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

count % of corpus

8 results for “zero-padding”

Universal Consistency of Deep Convolutional Neural Networkscs.LG

Proves DCNNs with expansive convolution are strongly universally consistent.

problem Theoretical consistency of deep convolutional neural networks (DCNNs).

method Empirical risk minimization on DCNNs with expansive convolution (with zero-padding).

result DCNNs with expansive convolution are strongly universally consistent.

deep convolutional neural networks universal consistency empirical risk minimization expansive convolution zero-padding

2021-06-23abs ↗pdf ↗

A guide to convolution arithmetic for deep learningstat.ML

We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers…

2016-03-23abs ↗pdf ↗

Two-Dimensional Deep ReLU CNN Approximation for Korobov Functions: A Constructive Approachstat.ML

2D CNNs approximate Korobov functions with near-optimal rates.

problem Approximating Korobov functions using 2D CNNs.

method Constructive approach for 2D CNNs with ReLU activations and fully connected layers.

result 2D CNNs achieve near-optimal approximation rates for Korobov functions.

2D CNNs Korobov functions ReLU activations approximation rates curse of dimensionality

2025-03-11abs ↗pdf ↗

On the rates of convergence for learning with convolutional neural networkscs.LG

Study on CNNs' learning rates and approximation capacities.

problem Learning rates and approximation capacities of CNNs.

method New approximation bound and covering number analysis for CNNs.

result Derives minimax optimal convergence rates for CNNs in various learning problems.

CNNs learning rates approximation capacities covering number nonparametric regression

2024-03-25abs ↗pdf ↗

Generalized Least Squares Kernelized Tensor Factorizationstat.ML

GLSKF improves tensor completion by capturing both global and local variations.

problem Tensor completion with missing entries, especially in data with spatial or temporal side information.

method Integrates smoothness-constrained low-rank factorization with a locally correlated residual process.

result GLSKF achieves superior performance and scalability on real-world datasets.

tensor completion low-rank factorization smoothness constraints local variations covariance norm

2024-12-09abs ↗pdf ↗

Arithmetic-Mean

μ

P for Modern Architectures: A Unified Learning-Rate Scale for CNNs and ResNetscs.LG

Unified learning-rate scale for CNNs and ResNets, avoiding depth imbalance.

problem Challenges in choosing an appropriate learning rate for deep networks, especially as depth increases.

method Introduces Arithmetic-Mean

μ

P (AM-

μ

P), constraining network-wide average pre-activation second moment to a constant scale, combined with residual-aware He fan-in initialization.

result Demonstrates a

-3/2

scaling law for learning rates across depths, enabling zero-shot learning-rate transfer.

learning rate CNNs ResNets depth imbalance maximal update

2025-10-05abs ↗pdf ↗

LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layerscs.LG

LipKernel adds robustness to CNNs by enforcing Lipschitz bounds.

problem Improving robustness of CNNs in real-time applications.

method Dissipative layers parameterized by LMIs and 2-D Roesser model.

result Orders of magnitude faster run-time compared to state-of-the-art methods.

Lipschitz bound Convolutional Neural Networks Robustness Dissipativity Real-time applications

2024-10-29abs ↗pdf ↗

Are Whitepaper Claims Reflected in Market Structure? A Contamination-Aware Pipeline and a Power-Limited Nullq-fin.CP

Study finds no significant alignment between whitepaper claims and market structure.

problem Correlation between cryptocurrency whitepaper narratives and market behavior.

method Developed a contamination-aware pipeline for measuring structural correspondence, combining NLP classification and market statistics.

result No significant claims-market alignment detected in the sample.

cryptocurrency whitepapers market structure contamination NLP

2026-01-28abs ↗pdf ↗