Tag: generative-models
Concepts
- Autoregressive Generation: PixelCNN and WaveNet
- Beta-VAE and Disentanglement
- Classifier-Free Guidance
- Conditional GANs
- Conditional Variational Autoencoders
- CycleGAN and Unpaired Translation
- DCGAN Architecture Guidelines
- DDIM and Fast Diffusion Samplers
- Denoising Diffusion Probabilistic Models
- Diffusion Models for Synthetic Market Data
- Discriminative vs Generative Models
- Energy-Based Models
- Evaluating Synthetic Market Data
- GAN-Generated Market Scenarios
- Generative Adversarial Networks
- Generative Scenario Generation for Stress Tests
- Generative vs Discriminative Modeling
- Generative vs Discriminative Models
- Large Language Models
- Latent Diffusion Models
- Latent Variable Models and the ELBO
- Linear Discriminant Analysis
- Masked Autoregressive Flow
- Mode Collapse in GANs
- Normalizing Flows
- Posterior Collapse and KL Annealing
- Privacy and Memorisation in Synthetic Data
- Probabilistic Programming Languages
- QuantGAN for Financial Time Series
- RealNVP and Coupling Layers
- Score-Based Models and Langevin Dynamics
- Spectral Normalization for GAN Stability
- Stylized Facts as Generative Benchmarks
- The GAN Minimax Objective
- The Reparameterization Trick
- TimeGAN for Sequential Synthetic Data
- Variational Autoencoders
- Vector-Quantized VAE (VQ-VAE)
- The Wasserstein Distance
- Wasserstein GAN and Gradient Penalty