Stochastic Sensitivity Regularized Autoencoder for Robust Feature Learning
Bibliographic record
Abstract
We present a new regularized autoencoder for robust feature learning. The regularization, implying stochastic sensitivity, is defined as the sum of entries of the absolute covariance matrix of the output perturbation at each layer of the autoencoder. The advantages of the stochastic sensitivity regularization are two-fold. Firstly, we show that the classical Frobenius norm regularization effectively enforces the network to be insensitive to input perturbation and that the Frobenius norm regularization is a special case of the proposed stochastic sensitivity regularization which enables the proposed method to train an autoencoder for robust feature learning. Secondly, we also show that the stochastic sensitivity regularization attempts to drive the network to learn a set of decorrelated feature maps which removes redundant information and thus improves generalization capabilities. These two properties enable the autoencoder to learn a set of robust and diverse feature maps. Finally, the efficacy and the robustness of the proposed regularization method are confirmed a nd quantified by comparing it against existing regularized auto encoders over a range of tasks.
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.
How this classification was reachedexpand
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".