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.

169,341 papers · 148 categories

Trend · papers per month

7152229 · Jun 202019922001200920182026
48 results for cusp prototypes

Prototypal analysis improves archetypal analysis by penalizing distant prototypes, making it more robust and interpretable.

problem Sensitivity to outliers and non-locality in archetypal analysis limit its applicability as a learning tool.
method Prototypal analysis finds prototypes through convex combination of data points, penalizing distant prototypes.
result Prototypal analysis is more robust and interpretable than archetypal analysis.

ProtoryNet interprets text sequences using prototype trajectories for better understanding.

problem Improving text classification interpretability and accuracy.
method ProtoryNet uses prototype trajectories to interpret text sequences, with prototype pruning for better interpretability.
result ProtoryNet outperforms baseline models and reduces performance gap compared to black-box models.

Prototype networks on hyperspheres improve classification and regression.

problem Improving classification and regression performance.
method Using hyperspherical prototypes for classification and regression, optimizing prototypes through data-independent margin separation.
result Hyperspherical prototype networks outperform other methods in classification, regression, and their combination.

Method generates prototypes from small datasets for efficient learning.

problem Efficiently learning from small datasets with soft labels.
method Modular method for generating soft-label prototypical lines and Hierarchical Soft-Label Prototype k-Nearest Neighbor algorithm.
result High classification accuracy with significantly fewer prototypes than classes.

Paper optimizes hyperspherical prototypes for better class separation.

problem Previous HPL approaches either lack principled optimisation or are limited to one latent dimension.
method Develops a principled optimisation procedure and uses linear block codes to create well-separated prototypes in various dimensions.
result Optimal prototype placement is characterized with achievable and converse bounds, showing near-optimality.

Prototype model improves model auditing and understanding.

problem Auditing and understanding modern language models is expensive and approximate.
method Introduced a sparse, non-negative mixture of learned prototypes trained with clustering objectives.
result Prototype models either surpass or remain within 2.5 percentage points of dense baselines on downstream tasks.

New invariant cusp crossing density shows cusp densities of hyperbolic knots and links are dense.

problem Densities of cusp invariants for hyperbolic knots and links.
method Defined cusp crossing density as ratio of cusp volume to crossing number; showed densities are dense.
result Cusp crossing density for links is bounded above by 3.1263... and is dense in [0, 2.120...].

Characterizes holonomies of convex projective cusps.

problem Understanding holonomies in strictly convex projective geometry.
method Complete characterization of holonomies for strictly convex and round cusps, building families of generalized cusps.
result Produces the first example of generalized cusps with non-virtually nilpotent fundamental group.

TPM improves medical image segmentation by separating foreground and background.

problem Few-shot medical image segmentation challenges due to background variability.
method Tied Prototype Model (TPM) focusing on foreground, adapting thresholds, and using class priors.
result TPM leads to improved segmentation accuracy compared to ADNet.

The paper proposes scalable methods for selecting prototypes from large dissimilarity datasets.

problem Selecting good prototypes from large dissimilarity datasets.
method Genetic algorithms, dissimilarity-based hashing, unsupervised and supervised criteria.
result The methods select good prototypes efficiently from large datasets.

A new neural network method improves interpretability and detection of outliers.

problem Improving interpretability and detection of outliers in neural networks.
method Prototype-based learning (PbL) using a winner-take-all (WTA) network with two prototypes: positive and negative.
result The negative prototype is similar to the positive one, aligning with the BCM theory.

Gaussian prototypical networks improve few-shot learning on Omniglot.

problem Few-shot classification on the Omniglot dataset.
method Extends prototypical networks by incorporating uncertainty estimates as Gaussian covariance matrices to define a distance metric.
result Report state-of-the-art performance in 1-shot and 5-shot classification.

Study geodesics entering a fixed cusp neighborhood multiple times.

problem Understanding geodesics entering a specific cusp neighborhood multiple times.
method Investigate reciprocal geodesics entering a fixed cusp neighborhood a fixed number of times.
result Characterized the class of reciprocal geodesics entering a fixed cusp neighborhood a fixed number of times.

Pantypes improve prototypical models by capturing diverse input distributions.

problem Prototypical models lack sufficient data representation in low density regions.
method Introducing pantypes, a sparse set of diverse objects to represent the full diversity of input distribution.
result Pantypes empower prototypical models to foster high diversity, interpretability, and fairness.

A neural network that explains its predictions through prototypes.

problem Lack of interpretability in deep neural networks.
method A novel network architecture with an autoencoder and prototype layer, trained with four terms.
result The network learns to explain its predictions through learned prototypes.

IMKPL learns interpretable prototypes for better classification.

problem Efficient trade-offs between interpretability and prediction accuracy in kernel-based data.
method Local discrimination in feature space, condensed class-homogeneous neighborhoods, combined embedding.
result IMKPL achieves better interpretability and discriminative representation.

PTBCC improves accuracy in multi-class annotation aggregation by learning from prototype confusion matrices.

problem Inaccurate and insufficient confusion matrices for annotators in multi-class classification tasks.
method PTBCC (ProtoType learning-driven Bayesian Classifier Combination) uses prototype confusion matrices to capture annotator expertise.
result PTBCC achieves up to 15% accuracy improvement and 3% higher average accuracy compared to existing methods.

New findings on cusped Borel Anosov representations and their properties.

problem Characterizing and understanding cusped Borel Anosov representations.
method Analyzing representations of lattices in PGL2(R)PGL_2(\mathbb{R}) to PGLd(R)PGL_d(\mathbb{R}).
result Cusped Borel Anosov representations with specific properties are Hitchin representations.

SPOT uses optimal transport to select important prototypes.

problem Summarizing datasets for better understanding and decision making.
method Modeling prototype selection as a submodular optimization problem and using a greedy algorithm.
result Our approach efficiently selects prototypes with optimal transport that best represent the target dataset.

The condensed nearest neighbor (CNN) algorithm is a heuristic for reducing the number of prototypical points stored by a nearest neighbor classifier, while keeping the classification rule given by the reduced prototypical set consistent with the full set. I present an upper bound on the number of prototypical points ac…

2013-09-29abs ↗pdf ↗

Computes cusp cobordism groups for Morse functions on manifolds.

problem Understanding the cusp cobordism groups of Morse functions.
method Employed Levine's cusp elimination technique and created pairs of cusps along fold lines.
result Both unoriented and oriented cusp cobordism groups are cyclic of order two in even dimensions and infinite order in odd dimensions.

Algorithm generates new drug molecules from prototypes, showing diversity and validity.

problem Designing new drugs from existing prototypes is expensive and time-consuming.
method Conditional Diversity Networks (CDN) for unsupervised generation of drug molecules.
result Generated molecules are valid and significantly different from prototypes, including FDA-approved drugs.