Stochastic Hyperparameter Optimization through Hypernetworks
Paper • 1802.09419 • Published • 1
Jonathan Lorraine's Papers
A collection of all of the papers from Jonathan Lorraine
-
-
Understanding Neural Architecture Search Techniques
Paper • 1904.00438 • Published • 1 -
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions
Paper • 1903.03088 • Published • 1 -
JacNet: Learning Functions with Structured Jacobians
Paper • 2408.13237 • Published • 1 -
Optimizing Millions of Hyperparameters by Implicit Differentiation
Paper • 1911.02590 • Published • 1 -
Meta-Learning to Improve Pre-Training
Paper • 2111.01754 • Published • 1 -
Input Convex Gradient Networks
Paper • 2111.12187 • Published • 1 -
Complex Momentum for Optimization in Games
Paper • 2102.08431 • Published • 1 -
Lyapunov Exponents for Diversity in Differentiable Games
Paper • 2112.14570 • Published • 1 -
On Implicit Bias in Overparameterized Bilevel Optimization
Paper • 2212.14032 • Published • 1 -
Task Selection for AutoML System Evaluation
Paper • 2208.12754 • Published • 1 -
ATT3D: Amortized Text-to-3D Object Synthesis
Paper • 2306.07349 • Published • 11 -
Using Large Language Models for Hyperparameter Optimization
Paper • 2312.04528 • Published • 1 -
Graph Metanetworks for Processing Diverse Neural Architectures
Paper • 2312.04501 • Published • 1 -
Training Data Attribution via Approximate Unrolled Differentiation
Paper • 2405.12186 • Published • 1 -
LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis
Paper • 2403.15385 • Published • 8 -
Scalable Nested Optimization for Deep Learning
Paper • 2407.01526 • Published • 4 -
Improving Hyperparameter Optimization with Checkpointed Model Weights
Paper • 2406.18630 • Published • 1 -
Multi-student Diffusion Distillation for Better One-step Generators
Paper • 2410.23274 • Published • 1 -
LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
Paper • 2411.09595 • Published • 77 -
Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond
Paper • 2505.04621 • Published • 2 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 71