Research map / Optimization / Optimizers
Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems
Mohsen Amidzadeh, Lauri Viitasaari, Mario Di Francesco
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 |
|---|---|---|---|
| omit the Malliavin-based optimality term from the loss (ablation) | SPF · Scalar TV-SO (Exp1), t=1 | learning performance | Hurt |
| use SPF (non-parametric) instead of PDM | SPF · Scalar TV-SO (Exp1) | runtime per update step: 9 -> < 1 | Improved |
| use SPF instead of PDM | SPF · Constrained TV-SO (Exp2) | runtime per update step: 41 -> < 1 | Improved |
| use SPF instead of PDM and PSG | SPF · Least-squares recovery (n=10, d=5) | optimality distance and suboptimality | Improved |
| use SPF instead of PDM | SPF · Logistic regression | objective suboptimality | No clear effect |
| use SPF instead of PSG | SPF · Logistic regression | objective suboptimality | Improved |
| increase NN parameterization dimension (ablation) | SPF · Least-squares recovery | runtime | No clear effect |
| increase NN parameterization dimension (ablation) | PDM · Least-squares recovery | runtime | Hurt |
| use SPF instead of PSG in high dimension | SPF · Least-squares recovery (n=100, d=50) | performance | Improved |
Closest papers by meaning
- A Latent Variational Framework for Stochastic Optimization (NeurIPS 2019 · similarity 0.88)
- Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape (JMLR 2022 · similarity 0.86)
- Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation (NeurIPS 2024 · similarity 0.85)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.85)
- Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization (NeurIPS 2025 · similarity 0.85)
- Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss (NeurIPS 2024 · similarity 0.85)
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.
