Research map / Optimization / Nonconvex and smooth optimization
An Inertial Newton Algorithm for Deep Learning
Camille Castera, Jérôme Bolte, Cédric Févotte, Edouard Pauwels
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 |
|---|---|---|---|
| increase beta (Newton damping) in INNA (ablation) | INNA · 2D non-smooth Rosenbrock-like function | transverse oscillations | Improved |
| increase alpha (viscous damping) in INNA (ablation) | INNA · 2D non-smooth Rosenbrock-like function | longitudinal oscillations | Improved |
| vary (alpha,beta) among four configurations (ablation) | INNA with NiN · MNIST, CIFAR-10, CIFAR-100 | training loss and test accuracy | No clear effect |
| use INNA instead of SGD | NiN training · MNIST, CIFAR-10, CIFAR-100 | training loss | Improved |
| use INNA instead of ADAM | NiN training · CIFAR-100 | test accuracy | Improved |
| use ADAM instead of INNA | NiN training · MNIST, CIFAR-10, CIFAR-100 | early training speed | Improved |
Closest papers by meaning
- Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit (NeurIPS 2026 · similarity 0.86)
- Small Steps and Giant Leaps: Minimal Newton Solvers for Deep Learning (ICCV 2019 · similarity 0.85)
- Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms (NeurIPS 2024 · similarity 0.85)
- Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization (NeurIPS 2024 · similarity 0.84)
- EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization (NeurIPS 2026 · similarity 0.84)
- Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation (NeurIPS 2024 · similarity 0.84)
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.
