Convergence of Stochastic Gradient Descent for PCA

Authors: Ohad Shamir

ICML 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we provide (to the best of our knowledge) the first eigengap-free convergence guarantees for SGD in the context of PCA. This also partially resolves an open problem posed in (Hardt & Price, 2014). Moreover, under an eigengap assumption, we show that the same techniques lead to new SGD convergence guarantees with better dependence on the eigengap.
Researcher Affiliation Academia Ohad Shamir OHAD.SHAMIR@WEIZMANN.AC.IL Weizmann Institute of Science, Israel
Pseudocode Yes Initialize by picking a unit norm vector w0 For t = 1, . . . , T, perform wt = (I + η At)wt 1 Return w T w T
Open Source Code No The paper does not contain any statement about releasing source code, nor does it provide a link to a code repository.
Open Datasets No The paper is theoretical and does not use or mention specific datasets for training. It refers to 'data x1, x2, . . . Rd' as i.i.d. from an 'unknown underlying distribution' in a theoretical context.
Dataset Splits No The paper is theoretical and does not describe empirical experiments or dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware, therefore no hardware specifications are provided.
Software Dependencies No The paper is theoretical and does not describe any software implementations with specific version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with concrete hyperparameter values or system-level training settings.