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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “Lipschitz-constrained”

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networkscs.LG

New method prevents gradient attenuation in Lipschitz constrained convolutional networks.

problem Gradient norm attenuation in Lipschitz constrained convolutional networks.

method Block Convolution Orthogonal Parameterization (BCOP) to train scalable, expressive, provably Lipschitz convolutional networks.

result Empirically, BCOP parameterization is competitive with existing approaches to provable adversarial robustness and Wasserstein distance estimation.

Lipschitz constraints convolutional networks gradient penalty adversarial robustness Wasserstein distance

2019-11-03abs ↗pdf ↗

Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shiftscs.LG

Density-Softmax improves uncertainty estimation and robustness without sampling, reducing model size and latency.

problem Sampling-based uncertainty estimation methods suffer from large model size and high latency.

method Combines a Lipschitz-constrained feature extractor with the softmax layer to create a sampling-free deterministic framework.

result Density-Softmax reduces over-confidence under distribution shifts and achieves competitive results in uncertainty and robustness.

uncertainty estimation distribution shifts sampling-free Lipschitz-constrained softmax

2023-02-13abs ↗pdf ↗

GAN Estimation of Lipschitz Optimal Transport Mapsstat.ML

Paper introduces a neural network for consistent estimation of optimal transport maps.

problem Statistically consistent estimation of optimal transport maps between probability distributions.

method Lipschitz-constrained GAN penalized by quadratic transportation cost.

result The generator converges uniformly to the optimal transport map as sample size increases.

GAN Optimal Transport Lipschitz Neural Networks Statistical Consistency

2022-02-16abs ↗pdf ↗

Approximation Theory for Lipschitz Continuous Transformerscs.LG

New Transformers maintain Lipschitz continuity for robustness.

problem Ensuring robustness in Transformers for safety-sensitive applications.

method Introducing gradient-descent-type in-context Transformers with explicit Euler steps of negative gradient flows.

result Universal approximation theorem for Lipschitz continuous Transformers.

Transformers Lipschitz continuity Robustness Stability Approximation theory

2026-02-17abs ↗pdf ↗

Certifiably Robust Variational Autoencodersstat.ML

Certifiably robust VAEs are trained with bounds on input perturbations.

problem Ensuring VAEs are robust to adversarial attacks.

method Derive bounds on minimal perturbation size, control parameters, and train VAEs to meet criteria.

result Certifiably robust VAEs are more robust to attacks than standard VAEs.

robustness variational autoencoder adversarial attack certifiability Lipschitz constants

2021-02-15abs ↗pdf ↗

Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networkscs.LG

1-Lipschitz networks are as accurate as classical networks and offer robustness.

problem Misconceptions about 1-Lipschitz neural networks and their properties.

method Analysis of 1-Lipschitz neural networks' accuracy, robustness, and generalization.

result 1-Lipschitz neural networks are as accurate as classical networks and can fit arbitrarily difficult boundaries.

Lipschitz networks neural networks classification robustness generalization

2021-04-11abs ↗pdf ↗

Orthogonalizing Convolutional Layers with the Cayley Transformcs.LG

New method enforces orthogonality in convolutional layers for improved robustness.

problem Improving adversarial robustness in deep learning models.

method Applying the Cayley transform to skew-symmetric convolutions in the Fourier domain.

result The proposed method preserves orthogonality and enhances adversarial robustness compared to existing techniques.

orthogonal convolution adversarial robustness Cayley transform deep learning

2021-04-14abs ↗pdf ↗

Moreau-Yosida

f

-divergencescs.LG

We introduce a new approximation of $f$ -divergences for machine learning.

problem Variational representations of

f

-divergences for machine learning.

method Definition and analysis of Moreau-Yosida approximation of

f

-divergences with the Wasserstein-1 metric.

result Generalization and relaxation of hard Lipschitz constraints in

f

-divergences.

$f$-divergences Wasserstein-1 metric Lipschitz functions Variational formulas GANs

2021-02-26abs ↗pdf ↗

Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustnesscs.LG

Framework learns robust control policies from expert demonstrations.

problem Adversarial robustness and closed-loop generalization in feedback control policies.

method Lipschitz-constrained loss minimization for certified robustness and generalization.

result Finite sample bound on policy learning error and robust closed-loop stability.

feedback control robustness Lipschitz closed-loop adversarial

2021-03-30abs ↗pdf ↗

Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Modelsstat.ML

Markov chain decoders improve generative models' ability to produce heavy-tailed data.

problem Generative models struggle with heavy-tailed distributions.

method Replaced Gaussian decoder with Markov chain-based Phase-Type distributions.

result Significantly reduced tail Kolmogorov-Smirnov distance and extreme quantile error.

Markov chains Phase-Type distributions Generative models Heavy-tailed data Kolmogorov-Smirnov distance

2026-05-18abs ↗pdf ↗

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networkscs.LG

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.

Lipschitz scaling neural networks robustness calibration Temperature Scaling

2026-07-08abs ↗pdf ↗