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.

168,878 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “T-norms”

On the relation between Loss Functions and T-Normscs.LG

Paper connects loss functions and t-norms for faster deep learning convergence.

problem Improving convergence rates in deep learning models.

method Interprets loss functions through t-norms and generator functions.

result Derives a general relation between loss functions and t-norms leading to faster convergence.

Deep learning Loss functions T-norms Generator functions Convergence rates

2019-07-18abs ↗pdf ↗

SPOCC: Scalable POssibilistic Classifier Combination -- toward robust aggregation of classifierscs.LG

A new method combines classifiers using possibility distributions and adaptive t-norms.

problem Aggregating predictions from multiple classifiers trained on overlapping datasets.

method Proposes a new approach to aggregate classifier predictions using possibility theory and adaptive t-norms.

result Proves the proposed approach possesses desirable robustness properties.

classifier combination possibility theory t-norms frequentist probabilities overlap datasets

2019-08-18abs ↗pdf ↗

Sparse Signal Detection in Heteroscedastic Gaussian Sequence Models: Sharp Minimax Ratesmath.ST

Study on signal detection in heteroscedastic Gaussian sequences with sparse alternatives.

problem Signal detection in heterogeneous Gaussian sequences with unknown means and known covariance.

method Characterization of minimax separation radius and derivation of matching upper and lower bounds.

result Matching minimax upper and lower bounds for signal detection in heteroscedastic Gaussian sequences.

signal detection heteroscedastic Gaussian sequences sparse alternatives minimax rates phase transitions

2022-11-15abs ↗pdf ↗

Constraint-Based Visual Generationcs.LG

In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive exploration of convolutional architectures. In this paper, we propose a general approach to visual generation that combines learning capabilities …

2018-07-16abs ↗pdf ↗

Probabilistic Foundations of Fuzzy Simplicial Sets for Nonlinear Dimensionality Reductioncs.LG

Unified probabilistic foundation for fuzzy simplicial sets in dimensionality reduction.

problem Lack of clear probabilistic interpretation in fuzzy simplicial sets.

method Introducing a probabilistic framework explaining fuzzy simplicial sets as marginals of probability measures on simplicial sets.

result Unified probabilistic theoretical foundation for fuzzy simplicial sets.

fuzzy simplicial sets dimensionality reduction probabilistic models Vietoris-Rips filtrations UMAP

2025-12-03abs ↗pdf ↗

A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classificationcs.CV

Unified framework for hierarchical image classification with epistemic uncertainty.

problem Overconfident predictions and lack of logical consistency in deep learning models.

method Neurosymbolic approach with epistemic deep learning, using focal set reasoning and differentiable fuzzy logic.

result Maintains accuracy on par with transformer baselines while providing more calibrated and interpretable predictions.

Hierarchical Image Classification Epistemic Uncertainty Neurosymbolic Focal Set Reasoning Differentiable Fuzzy Logic

2026-05-11abs ↗pdf ↗