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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “DKT”

Disease Knowledge Transfer across Neurodegenerative Diseasescs.LG

DKT transfers biomarker information between neurodegenerative diseases.

problem Estimating biomarker trajectories in rare neurodegenerative diseases with limited data.

method DKT is a joint-disease generative model that transfers biomarker progressions from common neurodegenerative diseases to rare ones.

result DKT estimates plausible multimodal biomarker trajectories in rare diseases like PCA using only unimodal data.

neurodegenerative diseases biomarker transfer DKT Alzheimer's variants Posterior Cortical Atrophy

2019-01-11abs ↗pdf ↗

Extending Deep Knowledge Tracing: Inferring Interpretable Knowledge and Predicting Post-System Performancecs.CY

Paper extends knowledge tracing algorithms to infer student knowledge and predict posttest performance.

problem Lack of algorithms that directly infer student knowledge and predict posttest performance.

method Extended DKT and DKVMN to infer knowledge, and applied to BKT and PFA for comparison.

result Knowledge estimates from the extended algorithms correlate better with posttest performance than existing methods.

knowledge tracing student performance posttest prediction algorithm extension Deep Knowledge Tracing

2019-10-14abs ↗pdf ↗

qDKT: Question-centric Deep Knowledge Tracingcs.LG

qDKT improves KT models by considering individual question outcomes.

problem Ignoring question-specific outcomes leads to inaccurate learner skill tracking.

method qDKT incorporates graph Laplacian regularization and uses a fastText-inspired initialization scheme.

result qDKT achieves state-of-the-art performance in predicting learner outcomes.

knowledge tracing deep learning question-centric graph Laplacian fastText

2020-05-25abs ↗pdf ↗

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernelscs.LG

Bayesian meta-learning improves few-shot learning with deep kernels.

problem Few-shot learning with small labeled datasets.

method Bayesian treatment of meta-learning using deep kernels.

result Deep Kernel Transfer (DKT) outperforms state-of-the-art algorithms.

Bayesian meta-learning few-shot learning deep kernels meta-learning transfer learning

2019-10-11abs ↗pdf ↗

Best-of-Both-Worlds Algorithms for Linear Contextual Banditscs.LG

New algorithms minimize regret in both adversarial and stochastic contexts.

problem Minimizing regret in linear contextual bandits.

method Best-of-both-worlds algorithms using FTRL with Shannon entropy regularizer.

result Achieves near-optimal regret bounds in both adversarial and stochastic regimes.

linear contextual bandits regret minimization FTRL entropy regularizer adversarial

2023-12-24abs ↗pdf ↗

A Self-Attentive model for Knowledge Tracingcs.LG

SAKT improves knowledge tracing by focusing on relevant past activities.

problem Handling sparse data in knowledge tracing models.

method Self-attention based approach to identify relevant past activities.

result SAKT outperforms state-of-the-art models, improving AUC by 4.43%.

knowledge tracing self-attention sparse data Recurrent Neural Networks Deep Knowledge Tracing

2019-07-16abs ↗pdf ↗