Training generative neural networks via Maximum Mean Discrepancy\n optimization
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
We consider training a deep neural network to generate samples from an\nunknown distribution given i.i.d. data. We frame learning as an optimization\nminimizing a two-sample test statistic---informally speaking, a good generator\nnetwork produces samples that cause a two-sample test to fail to reject the\nnull hypothesis. As our two-sample test statistic, we use an unbiased estimate\nof the maximum mean discrepancy, which is the centerpiece of the nonparametric\nkernel two-sample test proposed by Gretton et al. (2012). We compare to the\nadversarial nets framework introduced by Goodfellow et al. (2014), in which\nlearning is a two-player game between a generator network and an adversarial\ndiscriminator network, both trained to outwit the other. From this perspective,\nthe MMD statistic plays the role of the discriminator. In addition to empirical\ncomparisons, we prove bounds on the generalization error incurred by optimizing\nthe empirical MMD.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it