Average-case Acceleration for Bilinear Games and Normal Matrices

Authors: Carles Domingo-Enrich, Fabian Pedregosa, Damien Scieur

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

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate our findings through numerical simulations with a varying degree of mismatch with our assumptions.
Researcher Affiliation Collaboration Carles Domingo-Enrich Computer Science Department Courant Institute of Mathematical Sciences New York University New York, NY 10012, USA cd2754@nyu.edu Fabian Pedregosa Google Research pedregosa@google.com Damien Scieur Samsung SAIT AI Lab & Mila Montreal, Canada damien.scieur@gmail.com
Pseudocode Yes Optimal average-case algorithm for bilinear games. Initialization. x 1 = x0 = θ1,0, θ2,0 , sequence {ht, mt} given by Theorem 3.1. Main loop. For t 0, gt = F(xt F(xt)) F(xt) = 1 2 F(xt) 2 by (12) xt+1 = xt ht+1gt + mt+1(xt 1 xt) (11)
Open Source Code No No explicit statement providing access to the source code for the methodology.
Open Datasets No We consider min-max bilinear problems of the form (10), where the entries of M are generated i.i.d. from a standard Gaussian distribution. No concrete access information for a publicly available or open dataset.
Dataset Splits No No specific dataset split information (percentages, counts, or explicit standard splits) is provided.
Hardware Specification No No specific hardware details (like GPU/CPU models, memory, or specific computing platforms) are mentioned for running experiments.
Software Dependencies No No specific ancillary software details with version numbers are provided.
Experiment Setup No No specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, epochs) or detailed training configurations are provided.