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

4 results for “EigenGame”

EigenGame Unloaded: When playing games is better than optimizingstat.ML

EigenGame improves eigendecomposition by offering unbiased updates for larger datasets.

problem Minibatch bias in EigenGame limits convergence and parallelism.

method Proposed unbiased stochastic update for EigenGame.

result Asymptotic equivalence to EigenGame, greater parallelism, and improved performance.

EigenGame eigendecomposition stochastic update parallelism minibatch bias

2021-02-08abs ↗pdf ↗

EigenGame: PCA as a Nash Equilibriumcs.LG

EigenGame reinterprets PCA as a game to find eigenvectors.

problem Finding principal components efficiently and accurately.

method EigenGame treats PCA as a Nash equilibrium game, using gradient-based updates.

result EigenGame algorithm combines Oja's rule and Gram-Schmidt orthogonalization.

PCA Nash equilibrium Game theory Decentralized Orthogonalization

2020-10-01abs ↗pdf ↗

Speeding up PCA with primingcs.LG

pPCA speeds up PCA by priming initial estimates for faster, more accurate results.

problem Improving the speed and accuracy of principal component analysis (PCA).

method pPCA is a two-step algorithm: first, an approximate-PCA method primes the data, then exact PCA is applied in the span of the initial estimate.

result pPCA improves accuracy significantly with a small computational cost, outperforming other methods across various datasets.

PCA Principal Component Analysis Approximate-PCA Exact PCA Speedup

2021-09-08abs ↗pdf ↗

A Generalized EigenGame with Extensions to Multiview Representation Learningcs.LG

Develops a new method for solving generalized eigenvalue problems efficiently.

problem Efficiently solving generalized eigenvalue problems for large datasets.

method Inspired by the Generalized Hebbian Algorithm, develops a game-theory inspired approach to solving GEPs.

result Demonstrates state-of-the-art performance for optimizing Deep CCA.

Generalized Eigenvalue Problems Stochastic Optimization Canonical Correlation Analysis Deep Learning Multiview Representation Learning

2022-11-21abs ↗pdf ↗