Research map / Optimization / Optimizers
Learning Positive Functions with Pseudo Mirror Descent
Yingxiang Yang, Haoxiang Wang, Negar Kiyavash, Niao He
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 pseudo mirror descent instead of the link function approach and projected gradient descent | Poisson intensity estimation · Synthetic 1-D Poisson process, x*(t)=exp(-t) | estimation error convergence | Improved |
| use Sobolev kernel instead of polynomial kernel (ablation) | pseudo mirror descent · Synthetic piecewise-constant intensity | estimation error | Improved |
| use pseudo mirror descent instead of link function approach and neural network | Poisson shot-distance intensity · Basketball shot distance data | fit accuracy | No clear effect |
| use pseudo mirror descent instead of EM | multivariate Hawkes process · Mouse embryonic stem cell TRE data | log-likelihood per dimension | Improved |
| use pseudo mirror descent instead of MLE-SGLP | multivariate Hawkes process · Mouse embryonic stem cell TRE data | log-likelihood per dimension | No clear effect |
| use constant step size (ablation) | pseudo mirror descent · Synthetic 1-D Poisson process | objective error | Improved |
Closest papers by meaning
- Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM (NeurIPS 2022 · similarity 0.87)
- Implicit Bias of Mirror Flow on Separable Data (NeurIPS 2024 · similarity 0.85)
- Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression (ICLR 2025 · similarity 0.83)
- How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization (ICML 2024 · similarity 0.83)
- Mirror and Preconditioned Gradient Descent in Wasserstein Space (NeurIPS 2024 · similarity 0.83)
- A connection between Tempering and Entropic Mirror Descent (ICML 2024 · similarity 0.83)
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.
