Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

Authors: Nadav Hallak, Panayotis Mertikopoulos, Volkan Cevher

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper develops a methodology for regret minimization with stochastic first-order oracle feedback in online, constrained, non-smooth, non-convex problems. Both methods are order-optimal (in the min-max sense), and we also establish a bound on the number of proximal-gradient queries these methods require.
Researcher Affiliation Collaboration Nadav Hallak 1 Panayotis Mertikopoulos 2 Volkan Cevher 3. 1Faculty of Industrial Engineering and Management, The Technion, Haifa, Israel 2Univ. Grenoble Alpes, CNRS, Inria, LIG, Grenoble, France, & Criteo AI Lab 3 Ecole Polytechnique F ed erale de Lausanne (EPFL).
Pseudocode Yes Algorithm 1: Time-smoothed online prox-grad descent, Algorithm 2: Time-smoothed online stochastic prox-grad method
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets No This is a theoretical paper focused on developing a methodology and proving bounds; it does not report on experiments conducted using specific datasets.
Dataset Splits No This is a theoretical paper focused on developing a methodology and proving bounds; it does not report on experiments with dataset splits.
Hardware Specification No The paper does not provide any specific details about the hardware used for experiments.
Software Dependencies No The paper does not provide any specific software dependencies with version numbers.
Experiment Setup No This is a theoretical paper focused on developing a methodology and proving bounds; it does not report on experimental setup details like hyperparameters.