Demo Data from EDBT 2026 / reviewers in the wild / expert
David Yu Miller
dblp:350/4478
· DBLP profile ↗
2ranked-venue papers
0as first author
2since 2021 · last 2025
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 2 · 2 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
2 papers |
Deep learning architectures and training · 47% Optimization for machine learning · 33% Learning theory · 20% |
Topics — the 5 heaviest of 5, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Optimization for machine learning › hyperparameter optimization
hyperparameter sensitivity |
0.9 | 1 | 2025 | Gemstones: A Model Suite for Multi-Faceted Scaling Laws · NeurIPS 2025 |
Machine learning › Deep learning architectures and training
scaling laws |
0.9 | 1 | 2025 | Gemstones: A Model Suite for Multi-Faceted Scaling Laws · NeurIPS 2025 |
Machine learning › Learning theory › generalization
generalization theory |
0.7 | 1 | 2023 | Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent · ICLR 2023 |
Machine learning › Deep learning architectures and training
loss landscape |
0.7 | 1 | 2023 | Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent · ICLR 2023 |
Machine learning › Optimization for machine learning › gradient-based optimization
gradient descent |
0.2 | 1 | 2023 | Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent · ICLR 2023 |
Methods — techniques the papers use, named apart from their topics
scaling law fitting · 0.9loss landscape analysis · 0.7implicit bias analysis · 0.7
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | Gemstones: A Model Suite for Multi-Faceted Scaling LawsabstractScaling laws are typically fit using a family of models with a narrow range of frozen hyperparameter choices.
In this work we study scaling laws using multiple architectural shapes and hyperparameter choices, highlighting their impact on resulting prescriptions.
As a primary artifact of our research, we release the Gemstones: an open-source scaling law dataset, consisting of over 4000 checkpoints from transformers with up to 2 billion parameters and diverse architectural shapes; including ablations over learning rate and cooldown.
Our checkpoints enable more complex studies of scaling, such as analyzing the relationship between width and depth.
By examining our model suite, we find that the prescriptions of scaling laws can be highly sensitive to the experimental design process and the specific model checkpoints used during fitting. Sean McLeish, John Kirchenbauer, David Yu Miller, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein |
NeurIPS | 3 |
| 2023 | Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
Ping-Yeh Chiang, Renkun Ni, David Yu Miller, Arpit Bansal, Jonas Geiping, Micah Goldblum, Tom Goldstein |
ICLR | 3 |