Research map / Optimization / Nonconvex and smooth optimization
L-SVRG and L-Katyusha with Arbitrary Sampling
Xun Qian, Zheng Qu, Peter Richtárik
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use importance sampling instead of uniform sampling in L-Katyusha (ablation) | L-Katyusha · cod_rna and w8a logistic regression | primal-dual gap vs epochs: L-bar = 259, 158 vs max_i Li = 3, 506, 320 | Improved |
| increase update probability p of reference point above tau/n (ablation) | L-Katyusha · cod_rna and w8a logistic regression | running time | Mixed |
| replace Katyusha inner-loop averaging with loopless reference-point update | Katyusha · w8a, real-sim, astro_ph, a9a | running time: 20% to 50% less | Improved |
| use L-Katyusha instead of Katyusha | Katyusha · w8a, real-sim, astro_ph, a9a | epochs to converge | No clear effect |
| increase minibatch size tau in L-SVRG versus L-Katyusha (ablation) | L-SVRG · w8a and cod_rna | epochs | Hurt |
Closest papers by meaning
- Stochastic Variance Reduction for Nonconvex Optimization (ICML 2016 · similarity 0.90)
- Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs (ICML 2018 · similarity 0.90)
- Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization (NeurIPS 2022 · similarity 0.89)
- Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise (NeurIPS 2026 · similarity 0.88)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.88)
- Efficient Continual Finite-Sum Minimization (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
