AI Paper Atlas

Research map / Optimization / Optimizers

Learning Fractals by Gradient Descent

Cheng-Hao Tu, Hong-You Chen, David Carlyn, Wei-Lun Chao

AAAI 2023 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
Optimize fractal parameters with gradient descent rather than predict them with an inverse encoderIFS fractal reconstruction · FractalDB, MNIST, KMNIST, and FMNISTMSE: FractalDB: 0.3889 ± 0.0000 -> 0.0617±0.0009; MNIST: 0.1724 ± 0.0000 -> 0.0202 ± 0.0005; KMNIST: 0.3016 ± 0.0000 -> 0.078Improved
Use the Expectation rather than Fixed objective (ablation)IFS fractal reconstruction · FractalDB, MNIST, KMNIST, and FMNISTMSE: FractalDB: 0.0752±0.0027 -> 0.0630±0.0008; MNIST: 0.0312 ± 0.0002 -> 0.0223 ± 0.0004; KMNIST: 0.0979 ± 0.0008 -> 0.0826 Improved
Clamp rendered pixels to [0, 1] (ablation)IFS fractal reconstruction with the Fixed objective and no noisy SGD · FractalDB, MNIST, KMNIST, and FMNISTMSE: FractalDB: 0.0790±0.0006 -> 0.0752±0.0027; MNIST: 0.0475 ± 0.0012 -> 0.0312 ± 0.0002; KMNIST: 0.1023 ± 0.0016 -> 0.0979 Mixed
Add noisy SGD (ablation)IFS fractal reconstruction with the Expectation objective and clamping · FractalDB, MNIST, KMNIST, and FMNISTMSE: FractalDB: 0.0630±0.0008 -> 0.0617±0.0009; MNIST: 0.0223 ± 0.0004 -> 0.0202 ± 0.0005; KMNIST: 0.0826 ± 0.0010 -> 0.0781 Improved
Remove affine-matrix reparameterization (ablation)IFS fractal reconstruction · FractalDB, MNIST, KMNIST, and FMNISTMSEHurt
Increase the number of transformations from 2 to 6 (ablation)IFS fractal reconstruction · FractalDB and MNISTMSE: FractalDB: 0.0954±0.0035 -> 0.0687±0.0006; MNIST: 0.0423±0.0013 -> 0.0237±0.0015Improved
Increase the number of transformations from 6 to 10 (ablation)IFS fractal reconstruction · FractalDB and MNISTMSE: FractalDB: 0.0687±0.0006 -> 0.0627±0.0013; MNIST: 0.0237±0.0015 -> 0.0212±0.0009Improved
Replace Adam with SGD (ablation)IFS fractal reconstruction · MNISTMSE: 0.0212±0.0009 -> 0.0656±0.0014Hurt
Train fractal parameters with a GAN loss to match target image distributionsA set of 100 IFS fractals used for pre-training · MNIST, FMNIST, and KMNISTtest accuracyImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy