learning hierarchical data in Euclidean space requires exponentially many samples.
method Established geometric obstruction in Euclidean space and showed hyperbolic space's advantage.
result Hyperbolic space enables learning with O(mRlogm)O(mR \log m) samples, matching information-theoretic optimum.

The paper proves Lipschitz regularity of graph Laplacian eigenvectors on random data clouds.

problem Analyzing the regularity of solutions to graph Laplacian equations on random data points.
method Probabilistic coupling of random walks and interpolation method for point clouds to continuum.
result Graph Laplacian eigenvectors are essentially Lipschitz with constants depending on eigenvalues.

New method models fat-tailed distributions with anisotropic tail-adaptive flows.

problem Gaussian-based variational inference fails to accurately capture tail decay in fat-tailed distributions.
method Improved theory on tails of flows, developed anisotropic tail-adaptive flows (ATAF).
result ATAF models tail-anisotropy, outperforming prior work on synthetic and real-world targets.

Wide deep neural networks with Gaussian weights approximate Gaussian processes closely.

problem Understanding the approximation of deep neural networks with Gaussian weights to Gaussian processes.
method Established novel rates for the Gaussian approximation of random deep neural networks with Gaussian parameters and Lipschitz activation functions in the wide limit.
result The distance between the network output and the Gaussian approximation scales inversely with the width of the network.

LOT improves adversarial robustness by training 1-Lipschitz convolution layers.

problem Improving adversarial robustness of deep neural networks.
method LOT: Layer-wise Orthogonal Training for 1-Lipschitz convolution layers.
result LOT significantly enhances certified robustness of Lipschitz-bounded models.

In this paper, we prove results concerning the large scale geometry of connected, simply connected nonabelian nilpotent Lie groups equipped with left invariant Riemannian metrics. Precisely, we prove that there do not exist quasi-isometric embeddings of such a nilpotent Lie group into either a CAT(0) metric space or an…

1999-03-15abs ↗pdf ↗

Reduced sample complexity for group-invariant distributions.

problem Improving sample complexity for estimating divergences of group-invariant distributions.
method Quantified reduction in sample complexity for Wasserstein-1 metric and Lipschitz-regularized α-divergences under finite and infinite groups.
result Sample complexity reduction proportional to group size for finite groups, and convergence rate depends on intrinsic dimension for infinite groups.

The paper optimizes interpolation schedules in generative models to improve sampling accuracy.

problem Improving sampling accuracy in generative models with fewer resources.
method Minimizing the averaged squared Lipschitzness of the drift field, using transfer formulas.
result Designed schedules yield more accurate fine-scale statistics at fixed integrator budget.

A new model improves uncertainty estimation in deep learning.

problem Deep Kernel Learning (DKL) produces unreliable uncertainty estimates.
method Proposed a bi-Lipschitz constraint to preserve distances in feature space.
result DUE model outperforms previous DKL and other methods in uncertainty quality.

Constructs a map with prescribed local Lipschitz constants on a subset of a manifold.

problem Creating a Lipschitz map with specific local Lipschitz constants on a subset of a manifold.
method Constructs a Lipschitz map that matches a given map on a subset and has a local Lipschitz constant defined by a continuous function.
result A Lipschitz map can be constructed with a local Lipschitz constant prescribed by a continuous function.

Maps between certain Lipschitz manifolds are isometries if they preserve volume.

problem Volume preservation and isometry conditions for Lipschitz manifolds.
method Volume-preserving 1-Lipschitz maps from integral currents onto infinitesimally Euclidean Lipschitz manifolds.
result Volume-preserving maps are isometries under given conditions.

New optimizers control network width scaling, improving stability and transfer across different model sizes.

problem Designing stable optimizers for networks of varying widths.
method Interpreting optimizers as steepest descent under mean-normalized operator norms, enabling layerwise composability and width-independent bounds.
result New optimizers like row normalization and column normalization provide stable learning-rate transfer across different model widths.

New algorithm for MDS with quasi-polynomial dependency on aspect ratio.

problem Finding an embedding that minimizes a specific objective function for given dissimilarities.
method A novel geometry-aware analysis of a conditional rounding of the Sherali-Adams LP hierarchy.
result Achieved a solution with cost \(O(\log Δ) \cdot extrm{OPT}^{Ω(1)} + ε\) in quasi-polynomial time.

Optimizes optimal transport distances using low-dimensional embeddings.

problem High computational cost of optimal transport distances in high dimensions.
method Approximate OT distances using 1-Lipschitz maps in a lower-dimensional space.
result Efficiently approximates optimal transport distances with lower computational cost.

Let X be a finite CW complex or compact Lipschitz neighborhood retract with universal cover Z; let M be a compact orientable manifold of dimension at least 2 and nonempty boundary. We establish the existence of an isoperimetric profile for functions from M to Z, in the metric and cellular senses, and show that they are…

2009-01-15abs ↗pdf ↗

The study examines the limitations of bi-Lipschitz Normalizing Flows in approximating certain distributions.

problem The expressivity of bi-Lipschitz Normalizing Flows in approximating specific target distributions.
method Characterization of expressivity through lower bounds on Total Variation distance and discussion of potential remedies.
result Several target distributions are difficult to approximate using bi-Lipschitz Normalizing Flows, and lower bounds on their approximation are provided.

We introduce multiscale invariant dictionaries to estimate quantum chemical energies of organic molecules, from training databases. Molecular energies are invariant to isometric atomic displacements, and are Lipschitz continuous to molecular deformations. Similarly to density functional theory (DFT), the molecule is re…

2016-05-16abs ↗pdf ↗