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

7 results for “model-wise”

Understanding the Role of Optimization in Double Descentcs.LG

This paper explains why double descent sometimes occurs weakly or not at all from an optimization perspective.

problem Understanding the role of optimization in the phenomenon of double descent.

method Investigates model-wise double descent from an optimization perspective, proposing a unified explanation for its occurrence.

result Model-wise double descent is observed if and only if the optimizer can find a sufficiently low-loss minimum.

double descent optimization machine learning model-wise peak reduction

2023-12-06abs ↗pdf ↗

Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structuresstat.ML

Unified analysis of generalization curves in large models using gradient flow.

problem Analyzing generalization error curves in simple learning models.

method Gradient flow in the Gaussian covariate model, using random matrix theory.

result Unified understanding of multiple descent structures in learning curves.

generalization error gradient flow random matrix theory multiple descent asymptotic analysis

2022-12-13abs ↗pdf ↗

Influence of parallel computing strategies of iterative imputation of missing data: a case study on missForeststat.AP

Study examines parallel computing strategies for faster imputation of missing data.

problem Time-consuming iterative imputation methods for large datasets.

method Variable-wise and model-wise distributed parallel computing strategies in missForest.

result Variable-wise distributed strategy introduces additional biases in imputation results.

parallel computing imputation missing data machine learning missForest

2020-04-23abs ↗pdf ↗

Unveiling Multiple Descents in Unsupervised Autoencoderscs.LG

Study shows double and triple descent in unsupervised autoencoders, improving performance in various tasks.

problem Exploring the phenomenon of double descent in unsupervised learning.

method Analytical demonstration and extensive experiments on synthetic and real datasets.

result Over-parameterized unsupervised autoencoders exhibit double and triple descent, enhancing performance in downstream tasks.

unsupervised learning autoencoders double descent performance improvement downstream tasks

2024-06-17abs ↗pdf ↗

On the Limitations of Fractal Dimension as a Measure of Generalizationcs.LG

This paper evaluates fractal dimension and persistent homology for neural network generalization.

problem Bounding and predicting the generalization gap of neural networks.

method Empirical evaluation of fractal dimension and persistent homology as generalization measures.

result Fractal dimension and persistent homology fail to predict generalization of models trained from poor initializations.

neural networks generalization fractal dimension persistent homology topology

2024-06-04abs ↗pdf ↗

Contrasting random and learned features in deep Bayesian linear regressioncs.LG

Study compares random and learned features in deep Bayesian linear models.

problem Understanding how feature learning affects generalization in deep learning.

method Comparing deep random feature models to deep networks with trained layers.

result Random feature models can display double-descent behavior, while deep networks do not.

deep learning Bayesian linear regression feature learning generalization double-descent

2022-03-01abs ↗pdf ↗

Multi-scale Feature Learning Dynamics: Insights for Double Descentcs.LG

New insights into double descent phenomenon in neural networks.

problem Understanding the double descent behavior in deep learning models.

method Linear teacher-student setup and tools from statistical physics.

result Distinct features are learned at different scales, leading to epoch-wise double descent.

double descent neural networks statistical physics feature learning generalization error

2021-12-06abs ↗pdf ↗