Leveraging Non-uniformity in First-order Non-convex Optimization

Authors: Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvari, Dale Schuurmans

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results are used to illustrate and complement the theoretical findings.
Researcher Affiliation Collaboration 1University of Alberta 2Google Research, Brain Team 3Deep Mind.
Pseudocode Yes Algorithm 1 Geometry-aware Normalized Policy Gradient
Open Source Code No The paper does not provide concrete access to source code for the methodology described, such as a specific repository link or an explicit code release statement.
Open Datasets No The paper does not provide concrete access information for a publicly available or open dataset. It refers to synthetic examples and problem settings rather than established public datasets.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes Using normalized PG θt+1 = θt + η dπ θtr dθt. dπ θtr dθt 2, with η = 1/6, for all t 1, we have, (π πθt) r e c (t 1) 12 (π πθ1) r, (12) where c = inft 1 πθt(a ) > 0 is from Lemma 4, and c is a constant that depends on r and θ1, but not on the time t.