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

8 results for “canonicalization”

^2

: Leveraging Geometry for Conformal Prediction via Canonicalizationstat.ML

CP $^2$ uses geometric information to improve conformal prediction robustness.

problem CP fails under geometric data shifts, losing coverage guarantees.

method Integrates geometric pose information into CP via canonicalization.

result Integrating geometric information with CP ensures robustness under geometric shifts.

conformal prediction geometric shifts pose canonicalization robustness

2025-06-19abs ↗pdf ↗

Representation Learning Through Latent Canonicalizationscs.LG

This research improves representation learning for new domains with limited new supervision.

problem Learning representations that generalize well to new domains with minimal new data.

method Encourages linearity of factors of variation through learned linear transformations called latent canonicalizers.

result Reduces the number of observations needed to generalize to a similar target domain compared to supervised baselines.

representation learning latent canonicalizers disentanglement meta-labels generalization

2020-02-26abs ↗pdf ↗

Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariantstat.ML

LLoCa makes any network Lorentz-equivariant, achieving high accuracy and efficiency.

problem Limitations of specialized layers in Lorentz-equivariant neural networks.

method LLoCa framework using local reference frames and geometric message passing.

result Models achieve competitive and state-of-the-art accuracy on particle physics tasks.

Lorentz-equivariant neural networks high-energy physics message passing FLOPs

2025-05-26abs ↗pdf ↗

(Almost) All of Entity Resolutionstat.ME

This article reviews entity resolution methods and their applications.

problem Integrating information from multiple sources to clean and accurately link records.

method Clustering, semi- and fully supervised methods, canonicalization.

result Modern probabilistic record linkage has been foundational.

entity resolution record linkage clustering semi-supervised canonicalization

2020-08-10abs ↗pdf ↗

Learning Latent Permutations with Gumbel-Sinkhorn Networksstat.ML

Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collectio…

2018-02-23abs ↗pdf ↗

Improving Equivariant Networks with Probabilistic Symmetry Breakingcs.LG

SymPE breaks symmetries in equivariant networks, improving performance across various tasks.

problem Equivariant networks cannot break symmetries, leading to poor performance in tasks with symmetrical inputs.

method Novel equivariant conditional distributions and randomized canonicalization.

result SymPE significantly improves performance of group-equivariant and graph neural networks.

equivariance symmetry breaking neural networks conditional distributions generalization

2025-03-27abs ↗pdf ↗

DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weightscs.LG

DeepWeightFlow generates diverse neural network weights efficiently.

problem Generating complete neural network weights efficiently and accurately.

method Flow Matching in weight space with Git Re-Basin and TransFusion.

result DeepWeightFlow generates high-accuracy neural networks without fine-tuning.

neural network weights generative models flow matching Git Re-Basin transfer learning

2026-01-08abs ↗pdf ↗

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Modelscs.LG

LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.

problem Efficient processing of low-rank weight decompositions in large finetuned models.

method Developed symmetry-aware invariant and equivariant LoL models to process LoRA weights.

result LoL models can predict CLIP scores, finetuning data attributes, and accuracy on downstream tasks.

LoRAs Low-rank weights Machine learning Invariant models Equivariant models

2024-10-05abs ↗pdf ↗